Jev Users

The complete Jev app index

31 people in the Jev community each keep their own hand-picked list of projects worth using. This merges all 31 and ranks every project by how many of them picked it — so a small tool that experienced users keep recommending rises above a big repo nobody reaches for.

Apps indexed1299
Curators merged31
Picked by 2+816
Also in Top 100214

The number on the left is how many of the 31 curators picked that project — it is not a rank, and it is not related to stars.

Picked byProjectStars
  1. 28of 31 browser-use/jev-ultrafast in Top 100 Browser Jev chooses the browser operation and element while a smaller model writes text, keeping action selection explicit. Picked by Anil-matcha, yibie, v-modal and 25 more 11.4k★
  2. 26of 31 tamaratran/fast-jev-compaction in Top 100 Coding Agent Context management: Claude Code plugin that replaces the compaction summary with Jev decisions, scoring every tool call and result for whether it is still needed instead of summarizing the… Picked by yibie, v-modal, cobanov and 23 more 5.0k★
  3. 26of 31 devagrawal09/jev-review in Top 100 Coding Agent Software engineering: staged code-review workflow and local dashboard where Jev gates each review stage before a change advances. Picked by yibie, v-modal, AbdelStark and 23 more 402★
  4. 25of 31 jarrodwatts/jev-trader in Top 100 Other Experimental sub-second market-side decision loop; the project documents a default dry-run and a separate live-trading path. Picked by Anil-matcha, cobanov, logicrw and 22 more 1.5k★
  5. 25of 31 fhshaik/typesafe-mario in Top 100 Other Uses structured emulator state and typed decisions for game control. Picked by Anil-matcha, yibie, v-modal and 22 more 295★
  6. 25of 31 RomanSlack/jev-drone in Top 100 Home & IoT Experimental MuJoCo quadrotor control loop with Jev in the decision path. Picked by Anil-matcha, yibie, v-modal and 22 more 85★
  7. 23of 31 thruwire/foreman in Top 100 Coding Agent Software factory: sits above Codex workers and has Jev independently judge whether an implementation is complete, its tests sufficient, or a human is needed. Picked by yibie, v-modal, cobanov and 20 more 427★
  8. 23of 31 superagents-lab/jev-search in Top 100 Search Jev Search - Web search: uses Jev Noul judgments on result titles and snippets to rank Search1API results by relevance, with application code merging duplicate URLs and grouping… Picked by Anil-matcha, yibie, v-modal and 20 more 289★
  9. 23of 31 DevMortimer/pi-warden in Top 100 Other Pi guardrails built on pi-typesafe that return Jev's verdict to the agent as a held tool result or a short steer instead of a dialog, check writes against a project rules file, and grade… Picked by AbdelStark, cobanov, logicrw and 20 more 104★
  10. 23of 31 AboveColin/HA-Jev in Top 100 Home & IoT Expose `Noul`, `Choice`, and `Score` answers as automation entities and actions for household workflows. Picked by Anil-matcha, yibie, v-modal and 20 more 33★
  11. 23of 31 typesafe-ai/skills Other Official agent skills repository Picked by Anil-matcha, yibie, v-modal and 20 more
  12. 22of 31 jkudish/jev-mcp in Top 100 Coding Agent Give coding agents typed claim verification, content screening, and semantic ranking tools. Picked by Anil-matcha, yibie, v-modal and 19 more 150★
  13. 22of 31 itsmostafa/typesafe-mcp in Top 100 Coding Agent Go MCP server and CLI for exposing typed Jev decisions to coding agents and automation. Picked by Anil-matcha, AbdelStark, cobanov and 19 more 133★
  14. 22of 31 typesafe-ai/typesafe-sdk-js SDK & Runtime See the official Python SDK, official JavaScript SDK, and Quick start for the supported client options. Picked by Anil-matcha, AbdelStark, cobanov and 19 more
  15. 22of 31 typesafe-ai/typesafe-sdk-python SDK & Runtime See the official Python SDK, official JavaScript SDK, and Quick start for the supported client options. Picked by Anil-matcha, AbdelStark, cobanov and 19 more
  16. 21of 31 droidrun/mobile-jev in Top 100 Mobile Android agent using Mobilerun observations and bounded Jev actions; execute mode controls a real device, while the published Uber demo stops before booking. Picked by cobanov, logicrw, fatwang2 and 18 more 266★
  17. 21of 31 pithings/advocaat in Top 100 SDK & Runtime Data tooling: small type-safe client for asking Jev questions about a dataset. Picked by yibie, v-modal, AbdelStark and 18 more 86★
  18. 21of 31 awlevin/typesafe-computer-use Computer Use macOS computer-use experiment using OCR plus bounded Jev action selection. Picked by cobanov, logicrw, fatwang2 and 18 more
  19. 20of 31 vinnylarouge/jevlike in Top 100 Other Training library: build a small model that chooses among a changing list of text options and returns one probability per option in a single pass - the base CUA-S1-FORMS was built on. Picked by yibie, v-modal, cobanov and 17 more 1.1k★
  20. 20of 31 gargpratyush/jev-router in Top 100 Routing Developer tooling: routes Claude Code tasks to the cheapest capable model by asking Jev to choose among candidates. Picked by yibie, v-modal, cobanov and 17 more 251★
  21. 20of 31 y0usaf/pi-jev in Top 100 Coding Agent Agent safety: adds a measured tool-call gate to the Pi coding agent so risky calls are checked by Jev before execution. Picked by yibie, v-modal, AbdelStark and 17 more 116★
  22. 20of 31 yusukebe/hono-jev-router in Top 100 Search Web frameworks: Hono middleware that routes HTTP requests by meaning rather than by method and path, deciding with Jev. Picked by yibie, v-modal, cobanov and 17 more 41★
  23. 20of 31 phyous/tsai-sc in Top 100 Other Gaming: drives original StarCraft shareware through keyboard and mouse with Jev action probabilities recorded per decision. Picked by yibie, v-modal, AbdelStark and 17 more 19★
  24. 19of 31 realZachi/pg-jev in Top 100 Data PostgreSQL extension for asking typed semantic questions over table data. Picked by Anil-matcha, cobanov, logicrw and 16 more 245★
  25. 19of 31 iammrduncan/typesafe-ai-benchmark in Top 100 Routing A benchmark project for TypeSafe-shaped decisions; record whether a run uses the official API, a gateway, or an adapter. Picked by Anil-matcha, AbdelStark, cobanov and 16 more 34★
  26. 19of 31 typesafe-ai/system-one-adapter-python Eval & Align A drop-in System One-shaped adapter backed by OpenAI, Anthropic, or OpenAI-compatible models; useful for comparison and development, not a substitute for production Jev calibration. Picked by Anil-matcha, AbdelStark, cobanov and 16 more
  27. 18of 31 kitze/unclutter in Top 100 Browser Browser tooling: WXT extension where Jev decides per page element whether it is clutter, removing it under reusable template rules. Picked by yibie, v-modal, cobanov and 15 more 143★
  28. 18of 31 0xNatoshi/jev-codex-router in Top 100 Computer Use Per-turn Codex model, reasoning, and speed-mode routing. Picked by cobanov, logicrw, fatwang2 and 15 more 83★
  29. 18of 31 realZachi/typesafe-adblock in Top 100 Browser Browser tooling: Chrome extension that asks Jev whether each DOM element is an ad, turning ad blocking into a stream of per-element typed questions. Picked by yibie, v-modal, logicrw and 15 more 59★
  30. 18of 31 dannote/jev in Top 100 Other (Elixir) - Elixir ecosystem: GenServer client that replies with Jev's answer so callers can pattern match on it directly. Picked by yibie, v-modal, cobanov and 15 more 19★
  31. 18of 31 shiftynick/jev-axi in Top 100 Coding Agent Command-line primitives for picking, rating, checking, ranking, triaging, and guarding actions. Picked by Anil-matcha, yibie, v-modal and 15 more 17★
  32. 18of 31 valentynkit/jev-belay Coding Agent Claude Code Stop hook that checks transcript evidence before trusting a "done" claim, spending one four-question Jev call only when files changed with no passing check since, and failing… Picked by Anil-matcha, yibie, v-modal and 15 more
  33. 17of 31 NiazMorshed2007/jev-review in Top 100 Coding Agent MCP plugin - Local-first continuous software-quality review for coding agents. Picked by cobanov, logicrw, AnotiaWang and 14 more 180★
  34. 17of 31 jexp/neo4jev in Top 100 Other Navigates a Neo4j graph one hop at a time, asking Jev which relationship to follow next. Picked by logicrw, fatwang2, AnotiaWang and 14 more 46★
  35. 17of 31 ellipsis-dev/blink in Top 100 Search Navigates file and directory names with Jev-guided walkers to find codebase paths for a natural-language query. Picked by cobanov, logicrw, fatwang2 and 14 more 27★
  36. 16of 31 jkudish/jev-browser in Top 100 Browser Jev Browser - Browser automation: drives a browser with Jev deciding each step, pitched as fast and very cheap next to LLM-driven browsing. Picked by yibie, v-modal, cobanov and 13 more 180★
  37. 16of 31 Dicklesworthstone/skillranker in Top 100 Coding Agent Rust CLI that ranks agent skills against live session context and can abstain. Picked by cobanov, AnotiaWang, valentynkit and 13 more 91★
  38. 16of 31 ChetasLua/jevmeter in Top 100 Other Scores every sentence in a video and renders the result as an overlay. Picked by cobanov, logicrw, AnotiaWang and 13 more 75★
  39. 16of 31 mrnugget/jev-shell-history in Top 100 Search Ranks existing zsh history entries for inline completion; accepting a suggestion does not execute it. Picked by cobanov, logicrw, AnotiaWang and 13 more 69★
  40. 16of 31 blakestone-x/jev-mcp in Top 100 Computer Use (blakestone-x) - MCP ecosystem: MCP server exposing Jev classify, score, check, match, and screen as tools for any agent, with confidence on every answer. Picked by yibie, v-modal, AbdelStark and 13 more 14★
  41. 16of 31 abhixhek/jevcal Eval & Align Fits per-question confidence thresholds on labelled data, verifies them on a held-out split, and writes a calibration lock file. Picked by Anil-matcha, yibie, v-modal and 13 more
  42. 16of 31 valentynkit/jev-plays-pokemon-red Routing Real-time game control on PyBoy: deterministic code owns the route and arithmetic while Jev picks only at branches, and each battle turn's faint prediction is scored by Brier against RAM… Picked by Anil-matcha, yibie, v-modal and 13 more
  43. 16of 31 valentynkit/jev-skip Browser Browser extension that reads the YouTube caption track and paints a per-segment sponsor probability on the seek bar before the intro ends, with no crowd database. Picked by Anil-matcha, yibie, v-modal and 13 more
  44. 16of 31 valentynkit/jev.nvim Search Neovim plugin that splits the buffer into functions with Treesitter, scores each against a plain-language question with Jev, and lists answers in the quickfix window ranked by probability. Picked by Anil-matcha, yibie, v-modal and 13 more
  45. 15of 31 TheoLeeCJ/SemIf in Top 100 Search Formerly OpenJev: an independent study of typed option readout from frozen open models, with shared-prefix experiments and a WebGPU demo. Picked by cobanov, valentynkit, hellogumbo and 12 more 2.3k★
  46. 15of 31 BillionsBobby/JevRouter in Top 100 Routing Model, tool, and subagent routing: Jev answers one typed `Choice` over a candidate capability set while router code owns availability, permissions, risk, confirmation, and fallback policy. Picked by Anil-matcha, cobanov, logicrw and 12 more 109★
  47. 15of 31 vinilana/jev-eval-agent in Top 100 Eval & Align Compares LLM tool selection with Jev routing in a personal-assistant harness containing 100 mocked tools. Picked by cobanov, logicrw, AnotiaWang and 12 more 96★
  48. 15of 31 giuliosmall/pg_typesafe in Top 100 Data Pre-alpha PostgreSQL C extension exposing Choice, Noul, Score, and batched judgments from SQL. Picked by cobanov, logicrw, fatwang2 and 12 more 79★
  49. 15of 31 supercorp-ai/supercov in Top 100 Coding Agent Code quality and coverage for coding agents. Picked by Anil-matcha, yibie, v-modal and 12 more 74★
  50. 15of 31 bnsd55/jevmlx in Top 100 SDK & Runtime Jev-style parallel decisions on MLX for local experimentation; compare semantics and calibration separately from hosted Jev. Picked by Anil-matcha, cobanov, AnotiaWang and 12 more 44★
  51. 15of 31 aowang-ai/jev-trade in Top 100 Other Each Hyperliquid tick is evaluated as book, tape, and position state; Jev answers `Choice` questions for long/short, open/close/hold, and leverage; application code owns quoting and whether… Picked by Anil-matcha, yibie, v-modal and 12 more 39★
  52. 15of 31 leepokai/jev-guard in Top 100 Coding Agent Experimental tool-call risk scoring with explicit deny, ask, and allow outcomes. Picked by Anil-matcha, yibie, v-modal and 12 more 12★
  53. 15of 31 Mapika/decider Eval & Align Open models: reproduces the System One shape with a Qwen3.5-2B fine-tune that emits typed decisions with calibrated probabilities in one pass. Picked by yibie, v-modal, AnotiaWang and 12 more
  54. 15of 31 kylemclaren/jevql Data Adds Jev `Noul`, `Choice`, and `Score` filters, probability sorts, and choice groups to semantic SQL over Postgres. Picked by Anil-matcha, yibie, v-modal and 12 more
  55. 15of 31 valentynkit/jev-commit Other Pre-commit hook that uses one Jev call to check whether the commit message matches the staged diff, flags debug leftovers and unmentioned work, and blocks only when it detects a credential. Picked by Anil-matcha, yibie, v-modal and 12 more
  56. 14of 31 TianyuCodings/NanoJev in Top 100 Other Open replica: a 0.6B parallel decision model that returns full probability distributions with no output-token decoding, shipped with its training pipeline, weights, and dataset. Picked by yibie, v-modal, cobanov and 11 more 1.3k★
  57. 14of 31 ekzhang/openjev-sglang in Top 100 SDK & Runtime Jev-inspired/open-model infrastructure; it is not the hosted TypeSafe Jev model. Picked by Anil-matcha, cobanov, valentynkit and 11 more 216★
  58. 14of 31 moritzkremb/jev-voice-browser in Top 100 Browser Maps partial speech transcripts to browser intents and observed targets, with code deciding whether to act, wait, or ask. Picked by cobanov, logicrw, valentynkit and 11 more 152★
  59. 14of 31 Ying-Kai-Liao/jev-browser in Top 100 Browser A browser library, CLI and MCP server where the caller supplies goals and text while Jev selects actions. Picked by logicrw, fatwang2, AnotiaWang and 11 more 47★
  60. 14of 31 nshkrdotcom/typesafe_sdk in Top 100 SDK & Runtime Elixir SDK for TypeSafe AI and Jev with typed Choice, Score, and Noul structs, configurable retries, and upstream API parity. Picked by AbdelStark, logicrw, fatwang2 and 11 more 3★
  61. 14of 31 AkashPriyadarshii/jev-curate Eval & Align High-throughput synthetic dataset sifter in Rust: evaluates JSONL and Parquet rows via Jev Noul checks and streams clean/rejected rows to disk. Picked by Anil-matcha, yibie, v-modal and 11 more
  62. 14of 31 Butochnikov/laravel-typesafe-jev Other PHP ecosystem: unofficial Laravel integration for Jev with typed responses, async requests, scoped dependency injection, and testing fakes. Picked by yibie, v-modal, cobanov and 11 more
  63. 14of 31 Twister915/typesafe-ai SDK & Runtime Rust client with asynchronous and blocking transports, typed responses, observable retries, and inspectable errors. Picked by AbdelStark, logicrw, fatwang2 and 11 more
  64. 14of 31 anessbelbati/jev-rerank-bench Eval & Align Reranking comparison with raw provider responses, scoring code, dataset-level results, uncertainty intervals, and documented limitations. Picked by AbdelStark, cobanov, logicrw and 11 more
  65. 14of 31 reachjalil/jev-tree Routing Hierarchical decision-tree workflow for routing high-cardinality categories with Jev. Picked by Anil-matcha, cobanov, logicrw and 11 more
  66. 14of 31 reachjalil/jevlogs Eval & Align Annotate OpenTelemetry/log records with Jev decisions and optionally skip expensive analysis for low-value traces. Picked by Anil-matcha, cobanov, logicrw and 11 more
  67. 14of 31 zhengxuyu/litjev SDK & Runtime Local reproduction: a reproduction of Jev that turns any Qwen model into a fast decision model, serving the same `/v1/systemone` schema (Choice, Score, Noul) with no training and no… Picked by yibie, v-modal, cobanov and 11 more
  68. 13of 31 jaredpalmer/kev in Top 100 Other Trainable replica: a tiny Jev-like model on top of Qwen2.5-0.5B that trains and runs on a MacBook, shipped with its own research runs and evaluation scripts. Picked by yibie, v-modal, cobanov and 10 more 893★
  69. 13of 31 brainstormity/Jev-Moderation-Bot in Top 100 Other Jev Moderation Bot - Community moderation: Discord bot that scores incoming messages for phishing, spam, and social engineering with Jev and drives a four-stage escalation ladder, injecting… Picked by yibie, v-modal, logicrw and 10 more 39★
  70. 13of 31 shantanugoel/ask-jev-skill in Top 100 Coding Agent A skill for Hermes and other agents to query TypeSafe Jev for bounded option judgments and confidence escalations. Picked by logicrw, AnotiaWang, valentynkit and 10 more 35★
  71. 13of 31 sorrycc/typesafe-snake in Top 100 Other Real-time game control: code generates legal moves and exact state facts, while Jev chooses one move per tick. Picked by Anil-matcha, cobanov, logicrw and 10 more 18★
  72. 13of 31 jomatsu/pi-jev-auto-mode in Top 100 Coding Agent Adds rule checks to Pi commands and file operations, then uses Jev to assess cases that need further judgment. Picked by logicrw, AnotiaWang, valentynkit and 10 more 17★
  73. 13of 31 OmniJev/PlayJev in Top 100 Browser Open 0.8B model that reads a game frame and scores the moves the game lists in one forward pass; weights, games and the reproduction script are public, and it is not the hosted Jev model. Picked by Anil-matcha, yibie, v-modal and 10 more 10★
  74. 13of 31 shitianfang/jev-use in Top 100 Coding Agent Claude Code / Codex / pi plugin that hands steps needing no text output to Jev: MCP tools batch typed `Noul`/`Choice`/`Score` questions about agent state, and a typed escalation contract… Picked by Anil-matcha, yibie, v-modal and 10 more 10★
  75. 13of 31 AbdelStark/jev-benchmarks Eval & Align Useful for comparing decision quality and operational behavior; inspect the dataset and protocol before reusing a number. Picked by Anil-matcha, cobanov, logicrw and 10 more
  76. 13of 31 TokenTrim/jev-agent-failure-benchmark Eval & Align A benchmark using Jev to attribute multi-Agent failures to an Agent, step and error type. Picked by logicrw, AnotiaWang, valentynkit and 10 more
  77. 13of 31 WiktorB2004/llama-index-jev Search LlamaIndex Jev - Retrieval / RAG: unofficial LlamaIndex adapter where Jev `Score`s each retrieved passage and `Choice`/`Noul` selects the query engine, with nfcorpus nDCG@5 0.340→0.396 at… Picked by yibie, v-modal, AbdelStark and 10 more
  78. 13of 31 doeixd/jev-pref Coding Agent Semantic code review: project preferences from AGENTS.md are encoded as rules in `jev-pref.json` and checked with Jev against diff hunks, staged files, or PRs; findings are fed back to the… Picked by Anil-matcha, yibie, v-modal and 10 more
  79. 13of 31 jamesward/zio-typesafe-ai SDK & Runtime Scala ecosystem: ZIO client for TypeSafe AI with a typed DSL over Jev decisions. Picked by yibie, v-modal, logicrw and 10 more
  80. 13of 31 joshmn/typesafe-sdk SDK & Runtime Community Ruby client for TypeSafe's System One API with typed Noul, Choice, and Score questions, retries, model listing, and thread-safe pooled HTTP connections; requires Ruby 3.1 or newer… Picked by AbdelStark, logicrw, fatwang2 and 10 more
  81. 13of 31 kieranklaassen/ruby_llm-typesafe Other TypeSafe provider for RubyLLM 2 with offline model metadata and typed responses. Picked by AbdelStark, logicrw, fatwang2 and 10 more
  82. 12of 31 wy-coliney/jev-browser-use in Top 100 Browser Codex browser skill that uses Jev for navigation and target selection while Codex handles text entry and outcome verification. Picked by cobanov, logicrw, valentynkit and 9 more 245★
  83. 12of 31 kitze/skillbox in Top 100 Coding Agent Skills infrastructure: self-hosted versioned skills library that adds optional Jev recommendations using your own TypeSafe or Gateway key. Picked by yibie, v-modal, cobanov and 9 more 214★
  84. 12of 31 standardagents/jevpilot in Top 100 Other Three.js driving simulation where Jev chooses among candidate paths and speeds while local code handles vehicle dynamics and geometry. Picked by cobanov, logicrw, valentynkit and 9 more 115★
  85. 12of 31 GhalebDweikat/winnow in Top 100 Coding Agent Judges tool results before admitting them into Claude Code context. Picked by cobanov, logicrw, fatwang2 and 9 more 31★
  86. 12of 31 devanshbatham/commit-miner in Top 100 Other Classifies Git diffs and commit messages into change types and candidate security-fix/CWE labels for inspection. Picked by cobanov, logicrw, AnotiaWang and 9 more 29★
  87. 12of 31 compozy/yoshi in Top 100 Coding Agent Context management: proxy for Claude Code and Codex where Jev judges which conversation history is still needed before pruning. Picked by yibie, v-modal, cobanov and 9 more 19★
  88. 12of 31 AkashPriyadarshii/jev-seo in Top 100 Coding Agent Zero-cost agent-first SEO and GEO search radar CLI and MCP server. Picked by Anil-matcha, yibie, v-modal and 9 more 17★
  89. 12of 31 Gaurav-Gosain/jev-go in Top 100 Eval & Align A Go TypeSafe System One client with typed questions, answers and batching helpers. Picked by logicrw, fatwang2, AnotiaWang and 9 more 3★
  90. 12of 31 Gaurav-Gosain/jev-sec-bench in Top 100 Other Blind prompt-injection and vulnerable-code detection benches on public corpora, built on jev-go. Picked by AnotiaWang, valentynkit, hellogumbo and 9 more 2★
  91. 12of 31 AboveColin/jevclient SDK & Runtime Async Python client for typed Jev questions and probabilities. Picked by cobanov, logicrw, fatwang2 and 9 more
  92. 12of 31 Stumble/jev-go SDK & Runtime Go ecosystem: community Go SDK for Jev. Picked by yibie, v-modal, logicrw and 9 more
  93. 12of 31 bitnovus/jev-spam-eval Eval & Align Spam filtering: zero-shot spam classification with Jev `Boolean` questions, benchmarked against TF-IDF baselines. Picked by yibie, v-modal, AbdelStark and 9 more
  94. 12of 31 gilljon/typesafe-ai-rs SDK & Runtime An independently maintained Rust SDK with async and blocking clients, retries and response metadata. Picked by logicrw, fatwang2, AnotiaWang and 9 more
  95. 11of 31 hr98w/jev-visual in Top 100 SDK & Runtime Jev Visual - Educational MLX/Qwen vision-language experiment sharing image context across candidate-scoring questions; its probabilities are not calibrated correctness estimates. Picked by cobanov, AnotiaWang, valentynkit and 8 more 167★
  96. 11of 31 dbreunig/building-with-jev-skill in Top 100 Coding Agent Building with Jev - Community agent skill covering question design, state preparation, confidence thresholds, and debugging decisions. Picked by cobanov, valentynkit, hellogumbo and 8 more 126★
  97. 11of 31 tamaratran/jev-pruner in Top 100 Coding Agent Context management: Claude Code plugin that trims long Bash output with Jev before the model ever sees it, keeping terminal noise out of the window. Picked by yibie, v-modal, logicrw and 8 more 126★
  98. 11of 31 trungdq88/youtube-sponsor-detection in Top 100 Other Sponsor Skip - Finds sponsor reads in YouTube transcripts or transcribed audio while code owns timestamps and playback skipping. Picked by cobanov, logicrw, valentynkit and 8 more 78★
  99. 11of 31 obie/ruby_decision_model in Top 100 SDK & Runtime Ruby ecosystem: client for decision models such as Jev, so Ruby applications can put typed questions directly to the model. Picked by yibie, v-modal, cobanov and 8 more 46★
  100. 11of 31 socai-io/jev-social in Top 100 Browser Social research routing: Jev `Choice` selects the platform and bounded socai operation from observed state, while code rejects malformed or low-confidence decisions before the local CLI… Picked by Anil-matcha, yibie, v-modal and 8 more 21★
  101. 11of 31 TheoOliveira/pi-jev in Top 100 Coding Agent (TheoOliveira) - Coding agents: semantic tool routing and typed System One decisions for the Pi coding agent. Picked by yibie, v-modal, logicrw and 8 more 20★
  102. 11of 31 zhihz/openjev in Top 100 SDK & Runtime Open research: independent local preview that answers bilingual probability questions from context, questions, and candidate answers, inspired by TypeSafe Jev. Picked by yibie, v-modal, cobanov and 8 more 20★
  103. 11of 31 24601/Augustus in Top 100 Coding Agent Coding agents: agent skill that maps Choice, Score, and Noul onto classical methods so an agent can place typed judgment in software, with a composition algebra, question-design diagnosis… Picked by Anil-matcha, yibie, v-modal and 8 more 5★
  104. 11of 31 joelhooks/pi-fast-jev-compaction Coding Agent Context management: Pi extension that keeps conversation text verbatim while pruning stale tool history with Jev, falling back to Pi's own summarization only when pruning cannot free enough… Picked by yibie, v-modal, cobanov and 8 more
  105. 11of 31 romaluev/jev-ego Browser A browser Agent for ego lite that numbers actionable elements for Jev to choose the next step. Picked by logicrw, fatwang2, AnotiaWang and 8 more
  106. 11of 31 saibimajdi/typesafeai-dotnet-sdk Eval & Align Community .NET SDK for TypeSafe AI and Jev, providing asynchronous typed evaluation for Choice, Score, and Noul primitives. Picked by logicrw, fatwang2, valentynkit and 8 more
  107. 11of 31 sharziki/semdecide Search Typed semantic decisions for Unix pipelines and CI. Picked by cobanov, logicrw, fatwang2 and 8 more
  108. 11of 31 sufianetaouil/every Search Semantic code search CLI that asks a yes/no question of every function and ranks the resulting probabilities. Picked by AbdelStark, logicrw, AnotiaWang and 8 more
  109. 11of 31 zhuyansen/jev-search-rerank-eval Search Chinese/English retrieval evaluation comparing Jev reranking with lexical, embedding, and fusion baselines, including judge-circularity analysis. Picked by cobanov, logicrw, AnotiaWang and 8 more
  110. 10of 31 razorback16/openjev in Top 100 SDK & Runtime (DiffusionGemma) - Independent Jev-compatible server over DiffusionGemma/vLLM; the documented setup requires custom vLLM patches. Picked by cobanov, logicrw, valentynkit and 7 more 192★
  111. 10of 31 Kevthetech143/super-jev in Top 100 Other Decision harness: turns a Jev answer into a bounded action instead of leaving the caller to interpret it. Picked by yibie, v-modal, logicrw and 7 more 6★
  112. 10of 31 lbotinelly/jev-little-airways in Top 100 Other An island-airport simulator using Jev for routes, yielding, emergency broadcasts and landing order. Picked by logicrw, AnotiaWang, valentynkit and 7 more 4★
  113. 10of 31 AbdelStark/bicameral Other Pi coding harness where an LLM writes while Jev supplies typed reflexes for policy, loop detection, and review; explicitly not a sandbox. Picked by AbdelStark, AnotiaWang, valentynkit and 7 more
  114. 10of 31 AbdelStark/typesafe-rs SDK & Runtime Latency-focused Rust transport SDK designed around behavioral parity with the official clients. Picked by AbdelStark, logicrw, fatwang2 and 7 more
  115. 10of 31 AkashPriyadarshii/jev-scout Coding Agent Open-source repository and crate scout powered by Jev scoring, with Rust, CLI, and MCP surfaces. Picked by Anil-matcha, yibie, v-modal and 7 more
  116. 10of 31 AntonioCoppe/jev-harness Eval & Align Unofficial production layer around Jev: policy, confidence gate, shadow mode, recipes, and an eval CLI Picked by AnotiaWang, valentynkit, hellogumbo and 7 more
  117. 10of 31 GenieRobot/typesafe-ai-rails SDK & Runtime Community Rails integration for TypeSafe's System One API, built on typesafe-sdk, with Rails configuration, persisted usage and cost telemetry, and opt-in confidence policies for Choice and… Picked by AbdelStark, logicrw, fatwang2 and 7 more
  118. 10of 31 andrelandgraf/safer-with-jev Routing Cloud infrastructure: Neon Function proxy for the Neon AI Gateway that routes decisions with Jev. Picked by yibie, v-modal, logicrw and 7 more
  119. 10of 31 chy4pro/jev-for-chrome Browser Unofficial Chrome extension port of Jev Ultrafast: one Jev request per step selects the operation and DOM element, code owns the loop, budgets and stale checks, and two Noul cross-checks… Picked by Anil-matcha, yibie, v-modal and 7 more
  120. 10of 31 mejiasd3v/pi-jev-router Coding Agent Coding agents: adds automatic per-request model routing to the Pi coding agent through Jev decisions on Vercel AI Gateway. Picked by yibie, v-modal, logicrw and 7 more
  121. 10of 31 prismhq/jev-router Routing (prismhq) - LLM infrastructure: open-source LiteLLM-based router where a Jev decision picks which model serves each request. Picked by yibie, v-modal, logicrw and 7 more
  122. 10of 31 samtay32/jev-system-architect Coding Agent Skill that hunts for brittle semantic logic and turns it into Choice / Score / Noul boundaries. Picked by AnotiaWang, valentynkit, hellogumbo and 7 more
  123. 10of 31 tumf/jev-cli Other Developer tooling: small dependency-free CLI for Jev. Picked by yibie, v-modal, logicrw and 7 more
  124. 10of 31 vercel/eve Eval & Align Agent frameworks: Vercel's eve engine ships Jev as the default evaluation model (`typesafe-ai/jev`) in its experimental evaluate path. Picked by yibie, v-modal, AnotiaWang and 7 more
  125. 9of 31 featherless-ai/simple-jev in Top 100 Other Simple Jev - Transforms compatible open-model logits into typed decisions without a separately trained classifier head; model compatibility is constrained. Picked by cobanov, logicrw, valentynkit and 6 more 378★
  126. 9of 31 dabit3/jev-experiments in Top 100 Other Demo collection: 22 latency-focused Jev applications built by Devin, each with its own README and testing notes, spanning shell guards, log sentinels, instant search, reranking, and voice… Picked by yibie, v-modal, cobanov and 6 more 332★
  127. 9of 31 kyotofin/tax-doc-classifier in Top 100 Eval & Align Classifies text-bearing PDF pages into IRS form and page-kind candidates with a confidence gate; document triage, not tax advice, and scanned pages need OCR. Picked by cobanov, logicrw, valentynkit and 6 more 293★
  128. 9of 31 sutro-sh/jev-align in Top 100 Eval & Align Active-learning CLI that evaluates tabular rows with Jev `Choice`, `Score`, or `Noul` questions, sends uncertain and audit samples to a human, and uses GEPA to propose revised definitions… Picked by Anil-matcha, yibie, AbdelStark and 6 more 232★
  129. 9of 31 wfzyx/von in Top 100 SDK & Runtime Open alternative: a 395M non-autoregressive System One model that answers typed questions with calibrated probabilities in under 15 ms, positioned as a local drop-in replacement for Jev. Picked by yibie, v-modal, valentynkit and 6 more 143★
  130. 9of 31 uehaj/jev-semgrep in Top 100 Search Semantic search: greps by meaning across languages, having Jev score every line against a meaning and letting meanings combine with AND, backed by a 13-file test suite. Picked by yibie, logicrw, hellogumbo and 6 more 114★
  131. 9of 31 RafalWilinski/vibecheck in Top 100 Browser Vibe Check for X - Chrome extension that scores draft posts and reply context before posting; optional media descriptions come from a separate vision model. Picked by cobanov, logicrw, valentynkit and 6 more 44★
  132. 9of 31 r-ms/mini-jev in Top 100 Other Local reproduction: implements Jev's typed-decision interface on top of a local LLM. Picked by yibie, v-modal, valentynkit and 6 more 29★
  133. 9of 31 zadescoxp/Jev-Trades in Top 100 Other A dashboard combining live crypto market data with Jev-guided paper trading; no broker or live-order API is connected. Picked by logicrw, fatwang2, valentynkit and 6 more 18★
  134. 9of 31 Brainwires/jevwire in Top 100 Coding Agent MCP tools, an embeddable decision library, and advisory or restrictive Claude Code hooks; judgments do not grant native permissions. Picked by cobanov, logicrw, valentynkit and 6 more 13★
  135. 9of 31 Nasrallah-AL/jev-cli in Top 100 Search The jevctl command-line tool connects verification, classification and scoring questions to text input and scripts. Picked by AbdelStark, logicrw, valentynkit and 6 more 12★
  136. 9of 31 GodsBoy/jev-agent-skill-router in Top 100 Coding Agent Agent infrastructure: routes agent skill selection through typed, confidence-aware Jev decisions so weak matches are declined instead of guessed. Picked by yibie, v-modal, valentynkit and 6 more 11★
  137. 9of 31 anpicasso/hermes-jev-approvals in Top 100 Other Agent approvals: proof of concept that puts Jev in front of Hermes Agent's command approvals, reporting 8.7x faster decisions and 4.4x fewer prompts to the user. Picked by yibie, v-modal, logicrw and 6 more 9★
  138. 9of 31 AbdelStark/s1-rs Other Rust derive layer for Choice, Score, Noul, typed question sets, confidence gates, and network-free testing. Picked by AbdelStark, AnotiaWang, valentynkit and 6 more
  139. 9of 31 DanRWilloughby/snifftest Coding Agent Sniff Test - Writing: prose linter that asks Jev ten `Boolean` questions per paragraph (stacked hedges, restating closers, not-X-but-Y turns, naked cost figures) at a 0.7 threshold; CLI… Picked by yibie, v-modal, logicrw and 6 more
  140. 9of 31 DevMortimer/pi-typesafe SDK & Runtime Pi extension and library that gives the agent and other extensions one consented, key-managed TypeSafe client with a batched `typesafe_evaluate` tool and offline-testable transport… Picked by AbdelStark, logicrw, AnotiaWang and 6 more
  141. 9of 31 GiesN/typesafe-jev-workflow Routing Jev email intent workflow - Back-office automation: async LangGraph workflow gets a typed Jev `Choice` (`invoice` or `general`) and routes each inbound email to the matching handler. Picked by yibie, v-modal, cobanov and 6 more
  142. 9of 31 HyunjunJeon/jev-judgment Coding Agent Coding agents: agent skill that sends closed coding-agent judgments to Jev so verdicts stay typed, cheap, and comparable across runs. Picked by yibie, v-modal, logicrw and 6 more
  143. 9of 31 TarunTomar122/jev-askable-arm Home & IoT Uses Jev to chain predefined skills for English-language goals in a ManiSkill robot-arm simulation. Picked by logicrw, AnotiaWang, valentynkit and 6 more
  144. 9of 31 alterhq/typesafe-sdk-swift SDK & Runtime Swift 6 client for Jev `Choice`, `Score`, and `Noul` questions with strict concurrency, application-owned authentication and retry policy, and network-free tests. Picked by Anil-matcha, yibie, v-modal and 6 more
  145. 9of 31 anisselbd/jev-phishing-bench Eval & Align Jev Phishing Bench - 2,000 emails: Jev vs Claude Haiku 4.5 on click-or-not, with calibration, latency, and cost. Haiku wins accuracy here. Picked by AnotiaWang, valentynkit, hellogumbo and 6 more
  146. 9of 31 gamesonrblx/Jevbridge Other Agent integration bridge that makes Jev decisions available alongside coding-workflow tools. Picked by Anil-matcha, cobanov, logicrw and 6 more
  147. 9of 31 gtaras7/typesafe-jev Other CV screener - Recruiting: screens a folder of CVs with Jev typed judgments against an editable policy, re-scoring candidates for free when the policy changes. Picked by yibie, v-modal, valentynkit and 6 more
  148. 9of 31 keeltrace/hermes-jev Other An asynchronous Jev companion for Hermes Agent covering relevance, completion, recovery and optional admission decisions. Picked by logicrw, fatwang2, valentynkit and 6 more
  149. 9of 31 lukaske/jev-doom-agent Browser A browser Doom experiment comparing Jev-controlled players from the same initial state. Picked by logicrw, AnotiaWang, valentynkit and 6 more
  150. 9of 31 replynodes/jev-web-analyzer Eval & Align Public SaaS landing-page evaluation: clean Markdown is the state and ten bounded `Choice` questions ask what a first-time visitor is likely to understand; URL validation, SSRF protection… Picked by Anil-matcha, yibie, cobanov and 6 more
  151. 9of 31 santos-sanz/jev-audio-beeper Other Low-latency audio insult detector: Jev decides, ffmpeg beeps in ~466 ms without rewriting the rest of the track. Picked by AnotiaWang, valentynkit, hellogumbo and 6 more
  152. 9of 31 teyhouse/jev-secret-detection Eval & Align Benchmark and tool evaluating how well TypeSafe Jev identifies real secret credentials in file snippets. Picked by logicrw, AnotiaWang, valentynkit and 6 more
  153. 9of 31 vercel-labs/ai-cli Eval & Align AI CLI - Developer tooling: Vercel Labs CLI that can run Jev as the evaluation model for its `evaluate` command. Picked by yibie, v-modal, valentynkit and 6 more
  154. 8of 31 kshetrajna12/reflex in Top 100 Eval & Align Open-model decision engine with shared-state inference, isolated question branches, and a WebGPU demo; browser and Python configurations differ. Picked by cobanov, valentynkit, hellogumbo and 5 more 85★
  155. 8of 31 Heman10x-NGU/Verdict-open-jev in Top 100 Browser Non-autoregressive decision engine on ModernBERT with calibrated uncertainty and an in-browser WebGPU playground. Picked by valentynkit, hellogumbo, OmniJev and 5 more 36★
  156. 8of 31 ikermoel/open-alternative-jev in Top 100 Eval & Align Open alternative: runs a Jev-shaped decision model locally on your own GPU. Picked by yibie, v-modal, valentynkit and 5 more 32★
  157. 8of 31 burnigtm/jev-mcp in Top 100 Coding Agent (burnigtm) - MCP ecosystem: server that puts Jev into the coding loop for Cursor, Codex, and any MCP client, with 20 test files behind it. Picked by yibie, hellogumbo, heyjunpenn and 5 more 31★
  158. 8of 31 tacticocc/Jevbridge in Top 100 Computer Use Agent bridges: ACP and MCP adapter that exposes Jev typed decisions to Codex, Claude, Grok, and other LLMs. Picked by yibie, v-modal, valentynkit and 5 more 30★
  159. 8of 31 AlbionaHoti/refgarden in Top 100 Search A visual-reference gallery drawing from The Met, NASA and Cosmos, with Jev in local Explore mode. Picked by logicrw, hellogumbo, OmniJev and 5 more 26★
  160. 8of 31 keltokhy/jgrep in Top 100 Search Filters text, structured records, functions, and diff hunks against plain-English descriptions using Jev Noul judgments. Picked by logicrw, valentynkit, hellogumbo and 5 more 12★
  161. 8of 31 kavehmz/typesafe-playground in Top 100 Routing Interactive playground: small Jev experiments that put the decision on screen, from routing a support message to steering a car in a 3D world. Picked by yibie, v-modal, logicrw and 5 more 11★
  162. 8of 31 vinilana/live-jev in Top 100 Browser A browser-based top-down driving simulator using Jev for lane and speed choices, with an optional chat-model comparison. Picked by logicrw, valentynkit, hellogumbo and 5 more 11★
  163. 8of 31 hev/reranker in Top 100 Eval & Align A Python reranker that packs a query and up to 30 candidates into one Jev state, with one Noul relevance question per document. Picked by logicrw, fatwang2, valentynkit and 5 more 6★
  164. 8of 31 legacybridge-tech/pi-typesafe-jev in Top 100 Search Coding agents: exposes System One judgments as five Pi tools so a model makes narrow semantic judgments while code and users keep control of thresholds, weights, and actions. Picked by yibie, v-modal, logicrw and 5 more 1★
  165. 8of 31 markjaquith/typesafe-ai-playground in Top 100 Other Rust CLI experiments for health-information screening, comment review, tone analysis and business or occupation classification. Picked by logicrw, fatwang2, valentynkit and 5 more 1★
  166. 8of 31 AbdelStark/heist-one Browser Observable browser stealth game where Jev supplies batched typed judgments for six guards while deterministic code owns the simulation and validates every proposal; includes a Decision… Picked by AbdelStark, cobanov, logicrw and 5 more
  167. 8of 31 AkashPriyadarshii/jev-git Other Rust pre-commit and pre-push gate that screens staged diffs for secrets and destructive commands using Jev Noul checks. Picked by Anil-matcha, yibie, v-modal and 5 more
  168. 8of 31 AkashPriyadarshii/jev-superpowers Other Agentic software-development framework upgraded with TypeSafe Jev typed decisions. Picked by Anil-matcha, yibie, v-modal and 5 more
  169. 8of 31 Butochnikov/typesafe-sdk-php SDK & Runtime A community TypeSafe SDK for PHP 8.2+, with synchronous calls and Guzzle-based async requests. Picked by logicrw, fatwang2, AnotiaWang and 5 more
  170. 8of 31 EugeneBoondock/jevsql Data SQL-like filtering, ranking, classification, and scoring with natural-language predicates. Picked by cobanov, logicrw, valentynkit and 5 more
  171. 8of 31 FirasSX914/Janus Routing Measures calibration and confidence-based routing, with raw JSONL and figures committed for inspection. Picked by Anil-matcha, AbdelStark, cobanov and 5 more
  172. 8of 31 HyunjunJeon/pi-quiet-ask Other Coding agents: gives the Pi agent a quiet Jev decision layer for judgments it would otherwise hand to a chat model. Picked by yibie, v-modal, valentynkit and 5 more
  173. 8of 31 Nyarlathoteppppp/pi-heed SDK & Runtime Runtime constraints: checks every side-effecting tool call from the Pi agent against what the user actually asked for. Picked by yibie, v-modal, AbdelStark and 5 more
  174. 8of 31 OpenByteInc/QuantDinger Other Opt-in live pre-trade gate that sends structured strategy, market, position, exposure, and budget state to Jev `Choice` questions; application code validates probabilities and confidence… Picked by Anil-matcha, AbdelStark, OmniJev and 5 more
  175. 8of 31 Tangerg/typesafe-sdk-go SDK & Runtime A Go TypeSafe SDK for defining typed questions and reading Jev choices, scores, and probabilities. Picked by logicrw, fatwang2, valentynkit and 5 more
  176. 8of 31 adarshmishra07/jcm-router Routing Coding agents: local proxy that picks the Claude model and reasoning effort per message with a Jev decision while leaving the cached main chat untouched. Picked by yibie, v-modal, valentynkit and 5 more
  177. 8of 31 harshil1712/slidepilot Other Experimental Slidev controller that judges speech transcripts for slide completion, with deterministic checks and manual navigation. Picked by cobanov, logicrw, valentynkit and 5 more
  178. 8of 31 jomatsu/zod-jev Search Pairs local Zod shape validation with Jev semantic validation. Picked by cobanov, logicrw, valentynkit and 5 more
  179. 8of 31 leonaaardob/fast-dev-compaction Coding Agent Context management: Codex port of the Jev-guided compaction idea, restoring context verbatim around a session compaction rather than summarizing it. Picked by yibie, v-modal, cobanov and 5 more
  180. 8of 31 mahlernim/jev-korean-benchmark Eval & Align A language-specific benchmark candidate; treat results as workload evidence rather than a general multilingual guarantee. Picked by Anil-matcha, cobanov, valentynkit and 5 more
  181. 8of 31 monteduro/killmyidea Eval & Align Startup-idea evaluator that chooses kill, fix, or ship. Picked by cobanov, logicrw, valentynkit and 5 more
  182. 8of 31 nexibeo/jev-cookbook Routing Developer education: 15 runnable Node recipes that route support tickets, file documents, categorize bank transactions and label Gmail with Jev `Choice` and `Noul` questions, sending… Picked by yibie, v-modal, cobanov and 5 more
  183. 8of 31 noplan-inc/limpet Other Coding agents: Stop hook that keeps an agent from finishing too early by judging plain-language completion rules with Jev. Picked by yibie, v-modal, logicrw and 5 more
  184. 8of 31 phyous/tsai-civ2 Browser An experimental harness where TypeSafe Jev plays classic Civilization II in a browser, computing live action probability distributions. Picked by logicrw, AnotiaWang, valentynkit and 5 more
  185. 8of 31 siroccomask/snake-jev SDK & Runtime Real-time Snake game driven by parallel Jev assessments, deciding optimal turns in a single API call per tick. Picked by logicrw, AnotiaWang, valentynkit and 5 more
  186. 8of 31 zhirschtritt/typesafe-go SDK & Runtime Idiomatic Go SDK for the TypeSafe API. Picked by cobanov, logicrw, valentynkit and 5 more
  187. 7of 31 lakeday-org/perch in Top 100 Coding Agent Semantic code linter that evaluates code units against configurable Jev questions. Picked by cobanov, valentynkit, yzfly and 4 more 164★
  188. 7of 31 devagrawal09/stanley-code in Top 100 Other Coding agents: bounded Jev workflows that keep agent judgments typed instead of free-form. Picked by yibie, v-modal, hellogumbo and 4 more 98★
  189. 7of 31 daseinlabs/open-jev in Top 100 Other (MLX) - Gemma 3 option scorer for Apple MLX that shares one prefill across candidate continuations and exposes a System One-compatible endpoint; its docs show zero-shot overconfidence and… Picked by cobanov, valentynkit, hellogumbo and 4 more 65★
  190. 7of 31 choxos/jev-reviewer in Top 100 Browser Research-document extraction aid where Jev selects and verifies source lines for verbatim quotes; findings require human review and are not clinical decisions. Picked by cobanov, logicrw, valentynkit and 4 more 23★
  191. 7of 31 altryne/jevify in Top 100 Coding Agent An Agent Skill for finding suitable Jev decision points and designing questions and comparison experiments. Picked by logicrw, hellogumbo, heyjunpenn and 4 more 14★
  192. 7of 31 wondertwins/jev-benchmark in Top 100 Eval & Align Benchmarks Jev on chess moves and identifying which game NPC a player addresses. Picked by logicrw, valentynkit, hellogumbo and 4 more 3★
  193. 7of 31 Foadsf/jev-for-engineers in Top 100 Routing Eight mechanical and electrical engineering experiments using Jev for task routing, log checks and component selection. Picked by logicrw, valentynkit, hellogumbo and 4 more 2★
  194. 7of 31 DECRUX9812/typesafe-skill-router Coding Agent An opt-in Hermes Agent plugin that asks Jev to suggest one relevant skill before a model call. Picked by logicrw, valentynkit, hellogumbo and 4 more
  195. 7of 31 FFatTiger/new-api-plugin-typesafe Routing new-api-typesafe-plugin - LLM gateway: adds a native `/v1/systemone` endpoint to new-api so typed decisions sit behind the same gateway as chat models. Picked by yibie, v-modal, hellogumbo and 4 more
  196. 7of 31 Friedjof/jev-mobile Mobile Experimental Android agent that uses Jev for bounded, per-step choices over prevalidated UI actions, with confidence gates, pagination, escalation, and optional LLM planning; currently a… Picked by AbdelStark, valentynkit, hellogumbo and 4 more
  197. 7of 31 Hawxy/TypeSafeAI.Net Routing .NET client for TypeSafe's API with Noul, Choice, and Score question sets, HttpClientFactory and dependency injection support, plus Microsoft.Extensions.AI guardrail, routing, tool, and… Picked by AbdelStark, valentynkit, hellogumbo and 4 more
  198. 7of 31 NullPo-jp/PocketJev Other On-device iPhone visual decisions with MLX + Qwen3-VL option logits. Camera + 3-choice, no text generation, ~1s, no photo saved. Picked by AnotiaWang, hellogumbo, kraayenjon and 4 more
  199. 7of 31 Premo-Cloud/typesafe-sdk-java SDK & Runtime Community Java 17 client for TypeSafe's System One API with typed Noul, Choice, and Score questions, lambda-style builders for nested criteria, retries matching the official SDKs… Picked by AbdelStark, cobanov, logicrw and 4 more
  200. 7of 31 TheoLeeCJ/openjev Other Independent open-model research baseline for direct typed option scoring; it reproduces the interface pattern, not Jev's undisclosed model or training. Picked by AbdelStark, AnotiaWang, kraayenjon and 4 more
  201. 7of 31 ariel-frischer/jevkit SDK & Runtime Typed-decisions CLI: Rust command-line client that accepts `Choice`/`Score`/`Noul` question sets in terse YAML or JSON, validates them offline with 13 lint rules before any call, expands… Picked by Anil-matcha, yibie, v-modal and 4 more
  202. 7of 31 asfarsadewa/human-compiler Other Human Compiler - Paste corporate prose; Jev scores passive-aggression, urgency, and information density, then code emits rustc-style diagnostics. Live: human-compiler.asfarlab.fun. Picked by AnotiaWang, valentynkit, hellogumbo and 4 more
  203. 7of 31 emrickgarrett/OneVOneJev Browser A browser-based 1v1 shooter where Jev reads structured match state and chooses movement, aim, and firing. Picked by logicrw, valentynkit, hellogumbo and 4 more
  204. 7of 31 frostney/clean-code-review Coding Agent Clean Code Judge - Code quality: scores every file of a pull request on 31 boolean Clean Code smells plus function size and nesting, then hands the verdicts to a writing model for the… Picked by yibie, v-modal, valentynkit and 4 more
  205. 7of 31 gaborishka/jev-canvas Other Multimodal UI: draw on a tldraw canvas by voice while pointing a webcam-tracked finger; on every partial transcript Jev answers eight typed questions (is it a command, is the sentence… Picked by yibie, v-modal, cobanov and 4 more
  206. 7of 31 hamakyo/jev-starter Eval & Align TypeScript patterns for thresholds, fallbacks, human review and evaluation on top of the TypeSafe SDK. Picked by logicrw, fatwang2, hellogumbo and 4 more
  207. 7of 31 hegargarcia/jev-playground Eval & Align Jev Playground - Model evaluation: benchmarks Jev against Luna, Haiku, and Gemini at choosing validated legal moves in explicit-state games, scoring decision quality and consistency across… Picked by yibie, v-modal, valentynkit and 4 more
  208. 7of 31 huntedman/JevLint Search Configurable semantic linting with file-level Noul judgments. Picked by valentynkit, hellogumbo, AppitStudio and 4 more
  209. 7of 31 iamvatsalpatel/tiershift Routing Policy-bounded model routing for TypeScript and Python. Picked by cobanov, logicrw, valentynkit and 4 more
  210. 7of 31 inanna-malick/jev-dsl Other Early-alpha Haskell DSL that encodes typed question packets and decodes answers; HTTP transport is left to the caller. Picked by cobanov, logicrw, valentynkit and 4 more
  211. 7of 31 jgridifier/jev-research-eval Browser Research automation: reproducible eval harness plus field note for Jev Ultrafast research-browser tasks, with QC'd cases, a suite runner, and a report generator. Picked by yibie, v-modal, valentynkit and 4 more
  212. 7of 31 joshlarsen/jev-t-rex-runner Browser Chrome dinosaur game played by Jev. Picked by AnotiaWang, hellogumbo, kraayenjon and 4 more
  213. 7of 31 jtsang4/jev-cli Other A CLI for asking Jev classification, yes/no and scoring questions over text or JSON input. Picked by logicrw, valentynkit, hellogumbo and 4 more
  214. 7of 31 kikoncuo/jevfire Browser Jev-inspired parallel decisions for CUDA LLMs via vLLM, with a browser Mario demo (~71 ms/action locally) Picked by AnotiaWang, valentynkit, hellogumbo and 4 more
  215. 7of 31 kitze/pagegrade Other Content quality: grades page sections for clarity, writing, and on-page SEO with Jev and returns per-section scores. Picked by yibie, v-modal, AppitStudio and 4 more
  216. 7of 31 mateonunez/jod Other Zod-style schemas over Jev: validate the state locally, then project typed answers. Picked by valentynkit, hellogumbo, heyjunpenn and 4 more
  217. 7of 31 raihankhan-rk/diffjury Coding Agent Code review: routes each pull request by risk with Jev before a human reviewer is assigned, doubling as a review coach. Picked by yibie, v-modal, valentynkit and 4 more
  218. 7of 31 rorshopping/jev-on-a-laptop Other Study of Jev-style decisions on stock 1.5B to 8B models on a laptop, with a Hugging Face demo. Picked by valentynkit, hellogumbo, OmniJev and 4 more
  219. 7of 31 tontoko/jev-browser Browser Playwright browser automation with Jev decisions through a shared CLI, MCP server and TypeScript SDK. Picked by logicrw, valentynkit, hellogumbo and 4 more
  220. 7of 31 usenotra/notra Routing Marketing analytics: production GEO platform whose `NOTRA_JEV_CLASSIFIERS` flag routes brand-visibility classifiers off an LLM and onto Jev `Boolean` decisions at a 0.5 threshold, targeting… Picked by yibie, v-modal, valentynkit and 4 more
  221. 7of 31 y0usaf/typesafe-cli Other Noul, choice, and score answers as numbers from the shell. Picked by valentynkit, hellogumbo, AppitStudio and 4 more
  222. 6of 31 NandhaKishorM/laya in Top 100 Routing Open alternative: non-autoregressive decision model that answers `choice`, `score`, and `noul` questions with RLCD-trained calibrated probabilities in a single ~35 ms forward pass… Picked by yibie, v-modal, yzfly and 3 more 3.4k★
  223. 6of 31 Sac-Y/Jev-cu in Top 100 Computer Use A Codex Computer Use loop sending text candidates to Jev while desktop tools observe and act. Picked by logicrw, valentynkit, AppitStudio and 3 more 455★
  224. 6of 31 rokbenko/quackd in Top 100 Coding Agent Command line for LLM-piloted robots across seven bodies, with an optional Jev stepper that picks among calls without ever writing a joint angle. Picked by valentynkit, OmniJev, AppitStudio and 3 more 219★
  225. 6of 31 Heman10x-NGU/openJev-verdict-2.0 in Top 100 Eval & Align Open decision engine: a calibrated 151M non-autoregressive model that reports beating both TypeSafe Jev and Laya on typed-decision benchmarks, shipped with its own test suite. Picked by yibie, cobanov, hellogumbo and 3 more 165★
  226. 6of 31 logan-markewich/jeff in Top 100 Other by logan-markewich - Self-hosted System One API on the 400M GLiFormer, with benchmarks that say where it trails Jev. Picked by valentynkit, hellogumbo, yzfly and 3 more 160★
  227. 6of 31 nidhi-singh02/agent-router in Top 100 Coding Agent Pre-release Herdr integration that filters eligible coding models by quota and policy before Jev ranks them. Picked by cobanov, valentynkit, AppitStudio and 3 more 54★
  228. 6of 31 Bodila51/grok-bot-jev in Top 100 Coding Agent Agent bridges: connects Jev to Grok Bot as a cheap decision layer, with usage gates, a skill template, and worked examples. Picked by yibie, hellogumbo, OmniJev and 3 more 50★
  229. 6of 31 jcpsimmons/jev-macos-loop in Top 100 Computer Use A native macOS automation loop using local OCR and accessibility information with Jev action selection. Picked by logicrw, AppitStudio, ckaraca and 3 more 15★
  230. 6of 31 chopratejas/invalidate in Top 100 Other Gives every stored agent memory a lease and asks Jev whether new evidence ends it; live demo. Picked by valentynkit, hellogumbo, AppitStudio and 3 more 13★
  231. 6of 31 sosopop/jev_stock in Top 100 Other Short-term forecasting: experimental Hong Kong stock framework that turns structured market state into a Jev decision on price direction, with a backtest script for the first trading day. Picked by yibie, v-modal, hellogumbo and 3 more 10★
  232. 6of 31 BYK/jev-mcp in Top 100 Coding Agent An eval-first MCP server for Jev, that returns typed judgments (noul, choice, score) with probabilities instead of generated text. Picked by cobanov, logicrw, valentynkit and 3 more 1★
  233. 6of 31 jmanhype/jev-dspy-lab in Top 100 Eval & Align Jev DSPy Lab - Unofficial DSPy companion that records and replays TypeSafe calls while measuring calibration, selective risk, confidence-gated abstention, latency, tokens, and modeled cost. Picked by AnotiaWang, valentynkit, kraayenjon and 3 more 0★
  234. 6of 31 3clyp50/a0-typesafe-ai Other Typed tools and probability cards for Agent Zero. Picked by valentynkit, hellogumbo, AppitStudio and 3 more
  235. 6of 31 Bud-ro/jev-demos Other Maze experiments comparing Jev single-step choices with multi-step lookahead. Picked by logicrw, valentynkit, hellogumbo and 3 more
  236. 6of 31 MarissaFamularo/citation-verifier Other Academic publishing: checks whether each cited paper actually supports the sentence citing it, with Claude locating the quote, Jev scoring the support, and a human making the final call. Picked by yibie, v-modal, valentynkit and 3 more
  237. 6of 31 ShivamPansuriya/jev-skill-gate Coding Agent Ranks Claude Code skills for the current project to reduce the descriptions loaded by default. Picked by logicrw, hellogumbo, AppitStudio and 3 more
  238. 6of 31 ainame/swift-typesafe SDK & Runtime A community Swift TypeSafe client with typed questions, dynamic questions and response parsing. Picked by logicrw, fatwang2, AnotiaWang and 3 more
  239. 6of 31 arielweinberger/jev-autopilot Home & IoT This demo uses Jev from TypeSafe AI to autonomously fly a drone in a random city from point A to point B, avoiding obstacles along the way. A trip costs $0.01. Picked by hellogumbo, heyjunpenn, jtnkminimal and 3 more
  240. 6of 31 cephalization/jev-triage Other typeful-triage - Open-source maintenance: multiplayer triage dashboard where Jev answers a fixed set of typed questions per issue Picked by yibie, v-modal, valentynkit and 3 more
  241. 6of 31 coldteadotai/abide Coding Agent Agent supervision: reads every edit a coding agent makes and has Jev flag rule violations, with the project reporting that an independent reviewer confirmed 10 of the 39 flagged edits and… Picked by yibie, v-modal, OmniJev and 3 more
  242. 6of 31 devagrawal09/jev-code Other Helps coding Agents locate code, check change intent, triage test failures, and organize review findings. Picked by logicrw, fatwang2, valentynkit and 3 more
  243. 6of 31 docxology/daf-jev Coding Agent A Python toolkit for Jev requests, batch evaluation, calibration and MCP access. Picked by logicrw, hellogumbo, AppitStudio and 3 more
  244. 6of 31 fatwang2/jev-review-action Other A configurable GitHub Action that reviews catalog submissions or classifies PRs and updates a templated comment. Picked by logicrw, fatwang2, valentynkit and 3 more
  245. 6of 31 fgn/jevgo SDK & Runtime A community Go client with a standard-library core and optional Langfuse tracing. Picked by logicrw, hellogumbo, heyjunpenn and 3 more
  246. 6of 31 genai-craft/openvons Other Open decision layer for finite options across text, images, and Japanese voice commands. Picked by cobanov, valentynkit, hellogumbo and 3 more
  247. 6of 31 guillemus/jev-go SDK & Runtime A small unofficial Go SDK for Jev calls and model listing. Picked by logicrw, hellogumbo, heyjunpenn and 3 more
  248. 6of 31 harshwasan/pi-jev-sentinel Other Open-source Pi coding-agent extension that uses Jev to check tool calls before they run, scan files for prompt injection, flag risky replies, and keep secrets out of what it sends. Picked by logicrw, valentynkit, hellogumbo and 3 more
  249. 6of 31 haseeb-heaven/jev-system-one Other A terminal Q&A app where OpenAI writes answers and Jev sets response policy and reviews drafts. Picked by logicrw, valentynkit, hellogumbo and 3 more
  250. 6of 31 johnhughes3/LegalForecastBench Eval & Align LegalForecast-MTD - Legal forecasting: benchmark that asks Jev to predict federal motion-to-dismiss rulings from the judge's written record and scores the calibrated probabilities with… Picked by yibie, v-modal, hellogumbo and 3 more
  251. 6of 31 komikat/jev-bfs Search Search tooling: finds link paths between English Wikipedia articles by having Jev rank each page's outgoing links while Python controls the search. Picked by yibie, v-modal, logicrw and 3 more
  252. 6of 31 milanboers/jev-plays-pokemon Other Gaming: reads Pokémon Red game state as text, answers typed questions each turn, and lets deterministic code turn the answers into moves. Picked by yibie, v-modal, heyjunpenn and 3 more
  253. 6of 31 mizchi/jev-gomoku SDK & Runtime MoonBit client plus Jev-vs-Jev gomoku; write-up: jev 同士に五目並べで対戦させた. Picked by AnotiaWang, hellogumbo, kraayenjon and 3 more
  254. 6of 31 olanotolu/jevbetter Awesome List Improved scorer: a stronger one-pass scorer over a variable list of text options, using a hashed n-gram encoder, rival-aware attention, and gated heads. Picked by yibie, v-modal, valentynkit and 3 more
  255. 6of 31 phureewat29/got-jev Other Game of Thrones roleplay as Jon Snow. A story model writes the scene; Jev answers where he is, how much danger, and what should play under it. Picked by AnotiaWang, kraayenjon, yzfly and 3 more
  256. 6of 31 qkal/Canny Other Evidence ledger that challenges unsupported "done" claims from coding agents. Picked by cobanov, logicrw, hellogumbo and 3 more
  257. 6of 31 rashedInt32/jev-mcp Coding Agent An MCP server and Claude Code plugin for Jev classification, scoring, checks and batched questions. Picked by logicrw, hellogumbo, heyjunpenn and 3 more
  258. 6of 31 wustep/jev-playground Other by wustep - Can a System One model steer a music composition through typed classify, score, and pick decisions alone. Picked by valentynkit, hellogumbo, heyjunpenn and 3 more
  259. 5of 31 notque/vexjoy-agent in Top 100 Coding Agent An optional Jev routing path that matches VexJoy requests to specialist Agents, skills and workflows. Picked by logicrw, valentynkit, AppitStudio and 2 more 421★
  260. 5of 31 kerpopule/hermes-jev-skills in Top 100 Browser Jev-powered model routing, memory, compaction, skill selection, computer and browser use for Hermes agents (also Claude Code and Codex). Picked by hellogumbo, AppitStudio, MrJev and 2 more 219★
  261. 5of 31 vinilana/jev-gateway in Top 100 Coding Agent Local gateway for Codex and Claude Code that sends the "which tool next" decision to Jev and everything else to your usual model. Picked by valentynkit, AppitStudio, MrJev and 2 more 69★
  262. 5of 31 kbhuw/jev-sift in Top 100 Coding Agent MCP tool that scores a batch of files, URLs, or snippets for relevance so the agent opens only what matters. Picked by valentynkit, AppitStudio, MrJev and 2 more 45★
  263. 5of 31 EliaAlberti/jev-rules in Top 100 Other Scores your standing rules against each prompt and delivers only the ones that apply, once per session. Picked by valentynkit, AppitStudio, ckaraca and 2 more 43★
  264. 5of 31 yikangy873-gif/jev-desktop in Top 100 Computer Use Computer use: supplies Jev action selection inside Codex Computer Use, choosing among desktop actions rather than asking a language model at every step. Picked by yibie, v-modal, walidboulanouar and 2 more 41★
  265. 5of 31 kevinbadi/jev-voice in Top 100 Computer Use Talk to your Mac. Local whisper.cpp + one Jev (TypeSafe) call per command + macOS automation. Picked by hellogumbo, AppitStudio, MrJev and 2 more 39★
  266. 5of 31 myc0576/SmartMoney-Cub in Top 100 Eval & Align , Read-only trading journal and review harness with Jev judging entries against the evidence. Picked by OmniJev, AppitStudio, kraayenjon and 2 more 25★
  267. 5of 31 fazlerocks/jevmail in Top 100 Routing Read-only Gmail triage that stores messages locally and asks Jev for bounded category, urgency, and human-sender probabilities. Picked by cobanov, hellogumbo, AppitStudio and 2 more 24★
  268. 5of 31 Dimweaker/jev-libero in Top 100 Home & IoT Two LIBERO tasks, one control engine. Each demo loads its own JSON task definition. Videos follow simulation time, with decision and physics-preview waiting omitted. Picked by logicrw, hellogumbo, OmniJev and 2 more 23★
  269. 5of 31 mithalouni/system-one-open in Top 100 Eval & Align Typed calibrated decisions in one forward pass on Gemma 4 E2B and Gemma 3 270M. Picked by valentynkit, hellogumbo, heyjunpenn and 2 more 18★
  270. 5of 31 unicodeveloper/jevocks in Top 100 Other Jevinik - Stock decisions: terminal that gathers live market evidence through Valyu and asks Jev whether a stock is likely to trade higher over the next 30 days. Picked by yibie, v-modal, hellogumbo and 2 more 13★
  271. 5of 31 Charlyhno-eng/jev-document-classification in Top 100 Other JEV Document Classification enables the rapid and cost-effective classification of text-based documents using AI, leveraging TypeSafe's "System One" model. Picked by hellogumbo, AppitStudio, heyjunpenn and 2 more 2★
  272. 5of 31 hellogumbo/should-ai-kill-us-all in Top 100 Other Asks Jev the question every ten minutes, using the actual headlines. Picked by valentynkit, hellogumbo, heyjunpenn and 2 more 2★
  273. 5of 31 opaielsheikh/typesafe-migration-guard in Top 100 Data Reviews database migrations for safety before they run. Picked by valentynkit, hellogumbo, heyjunpenn and 2 more 2★
  274. 5of 31 Little-Planet-Labs/jev-playground in Top 100 Other A web playground for entering state and decision questions, then inspecting Jev answers and probability distributions. Picked by logicrw, hellogumbo, heyjunpenn and 2 more 1★
  275. 5of 31 4esv/jev-eval Eval & Align Independent Jev versus GPT-5.6 Terra comparison on three labeled classification tasks, reporting accuracy, calibration, latency, and cost. Picked by cobanov, logicrw, valentynkit and 2 more
  276. 5of 31 BorisLeMeec/jev Coding Agent A Go Claude Code plugin using Jev to find files, answer bounded questions across code and handle large reads. Picked by logicrw, hellogumbo, heyjunpenn and 2 more
  277. 5of 31 DomMonte/n8n-nodes-typesafe-ai Other n8n community node for yes/no, choice, and score questions. Picked by valentynkit, hellogumbo, heyjunpenn and 2 more
  278. 5of 31 HackSing/jev-report Other Independent Chinese research report: 52 pages, 50 reproducible tests, 143 traceable data rows. Picked by valentynkit, hellogumbo, heyjunpenn and 2 more
  279. 5of 31 Icohen007/jev-play-ping-pong Browser Uses Jev to choose serve direction, return angle and pace in a browser table-tennis game. Picked by logicrw, hellogumbo, heyjunpenn and 2 more
  280. 5of 31 JoshuaSP/open-jev Other Typed JSON inference with DiffusionGemma, benchmarked against Jev. Picked by valentynkit, hellogumbo, OmniJev and 2 more
  281. 5of 31 PistachioAIHQ/jev-synergy-screening Other A Jev title-and-abstract screening experiment compared with Cohen Abstract Triage labels for an ADHD review. Picked by logicrw, valentynkit, hellogumbo and 2 more
  282. 5of 31 RINNECODER/jev-behavior-study Other Independent synthetic-task study of Jev 1.13.0 framing sensitivity and failures, with raw responses and offline report checks. Picked by cobanov, logicrw, valentynkit and 2 more
  283. 5of 31 Vicente-MD/jev-resilience Other A Spring WebFlux integration that detects error messages hidden in HTTP 200 response bodies. Picked by logicrw, AnotiaWang, kraayenjon and 2 more
  284. 5of 31 ably-labs/jev-pong Routing Jev Pong - Model comparison: Pong where the ball advances one step per model decision, putting Jev head-to-head with LLMs through Vercel AI Gateway. Picked by yibie, v-modal, heyjunpenn and 2 more
  285. 5of 31 adhyaay-karnwal/jev-chat Other A research chat decoder that repeatedly asks Jev to choose words or phrases and assembles them in code. Picked by logicrw, hellogumbo, heyjunpenn and 2 more
  286. 5of 31 bespokelabsai/nimble Eval & Align Bespoke Nimble, Data, model and recipe for an open Jev: Qwen3.5-9B plus LoRA on contrastive examples, with a 13-subset public evaluation suite scored against Jev 1.13. Picked by OmniJev, MrJev, jtnkminimal and 2 more
  287. 5of 31 bohutang/sift Browser Content labelling: Chrome extension that labels every post in an X timeline - substance, humour, chit-chat, promo, junk, or AI-written - with Jev decisions. Picked by yibie, v-modal, hellogumbo and 2 more
  288. 5of 31 caiovicentino/jev-shield Coding Agent Semantic MCP firewall that screens every tool call, result, and description; reports 94 percent block recall at about $0.00002 a check. Picked by valentynkit, hellogumbo, AppitStudio and 2 more
  289. 5of 31 colliber/duckdb-jev Data DuckDB extension that exposes Jev judgments as SQL values with return types derived from the declared criteria. Picked by cobanov, logicrw, valentynkit and 2 more
  290. 5of 31 forvela/jev-agent-browser Browser Browser agents: a parent agent delegates bounded tasks to a Jev loop that selects typed browser actions, validates them through agent-browser, and escalates ambiguity or stuck states back… Picked by yibie, v-modal, AbdelStark and 2 more
  291. 5of 31 grmkris/robo-harness Other Robotics: SO-101 arm workbench where a Jev decision runner picks bounded joint steps from typed candidate actions under a spend budget. Picked by yibie, v-modal, logicrw and 2 more
  292. 5of 31 joevidev/ui-generator-instinct-jev Other Turns UI descriptions into selections from existing shadcn/ui components, fields and styles. Picked by logicrw, fatwang2, hellogumbo and 2 more
  293. 5of 31 kunobi-ninja/kunobi-jev SDK & Runtime Rust client for the System One API. Picked by valentynkit, hellogumbo, heyjunpenn and 2 more
  294. 5of 31 lukstei/slop-grader Other Content quality: CLI tool that grades text files against custom rulesets for AI slop, grammar, and technical doc quality using Jev scores and line-level flags, then guides an AI agent to… Picked by yibie, AbdelStark, cobanov and 2 more
  295. 5of 31 maker-KK/todo-jev Coding Agent A task-routing experiment combining skill conditions and environment checks to suggest rules, skills or a large model. Picked by logicrw, hellogumbo, AppitStudio and 2 more
  296. 5of 31 manifoldor/xtags Other Labels every post in your X timeline with what it wants you to do. Picked by valentynkit, hellogumbo, AppitStudio and 2 more
  297. 5of 31 matthewp/flue-jev-demo Routing Agent routing: routes a Flue agent's work with Jev through Cloudflare AI Gateway. Picked by yibie, v-modal, hellogumbo and 2 more
  298. 5of 31 nekuda-ai/WindTunnel Browser Browser-agent benchmark: measures WebMCP against other browser-agent interfaces, with Jev appearing as one of the compared configurations. Picked by yibie, v-modal, yzfly and 2 more
  299. 5of 31 noelzappy/tripwire Routing Unofficial AI SDK middleware and OpenAI-compatible proxy: seven Jev checks on every LLM response in ~100 ms, confidence-gated Picked by AnotiaWang, valentynkit, kraayenjon and 2 more
  300. 5of 31 omni-/ask-jev Coding Agent A Windows PowerShell tool for auditing recorded Codex execution evidence with :jev. Picked by logicrw, hellogumbo, heyjunpenn and 2 more
  301. 5of 31 paulsmith/computer-use-jev Computer Use A Go-based macOS controller that asks Jev to choose controls and actions from the accessibility tree. Picked by logicrw, hellogumbo, heyjunpenn and 2 more
  302. 5of 31 raihankhan-rk/jevarena Browser Two Jev Agents play Snake in side-by-side browser panes with visible per-step choices. Picked by logicrw, hellogumbo, heyjunpenn and 2 more
  303. 5of 31 ranjan2829/AskJev Browser Connects Agents to a browser over MCP, using Jev to choose page actions with confirmation gates for actions such as payment or deletion. Picked by logicrw, hellogumbo, heyjunpenn and 2 more
  304. 5of 31 scale-venture-partners/riff Other Ruff-style rule codes for writing. Picked by valentynkit, hellogumbo, heyjunpenn and 2 more
  305. 5of 31 shitianfang/wakegate Other Experimental wake gate for long-running agents: before a sleeping agent's LLM is resumed on a timer or incoming event, Jev answers one `Choice` (`wake` / `not_yet` / `unrelated`) against… Picked by Anil-matcha, yibie, v-modal and 2 more
  306. 5of 31 siddicky/omp-typesafe Coding Agent TypeSafe AI (Jev) adversarial reviewer and typesafe_ask tool for the omp coding agent. Picked by hellogumbo, heyjunpenn, walidboulanouar and 2 more
  307. 5of 31 sriganesh/jevibe-check Other Live tone labels for Bluesky posts and drafts. Picked by valentynkit, hellogumbo, heyjunpenn and 2 more
  308. 5of 31 valksor/typesafe-sdk-go SDK & Runtime 1:1 parity with the official JS and Python SDKs. Not affiliated with TypeSafe AI. Picked by hellogumbo, heyjunpenn, walidboulanouar and 2 more
  309. 5of 31 valksor/typesafe-sdk-php SDK & Runtime 1:1 parity with the official JS and Python SDKs. Not affiliated with TypeSafe AI. Picked by hellogumbo, heyjunpenn, walidboulanouar and 2 more
  310. 5of 31 yodablocks/jev-orderby-bench Data Measures whether ORDER BY over a Jev probability is defensible: pairwise inversion, Score ordinality against a human grade, calibration, and wording invariants under a pre-registered gate… Picked by yibie, v-modal, AbdelStark and 2 more
  311. 4of 31 githubnext/localjev in Top 100 Eval & Align , Local Jev-compatible POST /v1/systemone in TypeScript for Bun, backed by DiffusionGemma through an OpenAI-compatible endpoint. Picked by OmniJev, yzfly, MrJev and 1 more 586★
  312. 4of 31 brainstormity/Jev-X-Sentiment-Analysis in Top 100 Other Jev X Sentiment Analysis - Crypto terminal that reads up to 1,000 posts about a ticker alongside market and funding data and turns them into a buy, sell, hold, or take-profit call. No… Picked by MrJev, AiPersonacademy, RadRebelSam and 1 more 125★
  313. 4of 31 FBddcz/embodied-jev in Top 100 Home & IoT Embodied Jev - MuJoCo Franka Panda workbench where Jev can choose from bounded simulator actions over structured observations; deterministic code owns physics and safety checks, and the… Picked by cobanov, hellogumbo, OmniJev and 1 more 89★
  314. 4of 31 can1357/jegrep in Top 100 Search Rust semantic grep that scores live repository files and ranges with Jev probabilities, without an embedding index or background daemon. Picked by cobanov, AppitStudio, MrJev and 1 more 48★
  315. 4of 31 hqman/JevScout in Top 100 Browser A demo job-search Skill for coding Agents that browses company careers pages in Chrome, uses Jev to screen AI and software-engineering roles, and saves the results. Picked by logicrw, valentynkit, MrJev and 1 more 25★
  316. 4of 31 Zaious/jev-capability-atlas in Top 100 Eval & Align Jev Capability Atlas - Bilingual evidence map with recorded API runs and reusable suites that separates its own tests, third-party benchmarks, and editorial synthesis. Picked by cobanov, hellogumbo, MrJev and 1 more 21★
  317. 4of 31 khordoo/jev-reflex-autonomy-lab in Top 100 Home & IoT Drone autonomy: a multi-drone lab where Jev supplies the reflex decisions, with an optional slower strategy layer guiding them. Picked by yibie, hellogumbo, walidboulanouar and 1 more 12★
  318. 4of 31 himomohi/aside-jev in Top 100 Browser An MCP server and skill adding Jev decisions to Aside browser Agents. Picked by logicrw, hellogumbo, JohnDotOwl and 1 more 4★
  319. 4of 31 atarikcaliskan/jevball in Top 100 Other (site) - 22 Jev models, one ball: a 3D football match where every player is its own Jev (TypeSafe AI System One) decision. Watch, or take over the number 9. Picked by hellogumbo, rhc98, RadRebelSam and 1 more 3★
  320. 4of 31 anilsenay/jev in Top 100 SDK & Runtime Unofficial Go client for TypeSafe's System One API and its model, Jev. Picked by hellogumbo, heyjunpenn, JohnDotOwl and 1 more 1★
  321. 4of 31 edgardcham/huncho in Top 100 Eval & Align TypeScript ecosystem: dependency-free SDK that turns Jev `Noul`, `Choice` and `Score` answers into named decisions with `enter`/`exit` thresholds (hysteresis), nested decision trees settled… Picked by yibie, v-modal, rhc98 and 1 more 1★
  322. 4of 31 qddegtya/qualm in Top 100 Other A TypeScript wrapper for Jev decisions with an explicit unsure branch. Picked by logicrw, hellogumbo, heyjunpenn and 1 more 1★
  323. 4of 31 tinyhumansai/tinyjevclient in Top 100 Other An integration with jev by typesafe.ai in Rust. Picked by hellogumbo, heyjunpenn, JohnDotOwl and 1 more 0★
  324. 4of 31 0xnairb/research_desk Other TypeSafe Jev demonstration for new analyzation Picked by hellogumbo, jtnkminimal, JohnDotOwl and 1 more
  325. 4of 31 AshutoshVJTI/progressgate Search Detects semantic stagnation in agent loops: Jev judges the trajectory; code returns CONTINUE / WARN / REPLAN / HALT Picked by AnotiaWang, kraayenjon, jtnkminimal and 1 more
  326. 4of 31 BeLazy167/typesafe-mod Coding Agent Claude Code mod that routes decisions to TypeSafe's Jev model: ranks installed skills per prompt, and answers the agent's own this-or-that questions when confident. Picked by hellogumbo, heyjunpenn, JohnDotOwl and 1 more
  327. 4of 31 Bewinxed/jevgpt Other A chatbot built on a model that cannot generate text (TypeSafe AI's Jev, driven autoregressively). Picked by hellogumbo, heyjunpenn, JohnDotOwl and 1 more
  328. 4of 31 CodeAlive-AI/mastra-jev-moderation Other AI assistants: Mastra input processor that asks Jev a `Boolean` "must this message be blocked?" plus a category `Choice` in one request, aborting the turn at 0.7 and failing open behind a… Picked by yibie, v-modal, hellogumbo and 1 more
  329. 4of 31 DanielKillenberger/jev-predict-skill Coding Agent An Agent skill recipe that predicts another skill’s closed-set outcome from its rules and evidence. Picked by logicrw, hellogumbo, heyjunpenn and 1 more
  330. 4of 31 Dimesio/typesafe-chess Other (Dimesio) - FUn little experiment with Typesafe AI Jev Model playing chess against stockfish :). Picked by hellogumbo, walidboulanouar, RadRebelSam and 1 more
  331. 4of 31 InsaneArts/typesafe-sdk-swift SDK & Runtime Swift SDK for TypeSafe AI. Picked by hellogumbo, heyjunpenn, JohnDotOwl and 1 more
  332. 4of 31 JacobLinCool/jev-paper-judge Other (site) - Feedback on your paper in seconds. Picked by hellogumbo, heyjunpenn, JohnDotOwl and 1 more
  333. 4of 31 KesavanKing/jev-browser Browser (KesavanKing) - Local browser automation UI that uses TypeSafe Jev to choose bounded page actions and a text model only for field values. Picked by hellogumbo, heyjunpenn, JohnDotOwl and 1 more
  334. 4of 31 Menny1337/jev-lab Eval & Align TypeScript experiments, evaluations, and latency benchmarks for TypeSafe's Jev model. Picked by hellogumbo, heyjunpenn, JohnDotOwl and 1 more
  335. 4of 31 MongLong0214/jev-gate Coding Agent Not every coding task needs your best model. Experimental Jev-powered model routing for Claude Code Picked by hellogumbo, heyjunpenn, JohnDotOwl and 1 more
  336. 4of 31 Olti1947/jev-java SDK & Runtime Idiomatic Java SDK for TypeSafe AI Jev System One decision engine. Picked by hellogumbo, heyjunpenn, walidboulanouar and 1 more
  337. 4of 31 OmniJev/awesome-jev Eval & Align OmniJev/awesome-jev - Papers, open reproductions, independent evaluations, and technical lineage. Picked by cobanov, heyjunpenn, MrJev and 1 more
  338. 4of 31 Para-FR/casse-brique-typesafe Coding Agent A Next.js brick breaker whose paddle is controlled in real time by TypeSafe AI's Jev model. Built with Claude Code. Picked by hellogumbo, heyjunpenn, JohnDotOwl and 1 more
  339. 4of 31 Query-farm/vgi-typesafe Data DuckDB worker that exposes choice, noul, and score as lateral-joinable table functions in SQL. Picked by AbdelStark, valentynkit, rhc98 and 1 more
  340. 4of 31 SamuelSacco/jev-exploration Eval & Align A research repository tracking Jev claims and limitations, with calibration experiments and runnable examples. Picked by logicrw, hellogumbo, heyjunpenn and 1 more
  341. 4of 31 Skyvern-AI/jevscape Other RuneBench-based RuneScape harness that maps Jev choices to a bounded game-action catalog and records tick-level results. Picked by cobanov, logicrw, hellogumbo and 1 more
  342. 4of 31 TKY-27/JevSlop Other Writing quality: scores public note.com articles on eight Jev `Score` axes inside a single `systemOne` request and turns them into a 0-100 Slop Score in ordinary TypeScript. Picked by yibie, v-modal, AppitStudio and 1 more
  343. 4of 31 TypeSafeAI/typesafe-playground Other Community playground for TypeSafe AI and Jev featuring 110 real-world scenarios, dilemmas, and interactive experiments. Picked by logicrw, valentynkit, hellogumbo and 1 more
  344. 4of 31 Wizhill05/typesafe-image-diffusion Other (post) - Diffusion-style pixel art out of a classifier: 256 parallel per-pixel Jev questions plus refinement passes. Picked by hellogumbo, heyjunpenn, jtnkminimal and 1 more
  345. 4of 31 agentgateway/agentgateway Other A Jev guardrail example in Agentgateway using a webhook to inspect model requests and responses. Picked by logicrw, hellogumbo, heyjunpenn and 1 more
  346. 4of 31 ajensenwaud/hermes-jev-plugin Routing Four Hermes tools for atomic checks, routing, and rubric scoring; listed in the Hermes plugin catalog. Picked by valentynkit, hellogumbo, walidboulanouar and 1 more
  347. 4of 31 aniruddh-krovvidi/switchboard Routing Guardrail + model router for LLM gateways on TypeSafe's Jev (System One model), with an independent accuracy/calibration/latency evaluation. Stdlib Python. Picked by hellogumbo, heyjunpenn, JohnDotOwl and 1 more
  348. 4of 31 arunav25/jev-mcp Coding Agent (arunav25) - Connect JEV to MCP clients and compare its judgments against general-purpose LLMs using shared datasets and measurable accuracy. Picked by hellogumbo, heyjunpenn, walidboulanouar and 1 more
  349. 4of 31 bestagentkits/jev-skillful Coding Agent Per-prompt router over skills, MCP servers, agents, and commands, and it measures whether the injection helped. Picked by valentynkit, hellogumbo, heyjunpenn and 1 more
  350. 4of 31 binnash/typesafe-sdk SDK & Runtime (binnash) - PHP & Laravel SDK for TypeSafe AI's JEV Model series. Picked by hellogumbo, heyjunpenn, JohnDotOwl and 1 more
  351. 4of 31 buchmark/claude-jev Coding Agent Adds Jev checks to Claude Code review findings, debugging hypotheses, design options and search results. Picked by logicrw, hellogumbo, JohnDotOwl and 1 more
  352. 4of 31 chez-shanpu/typesafeai-go SDK & Runtime Go SDK for TypeSafe AI API Picked by hellogumbo, heyjunpenn, walidboulanouar and 1 more
  353. 4of 31 chy4pro/JevBrowserExt Browser Chrome extension (Manifest V3) port of Jev Ultrafast: Jev picks the operation and DOM element in one request, a small text model writes typed values, and it runs in the user's own tabs… Picked by AbdelStark, logicrw, AnotiaWang and 1 more
  354. 4of 31 codeitlikemiley/typesafe-sdk-rust SDK & Runtime A Rust client for TypeSafe with asynchronous and optional blocking calls plus typed question and answer wrappers. Picked by logicrw, hellogumbo, heyjunpenn and 1 more
  355. 4of 31 cole-gillespie/typesafe-go SDK & Runtime An unofficial Go SDK with typed answers, retries and context cancellation. Picked by logicrw, hellogumbo, heyjunpenn and 1 more
  356. 4of 31 colinmcdermott/emoji-jev Other Emoji autocomplete at the speed of typing. TypeSafe AI Jev on a Whop-hosted TanStack Start app. Picked by hellogumbo, heyjunpenn, JohnDotOwl and 1 more
  357. 4of 31 coo-quack/jev-pii-checker Other A CLI that sends text to TypeSafe Jev for PII category Nouls and a sensitivity Score, then locates spans with regex and segmentation. Picked by logicrw, hellogumbo, AppitStudio and 1 more
  358. 4of 31 different-ai/openwork Eval & Align Engineering workflow: wires Jev into its eval testkit as a verification judge so agent-produced work is gated by typed verdicts rather than a text model. Picked by yibie, v-modal, kraayenjon and 1 more
  359. 4of 31 geilt/typesafe-cli Coding Agent (geilt) - CLI and agent skill for TypeSafe System One (Jev): typed Choice, Score, and Noul judgments. Picked by hellogumbo, heyjunpenn, JohnDotOwl and 1 more
  360. 4of 31 goodrahstar/jev-column-race Other (site) - Jev vs Gemini 3.8 Flash: labelling 1,000 app reviews, 4.1× faster and 7× cheaper. Picked by hellogumbo, heyjunpenn, jtnkminimal and 1 more
  361. 4of 31 hifizz/jev-finance-benchmark Eval & Align Typesafe.ai model jev finance benchmark. Picked by hellogumbo, heyjunpenn, JohnDotOwl and 1 more
  362. 4of 31 hotchpotch/jev-reranker Search Retrieval and RAG: uses Jev Noul judgments to assess retrieved documents for relevance and usefulness as answer evidence, then sorts results and optionally filters them using a configurable… Picked by yibie, v-modal, cobanov and 1 more
  363. 4of 31 iammusham/jev-snake Other An experimental Snake environment where the game engine owns deterministic rules and TypeSafe AI's Jev makes the movement decision from structured state on every tick. Picked by hellogumbo, heyjunpenn, JohnDotOwl and 1 more
  364. 4of 31 jerryfane/omp-jev-compaction Coding Agent An Oh My Pi extension that prunes tool history verbatim and reuses decisions to limit prefix rewrites. Picked by logicrw, hellogumbo, heyjunpenn and 1 more
  365. 4of 31 justinhe16/trade-jev Other Backtests Jev as a buy, sell, or hold trader on NQ order-book data. Picked by valentynkit, hellogumbo, heyjunpenn and 1 more
  366. 4of 31 jyatesdotdev/jev-logtriage Other On-call operations: batches collapsed Loki logs into one Jev call of Noul, Score, and Choice questions, then maps answers in code to suppress, watch, review, notify, or page, with low… Picked by yibie, AbdelStark, cobanov and 1 more
  367. 4of 31 keltokhy/jsort Search Text measurement: ranks text along a plain-English criterion using pairwise Jev Noul comparisons and a locally fitted Bradley-Terry scale. Picked by yibie, hellogumbo, AppitStudio and 1 more
  368. 4of 31 kevinpita/pi-jev-context Other Opt-in Pi extension that filters older messages from model requests while preserving the original session history. Picked by cobanov, logicrw, hellogumbo and 1 more
  369. 4of 31 kxzk/typesafe-jev-drone-demo Home & IoT Simulation: Three.js drone simulator with a Python backend where Jev drives the navigation decisions. Picked by yibie, v-modal, heyjunpenn and 1 more
  370. 4of 31 lomeshdutta/skill-router Coding Agent Tell Claude Code which installed skill a session needs, using Jev (TypeSafe AI) for the decision and skills.sh for discovery. Picked by hellogumbo, heyjunpenn, JohnDotOwl and 1 more
  371. 4of 31 mattn/sqlite3-jev Data SQLite C extension enabling TypeSafe Jev judgments as native SQL functions for semantic scoring and choices. Picked by logicrw, AnotiaWang, kraayenjon and 1 more
  372. 4of 31 mgaitan/sqlite-jev Data SQLite ecosystem: loadable C extension and Python package that expose Jev Noul, Choice, and Score judgments as SQL functions and batched virtual-table queries with confidence results. Picked by yibie, v-modal, valentynkit and 1 more
  373. 4of 31 mkotlikov/jev-grug Other Helping JEV speak <3. Picked by hellogumbo, heyjunpenn, jtnkminimal and 1 more
  374. 4of 31 molis-ai/jev-workbench SDK & Runtime Defines, tests, and publishes Jev decision functions in a local UI so backends and Agents can call fixed versions. Picked by logicrw, hellogumbo, heyjunpenn and 1 more
  375. 4of 31 phureewat29/jev-got Other A Game of Thrones text-adventure demo where a language model writes the story and Jev labels the scene. Picked by logicrw, valentynkit, hellogumbo and 1 more
  376. 4of 31 rajdhakad9826/jev-router Routing Cost-aware LLM router that picks the cheapest model capable of handling a query, using TypeSafe's Jev for fast classification instead of an LLM call. Picked by logicrw, hellogumbo, walidboulanouar and 1 more
  377. 4of 31 reycn/smart-switch Computer Use Reimagined window switcher for macOS using frontier artificial intelligence. Predicted by TypeSafe's Jev model. Picked by hellogumbo, heyjunpenn, jtnkminimal and 1 more
  378. 4of 31 rupeshpoojary9/poorjev Eval & Align Local reproduction: implements Jev's typed `Choice`/`Score`/`Noul` interface on commodity zero-shot NLI models and makes the confidence honest with temperature scaling and conformal… Picked by yibie, AbdelStark, cobanov and 1 more
  379. 4of 31 saibimajdi/typesafe-dotnet-sdk SDK & Runtime .NET SDK - Community client for typed questions and confidence-scored answers. Picked by AnotiaWang, kraayenjon, anandi1989 and 1 more
  380. 4of 31 scienthoon/jev-ood-calibration Eval & Align Model evaluation: independent calibration test of Jev on 900 rule-generated support tickets it cannot have seen plus three public benchmarks, publishing every raw response, ECE against a… Picked by yibie, v-modal, hellogumbo and 1 more
  381. 4of 31 simota/tenbin Coding Agent Documentation, an MCP server and a Skill for designing Jev judgments with question linting, batch evaluation and calibration. Picked by logicrw, hellogumbo, walidboulanouar and 1 more
  382. 4of 31 trycua/cua Browser ’s preview jev-use example pairs Driver observation and execution with bounded Jev browser-action choices. Picked by logicrw, AppitStudio, ckaraca and 1 more
  383. 4of 31 twilwa/pi-typesafe SDK & Runtime Pi coding-agent extension built on the TypeSafe AI System One API (Jev). Picked by hellogumbo, heyjunpenn, walidboulanouar and 1 more
  384. 4of 31 typesend/typesafe_ai SDK & Runtime (typesend) (site) - Unofficial Elixir SDK for the TypeSafe AI API. Picked by hellogumbo, heyjunpenn, JohnDotOwl and 1 more
  385. 4of 31 ufec/jev-block-android-ad Mobile An Android notification and SMS filter that applies local OTP rules before asking Jev whether a message is advertising noise. Picked by AbdelStark, logicrw, hellogumbo and 1 more
  386. 4of 31 vercel-labs/json-render Other Generative UI: Vercel Labs' UI framework uses Jev in its compose path to pick which components and actions a rendered interface should contain. Picked by yibie, v-modal, logicrw and 1 more
  387. 4of 31 vibe-with-me-tools/n8n-nodes-jev Routing (site) - Helper n8n community node for Jev by TypeSafe. Classify, route, and score text with questions you define, and get a probability for every answer so unsure items can go to review. Picked by hellogumbo, rhc98, RadRebelSam and 1 more
  388. 4of 31 y0usaf/jev-lm Other A word-level generation experiment that asks Jev to select words or verify locally drafted continuations. Picked by logicrw, hellogumbo, heyjunpenn and 1 more
  389. 4of 31 zsavage8/padflow-jev-evals Eval & Align Typed-decision benchmark from PadFlow (land development SaaS): schemas, anonymized labeled rows, and a runner for confidence-calibrated models like TypeSafe Jev. Picked by hellogumbo, OmniJev, heyjunpenn and 1 more
  390. 4of 31 zwliJay/jev-forge Eval & Align JevForge - Open research: an end-to-end stack for auditable data construction, Qwen3.5-0.8B training, fixed Mind2Web and OOD evaluation, local serving, and a preliminary RLCD baseline. Picked by yibie, cobanov, valentynkit and 1 more
  391. 3of 31 samuelfaj/distill in Top 100 Computer Use , Lightweight coding-agent harness and TUI that routes its small decisions through Jev. Picked by OmniJev, AppitStudio, rhc98 680★
  392. 3of 31 milind-soni/tiptour-macos in Top 100 Computer Use TipTour, Menu-bar companion for macOS where Jev picks the next click from locally detected controls and TipTour executes and validates it. Picked by OmniJev, AppitStudio, yzfly 618★
  393. 3of 31 Yinsongxu/LLM2Jev in Top 100 SDK & Runtime Adapt local language models into Jev-compatible structured decision engines with Choice, Score, and Noul outputs powered by prefill-only binary inference. Picked by hellogumbo, OmniJev, RadRebelSam 73★
  394. 3of 31 savka777/jev-use in Top 100 Browser macOS computer use by voice or typing that reads the screen through the Accessibility tree rather than screenshots. Key stored in the Keychain. Picked by MrJev, RadRebelSam, dog-last 66★
  395. 3of 31 w3cj/jev-chat in Top 100 Other Jev Chat - Chat-style command bar where Jev picks the tool, arguments, and reply type, and code builds every reply from tool data. Picked by MrJev, RadRebelSam, dog-last 62★
  396. 3of 31 IAmUnbounded/save-token-jev-clean in Top 100 Other save-token-jev - Compaction that asks Jev which tool calls still matter and keeps the rest verbatim, with adapters for Claude Code, Codex, OpenCode, and raw API transcripts. Picked by valentynkit, ckaraca, ozers 57★
  397. 3of 31 hyperspaceai/jevcache in Top 100 Other memoize decisions so repeats are free, deterministic, and shareable. One 2 MB binary. Picked by hellogumbo, MrJev, RadRebelSam 51★
  398. 3of 31 achimala/jev-paint in Top 100 Other Jev Paint - Local browser app that turns batched per-pixel Jev distributions into paintings; prompts describe pixels and regions rather than sending raw images. Picked by cobanov, MrJev, RadRebelSam 42★
  399. 3of 31 skeptrunedev/jev-recruiter in Top 100 Other A Jev powered LinkedIn recruiting agent. Watch it browse relevant profiles, save links, and review evidence against your hiring brief. Picked by hellogumbo, RadRebelSam, dog-last 38★
  400. 3of 31 mizchi/jev-lint in Top 100 Other Ast-grep + TypeSafe Jev natural-language semantic linter (name/body drift, stale comments, weak tests); distinct from huntedman/JevLint. Project guide. Picked by AppitStudio, MrJev, dog-last 34★
  401. 3of 31 wundercorp/loki in Top 100 Coding Agent optionally adds Jev typed-judgment tools and routes a new session to a model within the selected gateway. Picked by logicrw, hellogumbo, heyjunpenn 26★
  402. 3of 31 danielgshea/jev-as-a-judge in Top 100 Eval & Align Using Jev as an evaluator. Picked by hellogumbo, heyjunpenn, RadRebelSam 25★
  403. 3of 31 samdotmak/jev-recall in Top 100 Search Retrieve by relevance, not resemblance: filter an AI assistant's memories with TypeSafe's Jev. Picked by hellogumbo, RadRebelSam, dog-last 24★
  404. 3of 31 win4r/jev-skill-suggester in Top 100 Coding Agent Coding agents: recommends which installed skills apply to a request, keeping the recommendation bounded and letting Jev decide. Picked by yibie, hellogumbo, RadRebelSam 18★
  405. 3of 31 runta-dev/jot in Top 100 Browser The first general-purpose System One agent for Jev. Picked by hellogumbo, MrJev, RadRebelSam 16★
  406. 3of 31 oso95/x-scanner in Top 100 Browser Chrome extension that labels every post you scroll past on X with typed Jev judgments and a live cost counter. Picked by hellogumbo, MrJev, RadRebelSam 14★
  407. 3of 31 carldaws/hunch in Top 100 Other `if Hunch.likely?("fraudulent", given: order)` reads like plain Ruby but branches on a typed Jev answer, with `pick` for Choice, `rate` for Score, and graded predicates from `possibly?` to… Picked by yibie, AbdelStark, cobanov 13★
  408. 3of 31 utk2103/jev-studio in Top 100 Coding Agent If you're experimenting with jev it will be easier from here. Picked by hellogumbo, AppitStudio, RadRebelSam 12★
  409. 3of 31 tyler-dot-earth/patdown in Top 100 Other Typesafe's jev as a "fuzzy linter". give your code an ocular patdown. Picked by hellogumbo, AppitStudio, MrJev 10★
  410. 3of 31 parth-kp/jev-mail-classifier in Top 100 Other Classify your inbox with Jev (TypeSafe's System One model) Picked by hellogumbo, AppitStudio, RadRebelSam 9★
  411. 3of 31 caiovicentino/jev-align in Top 100 Eval & Align Calibrated alignment verifier for LLM responses and agent plans Picked by hellogumbo, jtnkminimal, RadRebelSam 4★
  412. 3of 31 akash-kamat/system-one-gemma in Top 100 Eval & Align fast, calibrated decisions in a single forward pass. No text generation. Inspired by TypeSafe.ai's Jev. Picked by hellogumbo, heyjunpenn, JohnDotOwl 3★
  413. 3of 31 JanOstrowka/typesafe-assist in Top 100 Home & IoT Home Assistant Assist conversation agent powered by TypeSafe's Jev (System One) model. Picked by hellogumbo, heyjunpenn, JohnDotOwl 2★
  414. 3of 31 sightmap/jev-turbo in Top 100 Browser turbo - Jev-powered semantic browser use. Picked by hellogumbo, heyjunpenn, RadRebelSam 2★
  415. 3of 31 tylerjharden/ailerix in Top 100 Routing (site) - Type-safe model router. Jev (System One) banks each request to a typed catalog route. Picked by hellogumbo, heyjunpenn, JohnDotOwl 2★
  416. 3of 31 chris-wozniczek/jev-voice-control in Top 100 Computer Use Menu-bar Swift app turning spoken commands into Jev typed decisions and macOS actions. Picked by valentynkit, rhc98, RadRebelSam 1★
  417. 3of 31 rajivkuriakose/typesafe-jev-examples in Top 100 Other Starter examples: worked ticket-triage and reranking examples runnable through OpenRouter without an early-access key, shipped with their own sample data and Makefile. Picked by yibie, v-modal, heyjunpenn 1★
  418. 3of 31 0xPlaygrounds/rig Other Rust `rig-typesafeai` crate with typed Choice, Score, and Noul queries, response validation, examples, and fixtures. Picked by cobanov, logicrw, ckaraca
  419. 3of 31 0xtrou/rubikjev Other (site) - Challenge the Jev's intelligence in Rubik Cube puzzles. Picked by hellogumbo, heyjunpenn, jtnkminimal
  420. 3of 31 AnshChoudhary/typesafe-ai-firewall Other **0%** hard negatives blocked vs **39.2%** with a single "is this dangerous?" prompt Picked by anandi1989, aliaihub, JohnDotOwl
  421. 3of 31 Ayush0054/metis Other GitHub Action and Python CLI that triage new issues with TypeSafe Jev category labels and missing-detail follow-ups. Project guide. Picked by AppitStudio, jtnkminimal, JohnDotOwl
  422. 3of 31 BunsDev/typesafe-ai-playground Routing A community playground for TypeSafe AI's Jev: edit classification experiments, compare A/B inputs, route conversations, extract document fields, inspect code-policy decisions, and explore… Picked by fatwang2, heyjunpenn, ozers
  423. 3of 31 ComposioHQ/composio Other TypeSafe provider that shortlists tools, selects one from a bounded set, maps closed-set arguments, and exposes confidence and destructive-action gates. Picked by cobanov, logicrw, ckaraca
  424. 3of 31 DeepBlueDynamics/typesafe-arena Other A playground for TypeSafeAI's Jev Model. Picked by hellogumbo, heyjunpenn, JohnDotOwl
  425. 3of 31 GoldenLoaf24h/browserclaw Browser Browser automation: Zero-lock, session-preserving Chrome MCP server that couples a local Jev System One semantic micro-loop (`chrome_act_toward_goal`) with an 85%+ pruned DOM tree (Shadow… Picked by yibie, v-modal, cobanov
  426. 3of 31 Hexdigest123/typesafe-comment Eval & Align Small Python package that uses typesafe.ai to evaluate code comments on certain heuristics. Picked by hellogumbo, heyjunpenn, RadRebelSam
  427. 3of 31 ItisShikhar/gg-friggin-ez Other (site) - Fast, drop-in profanity and toxicity screener for Node.js, powered by TypeSafe AI Jev. Catches leetspeak, character spacing, and romanized profanity across languages including… Picked by hellogumbo, walidboulanouar, RadRebelSam
  428. 3of 31 JackZeng/Jev_apps Other 看看 Jev 能做什么：用中英文讲清热门应用、工作原理和各自优缺点。Explore Jev apps with plain-language examples, explanations, and comparisons. Picked by hellogumbo, yzfly, heyjunpenn
  429. 3of 31 Kelbie/hunch Coding Agent Code review: plain-English rules that Jev checks code against, locally or on every pull request, with Jev picking one label per finding. Picked by yibie, v-modal, heyjunpenn
  430. 3of 31 MachineLearning-Nerd/jev-tetris Other A visual TypeSafe demo where Jev chooses verified Tetris placements. Picked by hellogumbo, heyjunpenn, JohnDotOwl
  431. 3of 31 Mandrilsquad1441/jev-model-router Computer Use (Mandrilsquad1441) - Pick the best AI model and reasoning effort for any task in ~1s. Plugin for Claude Code, Claude Desktop and Codex, powered by TypeSafe's Jev decision model and live… Picked by hellogumbo, walidboulanouar, RadRebelSam
  432. 3of 31 Nainish-Rai/jev-frontend-qa Browser Frontend QA that uses Jev to choose browser actions and checks contracts through DOM, HTTP and database evidence. Picked by logicrw, hellogumbo, heyjunpenn
  433. 3of 31 NobleSpartan6/otto Computer Use Open-source native computer use for macOS and Windows: TypeSafe Jev, local OCR, and selective planning. Picked by hellogumbo, heyjunpenn, JohnDotOwl
  434. 3of 31 Ray-Hughes/jevalyn Eval & Align The decision layer for your Rails app. A Rails-native wrapper around TypeSafe's Jev System One API: typed, calibrated decisions in your control flow. Picked by hellogumbo, rhc98, RadRebelSam
  435. 3of 31 Red5d/jev-cvss Other Scripts that use Jev to select CVSS metrics from vulnerability descriptions, then compute v3.0, v3.1 or v4.0 scores in Python. Picked by logicrw, hellogumbo, RadRebelSam
  436. 3of 31 RyanKung/rotom Routing Local gateways: OpenAI- and Anthropic-compatible API gateway that carries Jev through its model catalog and evaluation path. Picked by yibie, v-modal, dog-last
  437. 3of 31 STRML/omp-jevens-classifier Other Jev-powered model-judged permission gate for OMP (TypeSafe System One). Picked by hellogumbo, heyjunpenn, JohnDotOwl
  438. 3of 31 Shogo-nfrealmusic/jev-eval Eval & Align Third-party check: compares Jev against GPT-4o-mini and Claude Sonnet 4.5 under identical conditions on the same judgment task. Picked by yibie, v-modal, jtnkminimal
  439. 3of 31 Shubham510/typesafe-go SDK & Runtime Shubham510/typesafe-go. Unofficial Go SDK for TypeSafe AI's System One API (Jev). 0 stars, Go, MIT License. Picked by walidboulanouar, MrJev, RadRebelSam
  440. 3of 31 ShuhanSun/jev-oas-sentinel Search Catch breaking API behavior hidden in OpenAPI prose with deterministic checks and TypeSafe JEV System One semantic review. Picked by hellogumbo, AppitStudio, RadRebelSam
  441. 3of 31 StefanoITA/ts-jev-cost-calculator SDK & Runtime Unofficial CLI + Python estimator of tokens, cost and context limits for TypeSafe (System One / Jev) API requests. Not affiliated with TypeSafe. Picked by rhc98, JohnDotOwl, RadRebelSam
  442. 3of 31 TanayPadar/gpt-vs-jev Other (site, post) - Compare GPT generated language with JEV structured Noul decisions on the same input. Picked by hellogumbo, heyjunpenn, jtnkminimal
  443. 3of 31 ThiagaoBR/typesafe_agent_gates Other typesafe-agent-gates - LangChain/Deep Agents middleware using TypeSafe Jev for shell gates, issue triage, MR detection, and test-spec review. Project guide. Picked by AppitStudio, RadRebelSam, dog-last
  444. 3of 31 TholeG/typesafe-chess Other Chess where both players are TypeSafe's Jev model: every move is a typed Choice decision. Picked by hellogumbo, heyjunpenn, JohnDotOwl
  445. 3of 31 TokenTrim/jev-routing-experiment Routing Benchmarking TypeSafe's Jev decision model as a cost-efficient LLM router on RouterArena. Picked by hellogumbo, heyjunpenn, walidboulanouar
  446. 3of 31 TrainLCD/Functions Coding Agent TrainLCD Jev rerank (post) - Pull request adding Jev to station-suggestion reranking in the TrainLCD transit app. Picked by hellogumbo, heyjunpenn, jtnkminimal
  447. 3of 31 WebGrga/btc-jev-signal Other Experimental multi-horizon BTC signal generator using TypeSafe Jev probabilities and Binance market data. Picked by hellogumbo, heyjunpenn, JohnDotOwl
  448. 3of 31 XieChengYuan/jev-gomoku Other A nine-board, 15×15 Gomoku workbench comparing how two Jev players respond to different input representations. Picked by logicrw, hellogumbo, heyjunpenn
  449. 3of 31 aabolfazl/typesafe-local Eval & Align Inspired by TypeSafe Ai, Ask a local LLM typed questions, get calibrated probabilities instead of text. Structured output without generation or parsing. MLX / Apple Silicon. Picked by hellogumbo, heyjunpenn, rhc98
  450. 3of 31 aaronshaf/opencode-jev-orchestrator Coding Agent Keeps an OpenCode parent model fixed and uses Jev difficulty judgments to delegate harder turns to temporary subagents. Picked by cobanov, logicrw, RadRebelSam
  451. 3of 31 abeldzan/jev-rs SDK & Runtime abeldzan/jev-rs. Async-first Rust SDK for the TypeSafe AI API. 1 stars, Rust, MIT License. Picked by walidboulanouar, JohnDotOwl, RadRebelSam
  452. 3of 31 agent-labs-dev/fastbrowse Browser Browser agents: Jev picks each action from what is on the page while an LLM reads and plans. Picked by yibie, v-modal, heyjunpenn
  453. 3of 31 antiyro/jevdroid Mobile Experimental Python framework that uses Jev to choose Android actions from accessibility trees and executes them through ADB or UIAutomator2, with explicit action permissions and per-run… Picked by AbdelStark, RadRebelSam, dog-last
  454. 3of 31 anxkhn/JevPlaysPokemon Other A Pokémon agent that lets you emulate GBA games and has Jev make the battle decisions based on the current stats, state, moves, and Pokémon. Picked by AbdelStark, valentynkit, RadRebelSam
  455. 3of 31 ashaazami/river-run-typesafe Other River shooter game in Python, inspired by Atari's River Raid, played by a TypeSafe AI pilot. Picked by hellogumbo, heyjunpenn, JohnDotOwl
  456. 3of 31 ax-llm/ax SDK & Runtime Native TypeSafe client and Ax provider for Boolean, Choice, Score, and raw Jev questions, with answer validation and examples. Picked by cobanov, logicrw, ckaraca
  457. 3of 31 backmeupplz/jev_antispam_bot Other Minimal grammY Telegram anti-spam bot powered by TypeSafe Jev. Picked by hellogumbo, AppitStudio, RadRebelSam
  458. 3of 31 baronunread/leanest Other Adds Jev-based selection before an existing test runner using diffs and test source. Picked by logicrw, fatwang2, RadRebelSam
  459. 3of 31 bastani-inc/atomic Coding Agent Coding agent runtime: ships a first-class Jev structured-output provider so an agent's decisions come back typed, through the same decision resolver as its other providers. Picked by yibie, v-modal, logicrw
  460. 3of 31 buluoray/JevOnly Other Pure Jev that can "type" and drive towards task completion. Picked by hellogumbo, AppitStudio, RadRebelSam
  461. 3of 31 cardotrejos/jev-ad-preflight Other Typesafe/Jev public X demo. Picked by hellogumbo, heyjunpenn, JohnDotOwl
  462. 3of 31 cardotrejos/jev-should-i-apply Other Typesafe/Jev public X demo. Picked by hellogumbo, heyjunpenn, JohnDotOwl
  463. 3of 31 cardotrejos/jev-user-jury Other Typesafe/Jev public X demo. Picked by hellogumbo, heyjunpenn, JohnDotOwl
  464. 3of 31 carlsonchik/judging-with-typesafe Other Скилл для агентов Letta: суждения по критериям через TypeSafe System One (Jev). Picked by hellogumbo, heyjunpenn, JohnDotOwl
  465. 3of 31 cobusgreyling/Jev Other Unofficial TypeSafe Jev showcase Picked by hellogumbo, rhc98, RadRebelSam
  466. 3of 31 cocktailpeanut/jevthoven Other Symbolic-music studio where Jev chooses plans, instruments, and bar patterns, and code renders editable music and MIDI. Picked by cobanov, logicrw, RadRebelSam
  467. 3of 31 collapseindex/jev-builder Browser (site) - A browser form for building requests to TypeSafe's Jev: pick a template, fill in the blanks, copy the request. No JSON, no install, runs locally. Picked by hellogumbo, rhc98, RadRebelSam
  468. 3of 31 collapseindex/jev-ultralightspeed Other (site) - BRRRRRRRRRRRRRRRRRRRRRR. Picked by hellogumbo, rhc98, RadRebelSam
  469. 3of 31 dakdevs/decide-mcp Coding Agent MCP ecosystem: configurable decision server with percentage scores and bias-profile routing on top of Jev. Picked by yibie, v-modal, heyjunpenn
  470. 3of 31 ddfeyes/jev-mode Eval & Align Ticket triage and file tagging on a typed-judgment model; reports 78 percent fewer tokens and 96.1 percent accuracy against a 93.7 percent baseline. Picked by valentynkit, hellogumbo, RadRebelSam
  471. 3of 31 denikuchero/jev-chess-lab Other Jev Chess Lab - Recorded chess experiments with a candid result: Jev on its own still blunders pieces. Picked by MrJev, JohnDotOwl, RadRebelSam
  472. 3of 31 dnakhoa/jev-deferred-crispification Other Position paper: the Hidden-Markov and fuzzy primitives missing from TypeSafe AI's Jev and System-One decision models. Two lemmas, one principle (Deferred Crispification), one architecture… Picked by hellogumbo, heyjunpenn, JohnDotOwl
  473. 3of 31 dzhng/duet-agent Routing Agent harness: keeps a Jev-backed routing table for deciding which model should serve a request. Picked by yibie, v-modal, heyjunpenn
  474. 3of 31 elpumberto/barrunto Browser A Chrome extension that brings TypeSafe's Jev to X.com to analyze posts as you browse. Picked by hellogumbo, heyjunpenn, JohnDotOwl
  475. 3of 31 eriestra/almond-fastloop Browser Almond-fastloop: Almond's browser computer-use rig (Chrome DevTools + TypeSafe Jev), and the Browser Use Olympics benchmark it is measured on. Picked by hellogumbo, heyjunpenn, JohnDotOwl
  476. 3of 31 ethanplusai/jev-chat-for-twitch Browser Filter any live Twitch chat with Jev: a bring-your-own-key Chrome extension. Picked by yibie, rhc98, RadRebelSam
  477. 3of 31 fstandhartinger/jevbench Eval & Align JevBench v1 - a benchmark for Jev-class typed decision models: smart, cheap, fast, reliable, open. Picked by hellogumbo, rhc98, RadRebelSam
  478. 3of 31 getexcited/stepwarden Coding Agent Every tool call your agent makes, checked before it runs. A Claude Code plugin that uses TypeSafe AI's Jev to verify each pending tool call against the session plan, then allows it, asks… Picked by hellogumbo, heyjunpenn, RadRebelSam
  479. 3of 31 hnegishi/typesafe-ai-ruby SDK & Runtime A stdlib-only Ruby client that sends Choice, Score, or Noul questions to TypeSafe System One. Picked by logicrw, walidboulanouar, RadRebelSam
  480. 3of 31 hugo-alves/jev-router-playground Routing A model-routing playground where Jev picks a candidate and users compare the resulting answers. Picked by logicrw, JohnDotOwl, RadRebelSam
  481. 3of 31 ickma2311/jev-baselines-eval Eval & Align ickma2311/jev-baselines-eval** - Pre-registered independent eval of TypeSafe Jev against a nano-class LLM, a frontier LLM, and a supervised encoder (Banking77 + CLINC150 zero-shot) Picked by RadRebelSam, dog-last, rupeshpoojary9
  482. 3of 31 iefnaf/pi-jev Coding Agent (iefnaf) - Pi extension suite powered by Jev: selective context compaction and model routing. Picked by hellogumbo, heyjunpenn, jtnkminimal
  483. 3of 31 jaewgwon/jevis Other A Flutter integration\_test package that registers allowed UI actions and lets Jev pick the next action and whether the goal is done. Picked by logicrw, RadRebelSam, dog-last
  484. 3of 31 jesset/pi-verdict SDK & Runtime deterministic rules settle clear cases first, deny blocks, ask escalates to a human confirm, and errors or timeouts deny; Jev is an optional backend, experimental, reached through… Picked by yibie, v-modal, AbdelStark
  485. 3of 31 jon-devlapaz/jev-me Other A grill-me style interrogation of your idea, with Jev doing the grilling. Picked by hellogumbo, heyjunpenn, RadRebelSam
  486. 3of 31 jonesmelton/verdict SDK & Runtime OCaml SDK - Unofficial eio-based client. Picked by AbdelStark, ckaraca, RadRebelSam
  487. 3of 31 jourdanlabs/assay-001 Eval & Align Independent pre-registered check of Jev calibration and type safety on Banking77 / CLINC150. Split verdict, full logs. Write-up: donttrustme.ai Picked by AnotiaWang, kraayenjon, AiPersonacademy
  488. 3of 31 jujumilk3/jev-calibration-audit Eval & Align Audits Jev calibration, option-wording effects and Korean judgments through public APIs and datasets. Picked by logicrw, walidboulanouar, RadRebelSam
  489. 3of 31 jvsteiner/jevex Coding Agent An Agent experiment where Jev directs a tool loop, a chat model fills arguments and prose, and MCP tools execute. Picked by logicrw, hellogumbo, heyjunpenn
  490. 3of 31 karanb192/jev-architect Coding Agent Design skill: finds, designs, and evaluates Jev decision loops, packaged as a skill with references on decision design and delivery. Picked by yibie, hellogumbo, RadRebelSam
  491. 3of 31 keltokhy/jlink SDK & Runtime Research data: links records under a plain-English match rule using Jev Noul pair judgments, with local candidate blocking and match resolution. Picked by yibie, valentynkit, AppitStudio
  492. 3of 31 keltokhy/jselect Search Research and retrieval: selects source-linked evidence within a token budget using Jev Noul relevance judgments and local diversity-aware selection. Picked by yibie, logicrw, AppitStudio
  493. 3of 31 kiarina/labs Other kiarina/labs: safety judgment: moderation plus shell-command safety checks. *Unique: strong non-English (Japanese) moderation: 36 misses vs OpenAI's 292 on 826 harmful texts.* Picked by anandi1989, aliaihub, jtnkminimal
  494. 3of 31 lahfir/agent-desktop Computer Use An optional Jev skill for agent-desktop that chooses controls and actions from native accessibility data. Picked by logicrw, MrJev, jtnkminimal
  495. 3of 31 lhemerly/mcts-agent Search Discriminative Monte Carlo Tree Search using TypeSafe Jev System One Primitives and Gemini. Picked by hellogumbo, heyjunpenn, JohnDotOwl
  496. 3of 31 malDuffin/typesafe-3d-chess Other 3D chess powered by TypeSafe AI (Jev). AI vs AI by default, or play either side. Multiple difficulty levels. Picked by hellogumbo, heyjunpenn, JohnDotOwl
  497. 3of 31 mattneel/typesafe SDK & Runtime An idiomatic Elixir client for the TypeSafe AI API. Picked by hellogumbo, heyjunpenn, walidboulanouar
  498. 3of 31 mattneel/typesafe.zig SDK & Runtime An idiomatic Zig client for the TypeSafe AI API. Picked by hellogumbo, heyjunpenn, walidboulanouar
  499. 3of 31 mizchi/jev-playground Other A MoonBit and TypeScript Jev playground covering games, browsers, command risk and small languages. Picked by logicrw, jtnkminimal, RadRebelSam
  500. 3of 31 mizorewww/laya-mlx SDK & Runtime 13.4 ms median end-to-end per short English decision, 7.4 ms with the multilingual checkpoint, and zero output tokens, with no PyTorch, Transformers runtime, or cloud API. Picked by yibie, OmniJev, rhc98
  501. 3of 31 morcoan/JevSeek Routing Local coding workspace and agent decoupling tool routing via Jev from detailed argument generation via DeepSeek. Picked by logicrw, fatwang2, ckaraca
  502. 3of 31 n3ndor/n8n-nodes-typesafe-jev Other Community n8n node for asking multiple typed questions over workflow state. Picked by cobanov, logicrw, rhc98
  503. 3of 31 ndolinschi/cartshield Other SMB checkout fraud disposition via TypeSafe Jev. Picked by hellogumbo, heyjunpenn, JohnDotOwl
  504. 3of 31 ndolinschi/jevplay Other custom Choice/Score/Noul builder with live distributions. Picked by hellogumbo, heyjunpenn, JohnDotOwl
  505. 3of 31 ndolinschi/lanebreak Routing support ticket priority+routing via TypeSafe Jev. Picked by hellogumbo, heyjunpenn, JohnDotOwl
  506. 3of 31 ndolinschi/pulselane Other clinic triage decisions via TypeSafe Jev. Picked by hellogumbo, heyjunpenn, JohnDotOwl
  507. 3of 31 ndolinschi/toolgate Coding Agent (site) - Agent tool/MCP call gate Picked by hellogumbo, heyjunpenn, JohnDotOwl
  508. 3of 31 nickthompson480/typesafe-ai-playground Mobile Community TypeSafe AI playground: 110 use cases, games, dilemmas and model challenges, with editable prompts, A/B comparisons and a mobile-friendly UI. Picked by hellogumbo, heyjunpenn, RadRebelSam
  509. 3of 31 noetion/dsh-jev Other noetion/dsh-jev. DSH bundle that registers jev_ask for TypeSafe Jev noul, choice, and score answers. 2 stars. Picked by walidboulanouar, JohnDotOwl, RadRebelSam
  510. 3of 31 ntedvs/commentcop Other Put your code comments on trial. Powered by Jev. Picked by hellogumbo, heyjunpenn, jtnkminimal
  511. 3of 31 opaielsheikh/ai-elo-ranker Search High-speed recursive AI Elo tournament engine powered by Jev and Swiss matchmaking. Picked by hellogumbo, yzfly, heyjunpenn
  512. 3of 31 opaielsheikh/ps2-ai-agent Other Autonomous PlayStation 2 AI Agent with real-time visual telemetry HUD powered by TypeSafe Jev System One. Picked by hellogumbo, heyjunpenn, JohnDotOwl
  513. 3of 31 pZacca/askjev Computer Use MCP server published on npm, with setup instructions for Claude Code, Claude Desktop, Cursor, and Codex. Picked by MrJev, jtnkminimal, JohnDotOwl
  514. 3of 31 pambrose/jev4k SDK & Runtime Kotlin DSL and client. Picked by valentynkit, hellogumbo, RadRebelSam
  515. 3of 31 pekth/draftpulse Other Experimental: live X draft viral scorer powered by TypeSafe Jev. Picked by hellogumbo, heyjunpenn, JohnDotOwl
  516. 3of 31 rashedInt32/jev-gates Coding Agent Seven calibrated gates for Claude Code (rules, scope, intent, done, claims, proof, and commit honesty) that escalate but never approve. Picked by MrJev, JohnDotOwl, RadRebelSam
  517. 3of 31 rchovatiya88/cyber-breach-jev Other Cyber-Breach: The Jev Protocol - A tactical cyberpunk arena combat game powered by TypeSafe AI Jev System One decision model. Picked by hellogumbo, heyjunpenn, JohnDotOwl
  518. 3of 31 ryanwaits/secondlayer Other Fault triage: self-hosted Stacks data service whose Slack gate and fault-triage paths both run on Jev decisions. Picked by yibie, v-modal, heyjunpenn
  519. 3of 31 shamazharikh/qwen-rlcd Eval & Align Jev-style calibrated decision model (Choice/Score/Noul) on Qwen3.5-0.8B. Picked by hellogumbo, OmniJev, heyjunpenn
  520. 3of 31 shantanugoel/mario-jev Other Python prototype that plays NES Super Mario Bros. from structured RAM observations, with Jev answering focused movement and jump questions. Picked by hellogumbo, heyjunpenn, ozers
  521. 3of 31 shinpr/jev-reranker Search Jev Reranker (Rust CLI) - Retrieval and RAG: JSON-in/JSON-out CLI that uses separate Jev `Noul` checks to rank candidates, apply evidence thresholds, or extract source text while keeping… Picked by yibie, cobanov, AppitStudio
  522. 3of 31 smasato/jev-jp-address SDK & Runtime 日本郵便 KEN_ALL をマスタに、AI SDK 経由の Jev が住所のあいまい一致にどこまで使えるかを検証. Picked by hellogumbo, heyjunpenn, RadRebelSam
  523. 3of 31 smithersai/smithers Other Agent frameworks: TypeScript workflow framework with a Jev session checker wired into its workflows. Picked by yibie, v-modal, heyjunpenn
  524. 3of 31 spoonnotfound/soupbase Other Gaming: uses Jev `Choice` judgments to answer lateral-thinking puzzle questions and assess proposed solutions, with application code requiring supported facts, a coherent explanation, and… Picked by yibie, cobanov, logicrw
  525. 3of 31 sysadarsh/zerosweep Eval & Align (site) - Autonomous System-One Triage Engine & Benchmark powered by TypeSafe AI (Jev). 75ms inference, $0 output tokens, and RLCD epistemic safety gates. Picked by hellogumbo, walidboulanouar, RadRebelSam
  526. 3of 31 thiago-ss/jev-review Eval & Align (thiago-ss) - Autonomous Jev pull-request review with typed decisions, calibrated approval gates, and trusted-owner escalation. Picked by hellogumbo, heyjunpenn, RadRebelSam
  527. 3of 31 tylerjharden/harden-jev-decides Other JEV picks which stream idea becomes the live MVP. TypeSafe System One decision board. Picked by hellogumbo, heyjunpenn, JohnDotOwl
  528. 3of 31 useopencompany/opencompany Other Agent workspace: runs its approval review through Jev so workspace actions are gated by a typed decision. Picked by yibie, v-modal, heyjunpenn
  529. 3of 31 vclic/smoking-extraction-benchmark Eval & Align Smoking-history extraction benchmark - 1,000 synthetic notes: Jev vs OpenAI structured outputs on accuracy, cost, and latency Picked by AnotiaWang, kraayenjon, AiPersonacademy
  530. 3of 31 vinilana/jev-browser Browser (vinilana) - Hybrid browser harness: an LLM turns goals into verifiable subgoals, Jev chooses each action and DOM field, Playwright acts. Picked by hellogumbo, heyjunpenn, RadRebelSam
  531. 3of 31 vinnie357/typesafe_sdk_ex SDK & Runtime Typesafe AI SDK in Elixir using Req Picked by fatwang2, hellogumbo, heyjunpenn
  532. 3of 31 vlad-terin/jev-browser Browser Jev Browser (Vlad Terin) - Agent skill + runtime: Codex plans, Jev selects elements, a runner acts and verifies each step. Picked by AnotiaWang, kraayenjon, AiPersonacademy
  533. 3of 31 vmendes90/jev-shield Browser A Chrome ad-filtering extension that uses Jev to assess promotional intent in feed elements. Picked by logicrw, hellogumbo, heyjunpenn
  534. 3of 31 xingwudao/OpenJev SDK & Runtime OpenJev: an independent Jev-inspired System One decision API based on TypeSafe.ai concepts. Choice, score and noul primitives, local mock server, Python and TypeScript SDKs. Real inference… Picked by hellogumbo, walidboulanouar, RadRebelSam
  535. 3of 31 yuyang2230/jev-agent-skill Computer Use Developer tooling: Claude Code/ZCode skill that offloads classify/route, batch-screen, score, and compliance-check judgments to Jev via OpenCode Zen's free tier, bundling a zero-dependency… Picked by yibie, AbdelStark, cobanov
  536. 3of 31 zefir1990/openjev-experiments SDK & Runtime (site) - Experiments with openjev, an open Jev-style option-logit runner, on local models. Picked by hellogumbo, heyjunpenn, JohnDotOwl
  537. 3of 31 zeredy879/minojev Eval & Align Open replica: a 547k-parameter model that answers runtime-defined `Choice` (2-255 candidates), `Boolean`, and `Score` questions with dev-calibrated distributions in one forward pass and… Picked by yibie, cobanov, logicrw
  538. 2of 31 okinaaudio/live-jev in Top 100 Computer Use `BYOK`. Early macOS Ableton Live controller: hotkey bar + TypeSafe Jev picks typed mixer/device actions from short EN/JP phrases. Project guide. Picked by AppitStudio, MrJev 36★
  539. 2of 31 Alurith/jeff in Top 100 Computer Use by Alurith - Read-only Go CLI that checks files against coded rules such as hidden side effects and weak error handling. Picked by valentynkit, MrJev 31★
  540. 2of 31 openroboto-ai/jev-robot-control in Top 100 Home & IoT , Same task, different decisions: Jev against GPT-4.1 and GPT-4o mini on a robot arm, with cost and time per episode. Picked by OmniJev, yzfly 26★
  541. 2of 31 Devin-AXIS/jev-dsh-decision in Top 100 Coding Agent Jev DSH 决策引擎｜面向 Agent Harness 的结构化决策插件。原生支持 DeepSeek Harness，通过 iPolloWork 支持 OpenCode、Codex Harness。 Picked by hellogumbo, RadRebelSam 25★
  542. 2of 31 CheshiAI/Cheshi in Top 100 Computer Use Jev-powered conversation memory: find past sessions and revisit decisions with original sources. A macOS workspace for OpenAI Codex. Manage AI conversations and agents, explore code with… Picked by hellogumbo, MrJev 16★
  543. 2of 31 erendikmenn/jev-rag-benchmark in Top 100 Search Reproducible benchmark for measuring Jev reranking quality, latency, and cost in RAG. Picked by hellogumbo, RadRebelSam 13★
  544. 2of 31 BoundaryML/feelings in Top 100 Other BAML `.feels()` / `.how()` / `.matches ()` typed AI-if methods powered by TypeSafe Jev; upstream licensing unspecified. Project guide. Picked by AppitStudio, RadRebelSam 11★
  545. 2of 31 0x7067/jev-browse in Top 100 Browser (0x7067) - Browser automation with Jev (TypeSafe) as decision model. Picked by hellogumbo, RadRebelSam 3★
  546. 2of 31 soderlind/ai-provider-for-jev in Top 100 Other Connect WordPress to TypeSafe's Jev System One model for structured decisions (choice, score, noul). Picked by hellogumbo, RadRebelSam 3★
  547. 2of 31 zhangxaochen/dsh-jev in Top 100 Other Jev (System One decision model) plugin suite for DeepSeek Harness (dsh). Picked by hellogumbo, RadRebelSam 3★
  548. 2of 31 omkarghugarkar007/actiongate-jev in Top 100 Coding Agent Runtime authorization and guardrails for AI-agent tool calls with deterministic policy and TypeSafe Jev via OpenRouter. Picked by hellogumbo, RadRebelSam 2★
  549. 2of 31 DDnim/jev-tweet-radar in Top 100 Browser A Chrome extension that scores each X timeline post with one Jev Noul batch for engagement value and optional tags. Picked by logicrw, RadRebelSam 1★
  550. 2of 31 choxos/jevchess in Top 100 Eval & Align (site) - Jev, TypeSafe's System One model, plays chess against any OpenRouter LLM, Stockfish and you. One-page web app with live moves, Jev's move probabilities, saved games and win rates. Picked by hellogumbo, RadRebelSam 1★
  551. 2of 31 kspviswa/chakravyuha-jev in Top 100 SDK & Runtime a polar ring-maze where every move is a Jev (TypeSafe System One) decision. A fun experiment: the model picks each move, the walk grades it… `★ 0` Picked by jtnkminimal, JohnDotOwl 1★
  552. 2of 31 llt22/jev-lab in Top 100 Eval & Align Hands-on research lab for TypeSafe's Jev (System One model): reproducible benchmarks of Noul/Choice/Score primitives, confidence gating, fan-out latency, agent control Picked by rhc98, RadRebelSam 1★
  553. 2of 31 0x963D/last-exit Other (site) - A cyberpunk border encounter powered by TypeSafe Jev. Bluff the guard. Inspect the receipts. Picked by hellogumbo, heyjunpenn
  554. 2of 31 0xArx/jevegis SDK & Runtime (site) - Guardrails for LLM apps in one API call. Prompt injection, jailbreaks, leaks, unsafe content. Built on TypeSafe Jev. MIT. Picked by hellogumbo, heyjunpenn
  555. 2of 31 1jehuang/jev-pr-labeler Search Semantic GitHub PR labels using Jev's typed decisions, with conceptual scope instead of line counts. Picked by hellogumbo, RadRebelSam
  556. 2of 31 455-dIAO/windows-save-token-jev-setup Coding Agent Windows Codex Skill：通过 npx 或 Git 安装，安全配置 save-token-jev 的 PreCompact/SessionStart Hooks，并提供信任、原生压缩与旧内容隔离验证。 Picked by hellogumbo, RadRebelSam
  557. 2of 31 4anti/jev-broadcast-lab Other A Jev experiment workbench centered on chess, with additional classification and matching exercises. Picked by logicrw, JohnDotOwl
  558. 2of 31 AIPI-mvoronovych/JEVBenchmark-Contradiction-Detection Other Checking JEV's Contradiction detection (Model by TypeSafe.AI). Picked by JohnDotOwl, RadRebelSam
  559. 2of 31 AIsa-team/worth-replying Other Worth Replying by AIsa. `★ 3` Picked by jtnkminimal, RadRebelSam
  560. 2of 31 AiPersonacademy/apa-agent-harness Coding Agent Safety scoring & trajectory verification harness for Claude Code, Codex, and Cursor Picked by AiPersonacademy, RadRebelSam
  561. 2of 31 AliceRoselia/Typesafe_chess_eval Eval & Align An evaluation of typesafe AI chess. As it turns out, the AI isn't doing really well even though chess is not a particularly open-ended game. Still, it's only a prototype and this probably… Picked by hellogumbo, heyjunpenn
  562. 2of 31 AppitStudio/testimonial-miner Other Testimonial miner - Python CLI that finds quotable user praise in Gmail mailboxes with one Jev request per email (message kind, app, praise quality, and a Noul per sentence) and stores… Picked by AppitStudio, RadRebelSam
  563. 2of 31 Argos1111/jev_local SDK & Runtime Replicating Jev with a local LLM. Picked by hellogumbo, MrJev
  564. 2of 31 ArkadyBuryakov/jev-preview SDK & Runtime TUI Sandbox for Typesafe Jev API. Picked by rhc98, RadRebelSam
  565. 2of 31 BerriAI/litellm Routing Jev-backed complexity routing and an optional relevance guardrail for compacting tool results before they return to an agent. Picked by cobanov, logicrw
  566. 2of 31 BoundaryML/baml Other The v1 nightly integration maps typed function return values to Jev questions; it is not part of the stable release line yet. Picked by cobanov, jtnkminimal
  567. 2of 31 BradMyrick/Jev-Rug-Checker Other A multi-chain EVM token screener built on Jev by @TypeSafe AI. Picked by JohnDotOwl, RadRebelSam
  568. 2of 31 BrendanH18/jev-lab Other Six small apps and a workbench that show what TypeSafe's Jev (System One) model can do. Picked by JohnDotOwl, RadRebelSam
  569. 2of 31 BunsDev/clarity-judge Other Multi-axis writing quality checker powered by TypeSafe AI's Jev model. Separate named checks, each with its own verdict and confidence. Picked by heyjunpenn, JohnDotOwl
  570. 2of 31 BunsDev/river-oaks Other NPCs of River Oaks Houston, Texas using Jev to power NPCs. Picked by hellogumbo, heyjunpenn
  571. 2of 31 CelestoAI/celesto Other A Celesto PR-review example prepares sandbox checks and compares a general model with Jev on candidate findings. Picked by logicrw, jtnkminimal
  572. 2of 31 Clueless-Creations/jev-ios-ultrafast Mobile Clueless-Creations/jev-ios-ultrafast** - Run iOS Simulator goals with Jev, compare decision models, and replay every attempt. Python CLI and Brigade host wrapper. Picked by RadRebelSam, dog-last
  573. 2of 31 CorieW/JevTest Browser (site) - Bounded exploratory browser testing with Jev, deterministic assertions, and replayable evidence. Picked by hellogumbo, heyjunpenn
  574. 2of 31 CrowdLinker/JevPromptCoach Coding Agent Claude Code plugin that scores how well you prompt a coding agent, and shows whether your habits are improving. Runs on TypeSafe's Jev model. Zero added latency. Picked by hellogumbo, RadRebelSam
  575. 2of 31 Dharundp6/jev-carryforward Coding Agent (site) - What your last session knew, scored against what this one is doing. MCP server: a per-project ledger written as things happen, recalled per task with TypeSafe's Jev evaluation… Picked by hellogumbo, RadRebelSam
  576. 2of 31 EmreKaplaner/rag-jev Search Make room for useful evidence. Inspectable context selection for RAG, with Jev reranking and open benchmark studies. Picked by rhc98, RadRebelSam
  577. 2of 31 Fox-Islam/jev-bias-bench Eval & Align Fox-Islam/jev-bias-bench** - A benchmark for Jev's biases, built from people who differ in one attribute at a time. Picked by RadRebelSam, dog-last
  578. 2of 31 GPT-AGI/OpenJev Other (GPT-AGI) - Jev-compatible System 开源Jev. Picked by hellogumbo, RadRebelSam
  579. 2of 31 Gaurav-Gosain/jev-alpha-bench Other Does Jev predict stock returns from news? It reads the news well; there is no tradeable alpha. Three arms separate reading from recall. Picked by hellogumbo, heyjunpenn
  580. 2of 31 Gaurav-Gosain/jev-headline-bench Other Can Jev pick the winner of a real headline A/B test? 64.5% across 10,984 Upworthy randomized experiments, 74.7% when the difference was decisive. Picked by hellogumbo, heyjunpenn
  581. 2of 31 GhrezaKh74/JevTicktRouter Other A .NET 10 and React 19 application for fast, structured AI-powered ticket triage using TypeSafe Jev. Picked by hellogumbo, heyjunpenn
  582. 2of 31 Hardel-DW/jev.mods Routing Minecraft mod where Jev tries to finish the game from scratch without a scripted route. Picked by hellogumbo, heyjunpenn
  583. 2of 31 Hldwsd/minesweeper-jev Other Minesweeper where deterministic logic does the provable work and TypeSafe Jev is consulted only when the board forces a guess. Picked by rhc98, RadRebelSam
  584. 2of 31 Jackalope-Dev/jackalope Computer Use (site) - Desktop GUI for agentic coding that routes tasks across local agents and accounts, with Jev picking the best agent per task, running basic code-review checks, and supplying context. Picked by hellogumbo, heyjunpenn
  585. 2of 31 JacquesGariepy/ORIGIN-CIVILIZATION Other AI life-and-civilization simulation: TypeSafe Jev makes every decision (typed, probabilistic, auditable); LLMs plan Picked by hellogumbo, walidboulanouar
  586. 2of 31 Jason-Doyle/jev-parallel-dispatch Browser Browser simulation for parallel Jev decisions with capacity-constrained assignment and retained evidence. Picked by rhc98, RadRebelSam
  587. 2of 31 JedimEmO/typesafe-client SDK & Runtime Unofficial typed async Rust client for the TypeSafe System One API. Picked by hellogumbo, heyjunpenn
  588. 2of 31 JordiParraCrespo/typesafe-ai-trading-showcase Other Probably (site) - Probably: live BTC, ETH, and XRP prices with a shared TypeSafe buy-or-wait demonstration. No trades placed. Picked by hellogumbo, heyjunpenn
  589. 2of 31 KamilPostrozny/pi-jev-code Search Single-agent Pi coding coprocessor with Jev semantic gates, baseline-to-current diff review, and append-only observability telemetry. Picked by hellogumbo, heyjunpenn
  590. 2of 31 Kiln-AI/jev_jsonschema SDK & Runtime Run a JSON Schema through TypeSafe's Jev API, and get JSON back. Picked by hellogumbo, RadRebelSam
  591. 2of 31 Kushwho/jev-codes Coding Agent (site) - Audit your git diff against YAML coding-standards packs using TypeSafe's Jev model, from a CLI or your AI agent's command/skill. Picked by hellogumbo, RadRebelSam
  592. 2of 31 KyleKreuter/jev2048 Other Let Jev (TypeSafeAI) solve 2048. Picked by hellogumbo, heyjunpenn
  593. 2of 31 MahmoudAdelbghany/jev-browser Browser ~300ms decisions, no LLM tokens in the loop. Benchmark vs Playwright MCP included. Picked by hellogumbo, heyjunpenn
  594. 2of 31 Mintzs/jevify Other (Mintzs) - An optimized inference engine to turn LLMs into Jev-like machines: optimized for quick, lightweight, and accurate decision-making, classification, and scoring. Picked by hellogumbo, RadRebelSam
  595. 2of 31 MithrilMan/your-signal Browser A BYOK Chrome extension using Jev to score X posts against personal preferences and adjust their display. Picked by logicrw, jtnkminimal
  596. 2of 31 NSStudent/JevSwiftSDK SDK & Runtime An independent, type-safe Swift SDK for TypeSafe Jev, with async/await, batching, retries, and SPM support. Picked by hellogumbo, RadRebelSam
  597. 2of 31 Nibir1/typesafe-go Eval & Align Zero-dependency Go SDK for TypeSafe's System One API (Jev). Typed questions in, calibrated probabilities out with static analyzers that catch bad question design at build time, a decision… Picked by rhc98, RadRebelSam
  598. 2of 31 NicolasMontone/jev-tool-permissions SDK & Runtime Adds tool-call approval and tool-list pruning to the Vercel AI SDK. Picked by logicrw, jtnkminimal
  599. 2of 31 NorbertBodziony/guard-jev Other (site) - Comment-moderation playground: paste a comment, Jev decides what to do with it. Picked by hellogumbo, heyjunpenn
  600. 2of 31 Nyarlathoteppppp/pi-jev-context Coding Agent Nyarlathoteppppp/pi-jev-context** - Cache-neutral context trimming for the pi coding agent, powered by TypeSafe Jev: long tool output cut to verbatim key lines before it enters context… Picked by AbdelStark, RadRebelSam
  601. 2of 31 Olli0103/openclaw-typesafe-ai Other An independent OpenClaw plugin registering one explicitly invoked typesafe\_decide tool. Picked by logicrw, walidboulanouar
  602. 2of 31 Patrick-SCH03/jev-issue-radar Search Jev Issue Radar is a read-only dashboard for GitHub duplicate-issue triage. It retrieves likely candidates, asks Jev whether each pair is duplicate, related, distinct, or insufficiently… Picked by logicrw, AppitStudio
  603. 2of 31 Peu77/JevFind Search Fast semantic code search CLI with path relevance and line-level confidence Picked by AiPersonacademy, RadRebelSam
  604. 2of 31 PyModel/typesafe-mcp Coding Agent , MCP adapter that exposes Jev decisions as tools. Picked by OmniJev, MrJev
  605. 2of 31 QuentinDanblon/pi-fast-jev-compaction Coding Agent Agent tooling (13):** tenet, jev-belay, jev-commit, pi-fast-jev-compaction, jev-flash-router, pi-jev, pi-jev-helm, stepwarden, AskJev-MCP, jev-compaction, jev-plugins, jevkeep, pi-jev-router Picked by heyjunpenn, RadRebelSam
  606. 2of 31 Ravinder82/jev-flash-router Coding Agent Agent tooling (13):** tenet, jev-belay, jev-commit, pi-fast-jev-compaction, jev-flash-router, pi-jev, pi-jev-helm, stepwarden, AskJev-MCP, jev-compaction, jev-plugins, jevkeep, pi-jev-router Picked by heyjunpenn, RadRebelSam
  607. 2of 31 Ripwords/agent-gate-loop Other Reusable GitHub Action: agent fix loop gated by checks, an AI reviewer, and TypeSafe Jev. Picked by hellogumbo, heyjunpenn
  608. 2of 31 RiskAverseTech/toolgate Coding Agent a calibrated tool-call firewall powered by TypeSafe Jev. Ships as a Claude Code hook. Picked by hellogumbo, AppitStudio
  609. 2of 31 RubyBrewsday/jevcumber Other (site) - Write Cucumber tests with just the .feature file. No step definitions Picked by hellogumbo, RadRebelSam
  610. 2of 31 SeeAPI/awesome-jev-use-cases Search Explore real-world use cases and projects built with TypeSafe AI's Jev: content moderation, AI agents, model routing, and semantic search. Curated by SeeAPI. Picked by rhc98, JohnDotOwl
  611. 2of 31 SergeAx/typesafe-sdk-go SDK & Runtime SergeAx/typesafe-sdk-go** - TypeSafe.AI Go SDK Picked by AbdelStark, RadRebelSam
  612. 2of 31 Shifros/Search-Function-Test Search (site) - A test project based on Jev AI, the goal is to build a search function for a blog/article website that has 100s of articles to search from, So the user can actually use the search… Picked by hellogumbo, heyjunpenn
  613. 2of 31 ShupingR/scam-shield Other (site) - Scam text message filter powered by TypeSafe's Jev model. Picked by hellogumbo, heyjunpenn
  614. 2of 31 Silbercue/public-browser Browser Browser control: lets Claude Code and Cursor drive a real Chrome profile, with a Jev loop deciding the actions, reporting roughly 30% fewer tokens and 25% lower cost. Picked by yibie, v-modal
  615. 2of 31 Solido/jev_dart SDK & Runtime Jev Dart SDK to build cli, server and Flutter apps. Picked by logicrw, RadRebelSam
  616. 2of 31 SoundBlaster/Jev4Mellea Other Jev adapter to Mellea. Picked by hellogumbo, heyjunpenn
  617. 2of 31 TheGali/terrarium Other A sandbox where a TypeSafe System One model presses the controls of a small creature. Code runs the world. Picked by hellogumbo, heyjunpenn
  618. 2of 31 Tsagaanbayr1/jev-tetris Other Real-time Tetris versus Jev, a TypeSafe decision model Picked by rhc98, RadRebelSam
  619. 2of 31 TypeSafeAI/clarity-judge Other (site) - Multi-axis writing quality checker powered by TypeSafe AI's Jev model. Separate named checks, each with its own verdict and confidence. Picked by hellogumbo, RadRebelSam
  620. 2of 31 VladyslavHontar/clear-head Coding Agent Claude Code Stop hook that checks an AI assistant's claims against what it actually read this session, using TypeSafe's Jev as the judge. Picked by hellogumbo, AppitStudio
  621. 2of 31 Wang-auspicious/codex-jev-compaction Coding Agent Curates Codex handoff context by using Jev to select old tool records while retaining selected text verbatim. Picked by logicrw, RadRebelSam
  622. 2of 31 Wang-auspicious/pi-jev-compaction Coding Agent Extractive context compaction for Pi that keeps selected original tool records instead of generating a summary. Picked by logicrw, RadRebelSam
  623. 2of 31 WeSecureYou/Jev-test SDK & Runtime Job Risk Analyzer (site) - Job Risk Analyzer: CLI and REST API that uses Jev to score an occupation's exposure to AI-driven layoffs and its resilience. Picked by hellogumbo, heyjunpenn
  624. 2of 31 WebGrga/jev-board-lab Other Interactive explorer and Jev question workspace for Jev Board datasets. Picked by hellogumbo, heyjunpenn
  625. 2of 31 WrongStack/WrongStack Other An optional Jev dispatch classifier for choosing among WrongStack specialist Agents. Picked by logicrw, ckaraca
  626. 2of 31 Yasserbhb/Agent-JEV-Tetris Other Using the new model JEV to play the game tetris. Picked by hellogumbo, heyjunpenn
  627. 2of 31 Z761293629/pi-jev-helm Coding Agent Agent tooling (13):** tenet, jev-belay, jev-commit, pi-fast-jev-compaction, jev-flash-router, pi-jev, pi-jev-helm, stepwarden, AskJev-MCP, jev-compaction, jev-plugins, jevkeep, pi-jev-router Picked by heyjunpenn, RadRebelSam
  628. 2of 31 Zahrannnn/zcode-jev Other gates from PRD to ship. Jev-ready, provider-agnostic. Picked by hellogumbo, heyjunpenn
  629. 2of 31 abhishekashokvkumar/jev-mcp-dispatcher Coding Agent abhishekashokvkumar/jev-mcp-dispatcher. Natural-language MCP tool dispatcher powered entirely by TypeSafe's Jev , no general-purpose LLM. Discovers a simple MCP server's tool signatures at… Picked by walidboulanouar, RadRebelSam
  630. 2of 31 achimala/jevinci Other Creative experiment: paints images by having Jev predict every pixel's colour in parallel, with predicted confidence deciding how wide each stroke is drawn. Picked by yibie, v-modal
  631. 2of 31 adtyavrdhn/pydantic-jev-examples Other Pydantic AI capabilities made stronger with Jev: small runnable demos, one file each. Picked by hellogumbo, heyjunpenn
  632. 2of 31 agentjido/req_llm Eval & Align A TypeSafe provider for calling Jev through ReqLLM’s evaluate interface in Elixir. Picked by logicrw, ckaraca
  633. 2of 31 ai-suifeng/comment-jev-chrome Browser Typed four-way triage of social-media comments, with hostility scoring for malicious ones. `★ 1` Picked by jtnkminimal, RadRebelSam
  634. 2of 31 aidil2105/jev-browser-pilot Browser Browser & computer use (6):** jev-social, jev-skip, jevarena, jev-browser-pilot, jevlens, jev-orb Picked by heyjunpenn, MumuTW
  635. 2of 31 aieo-product/jev-gamebenchmark Eval & Align Sandbox & benchmark: optimize how you ask Jev (TypeSafe System One) to play falling-block puzzle games, head-to-head against LLMs. `★ 0` Picked by jtnkminimal, JohnDotOwl
  636. 2of 31 alexshpunt/pi-agent-foreman Other (site) - Send Pi agents back to work when they stop before the job is done. Picked by hellogumbo, heyjunpenn
  637. 2of 31 atharvamhaske/typesafe-sdk-go SDK & Runtime (atharvamhaske) - Unofficial go sdk for typesafe ai. Picked by hellogumbo, RadRebelSam
  638. 2of 31 awun8191/jev-resume-analyzer Eval & Align CV diagnostics and job alignment with TypeSafe Jev, React and FastAPI. Picked by hellogumbo, heyjunpenn
  639. 2of 31 az9713/jev-model-router Routing (site) - Jev (TypeSafe) model router on the Vercel AI Gateway. Picked by hellogumbo, RadRebelSam
  640. 2of 31 bestagentkits/typesafe-demo-mcp Coding Agent MCP server exposing TypeSafe System One judgments (noul, choice, score) as agent tools. Picked by hellogumbo, heyjunpenn
  641. 2of 31 blas0/jev-shadcn-lint-eval Eval & Align A small second eval for shadcn-ui/lint that uses TypeSafe's Jev to judge the linter's own output. Picked by hellogumbo, heyjunpenn
  642. 2of 31 bojansandhaus/jev-decisions Other (site) - Safety checks for Hermes and other AI agents before they act, ask for approval, or verify a change. Picked by hellogumbo, RadRebelSam
  643. 2of 31 bottlebrushes/jev-orb Browser Browser & computer use (6):** jev-social, jev-skip, jevarena, jev-browser-pilot, jevlens, jev-orb Picked by heyjunpenn, RadRebelSam
  644. 2of 31 brandonbryant12/transcript-scorecard Other ACME live support-call scoring demo with TypeSafe AI, Effect, SQLite, React, Vite, and Turborepo. Picked by hellogumbo, heyjunpenn
  645. 2of 31 brnyxx/jev-ra Browser (site) - Browser use for coding agents, 3-5x faster than browser-use. MCP server + CLI; TypeSafe Jev decides every step in ~300 ms. Picked by hellogumbo, RadRebelSam
  646. 2of 31 brudarko/jev-mac-voice Computer Use English full-duplex voice control for macOS with OpenAI Realtime, native Accessibility, and Jev. Picked by hellogumbo, RadRebelSam
  647. 2of 31 buberlo/dsh-jev Other Jev-powered decision layer for DeepSeek Harness. Picked by rhc98, RadRebelSam
  648. 2of 31 ca7ai/jev-prompt-sentry Routing Anthropic Messages reverse proxy that screens jailbreaks/injections with one batched TypeSafe Jev call (PolyForm Noncommercial). Project guide. Picked by AppitStudio, dog-last
  649. 2of 31 cablehead/jev.nu Eval & Align Nushell module for the TypeSafe System One API: typed decisions with calibrated probabilities. Picked by hellogumbo, RadRebelSam
  650. 2of 31 can1357/oh-my-pi Other Oh My Pi includes an optional TypeSafe judgment provider for bounded decisions in coding-agent workflows. Picked by logicrw, jtnkminimal
  651. 2of 31 carlaiau/jev-reranking Search Search engine experimentation on the TREC collections. Currently focused on zero-shot reranking implementations with typesafe.ai's JEV model. Picked by JohnDotOwl, RadRebelSam
  652. 2of 31 cbetz/extremely-specific-council Other (site) - Twelve members. Zero qualifications. A playful TypeSafe AI council with animated votes, inspectable decisions, and shareable verdicts. Picked by hellogumbo, heyjunpenn
  653. 2of 31 cequence-io/openai-scala-client SDK & Runtime A dedicated TypeSafe module in a Scala client that supports multiple AI providers. Picked by logicrw, ckaraca
  654. 2of 31 chrishan17/claude-jev-mod Coding Agent chrishan17/claude-jev-mod. Typed decisions in Claude Code: adds $.jev over TypeSafe's Jev, through OpenRouter, Vercel AI Gateway, Cloudflare Workers AI, LiteLLM or the TypeSafe API. 1… Picked by walidboulanouar, RadRebelSam
  655. 2of 31 clankagent/pi-jev Coding Agent Jev-powered semantic process conditions and skill suggestions for Pi. Picked by JohnDotOwl, RadRebelSam
  656. 2of 31 cline/plugins Browser Cline plugins - Coding agents: Cline's official plugin collection includes a Jev-driven browser plugin (`jev-browser`), so Jev arrives as a first-class Cline capability. Picked by yibie, v-modal
  657. 2of 31 cmartinez9/jev-judge-bench Other compare Jev (TypeSafe System One) against a frontier LLM judge on speed, cost, and agreement with human labels. Picked by JohnDotOwl, RadRebelSam
  658. 2of 31 codeitlikemiley/system-one-adapter-rust Eval & Align Rust port of TypeSafe system-one-adapter (LLM-backed system_one evaluations). Picked by hellogumbo, heyjunpenn
  659. 2of 31 community-ports/typesafeai-sdk-rust-community SDK & Runtime community-ports/typesafeai-sdk-rust-community. Community-built Rust SDK for the TypeSafe AI API (System One / Jev). A port of typesafe-sdk-python. 0 stars, Rust, MIT License. Picked by walidboulanouar, RadRebelSam
  660. 2of 31 compozy/compozy Coding Agent Context-pruning proxy for Claude Code and Codex: Jev judges which history is still needed, measured not claimed. POC here now, heading soon into Compozy. Picked by heyjunpenn, RadRebelSam
  661. 2of 31 compozy/compozy. Coding Agent yoshi - Context-pruning proxy for Claude Code and Codex: Jev judges which history is still needed, measured not claimed. POC here now, heading soon into Picked by hellogumbo, JohnDotOwl
  662. 2of 31 copyleftdev/jev-labs Other (site) - Never confidently wrong: a TLA+-verified consensus kernel around TypeSafe's Jev, run through 1,680 chaos-tested pharmacy decisions with zero wrong verdicts. Film, code, and every… Picked by hellogumbo, RadRebelSam
  663. 2of 31 cpaczek/s1s Search (site) - System One Search: navigate and trace code with TypeSafe judgments and repository evidence. Picked by hellogumbo, heyjunpenn
  664. 2of 31 ctaxnagomi/dgui-hypermem Coding Agent (site) - DGUI-HyperMem (DeckerGUI HyperMemory) - self-hosted hybrid memory MCP server on Cloudflare Workers with a JEV (Choice/Noul/Score) reasoning layer and a HuggingFace training-brain… Picked by hellogumbo, RadRebelSam
  665. 2of 31 david-cermak/jevlike-esp32 Other Edge deployment: exports a jevlike scorer as ESP32 firmware with a C scorer and a host-side check, putting one-pass decisions on a microcontroller. Picked by yibie, v-modal
  666. 2of 31 davila7/claude-code-templates Coding Agent A community Claude Code Templates mod that uses Jev to suggest subagent models and reasoning levels. Picked by logicrw, AppitStudio
  667. 2of 31 derinworks/penr-oz-jev-syslog-analyzer Other An asyncio daemon that tails journald or syslog and asks Jev, for each event, which subsystem it belongs to, how severe it is, and whether it's noise. Plain code then ignores the event… Picked by JohnDotOwl, RadRebelSam
  668. 2of 31 djascorp/jev-trade Other Trading project using JEV by TypeSafe AI. Picked by JohnDotOwl, RadRebelSam
  669. 2of 31 donvito/ai-backends Eval & Align donvito/ai-backends - API server with a dedicated Jev evaluation endpoint and an interactive playground for typed decisions. ⭐ 145 Picked by ckaraca, jtnkminimal
  670. 2of 31 dottxt-ai/outlines Other , "Efficient Guided Generation for Large Language Models". The finite-state-machine guided decoding HN named as the incumbent way to get typed values, which Jev claims to replace. Picked by OmniJev, rupeshpoojary9
  671. 2of 31 ellistev/typesafe-minecraft-demo Other A Minecraft Java player controlled by TypeSafe AI, with live decisions, Canadian flag building, and a side-by-side dashboard. Picked by hellogumbo, heyjunpenn
  672. 2of 31 erhanmeydan/jev2048 Other (erhanmeydan) - TypeSafe'in Jev karar modeli gerçek bir online 2048 sitesinde oynuyor Picked by hellogumbo, RadRebelSam
  673. 2of 31 eriestra/browser-use-olympics Browser Browser Use Olympics by Almond: one prompt, five events, one clock. Plus fast loop, a ~200-line browser computer-use agent (Chrome DevTools + TypeSafe Jev). Picked by hellogumbo, heyjunpenn
  674. 2of 31 florian-hoenicke/jev-gpt Other Cascaded Choice questions that make Jev pick the next word from a word tree instead of generating text. Picked by logicrw, RadRebelSam
  675. 2of 31 gemanor/jev-code-review-benchmark Coding Agent Comparing Jev, Gemini Flash, and Claude Fable on Python code review rules: cost, speed, accuracy, and consistency. Includes results, charts, and… `★ 1` Picked by jtnkminimal, RadRebelSam
  676. 2of 31 godspede/construct-auto-classifier Coding Agent (site) - Effect-based safety gate for AI coding agents' shell commands (OpenCode, Antigravity): fast structural rules, then TypeSafe's Jev or a chat model judges what a command does… Picked by hellogumbo, RadRebelSam
  677. 2of 31 gpazo/jev-vphone-cli Other Jev from Typesafe.ai + vphone-cli. Picked by JohnDotOwl, RadRebelSam
  678. 2of 31 greenyamao/Antigravity-mcp-semantic-search-with-TypeSafeAi Coding Agent Fast semantic code search & diff sanity auditor for AI coding assistants (Antigravity, Cursor, Claude Code) powered by TypeSafe System One. Picked by hellogumbo, heyjunpenn
  679. 2of 31 grishahq/decisionbridge Eval & Align A Jev-inspired decision interface for existing LLMs. Explicit choices, scores, calibration, and review thresholds. Picked by hellogumbo, heyjunpenn
  680. 2of 31 gudcks0305/jev-java Routing (gudcks0305) - Unofficial Java SDK for TypeSafe Jev and Vercel AI Gateway, with Spring Boot and WebClient support. Picked by hellogumbo, RadRebelSam
  681. 2of 31 guidance-ai/guidance SDK & Runtime , Constrained generation library named on the HN launch thread as what Jev's typed outputs get compared against. Picked by OmniJev, rupeshpoojary9
  682. 2of 31 harrymunro/decision-first Coding Agent Agent skill that tries TypeSafe Jev on bounded-judgment steps first and documents every attempt in a reusable decision lab. Project guide. Picked by AppitStudio, RadRebelSam
  683. 2of 31 heiwa4126/jev-bun1 SDK & Runtime TypeSafe の Jev を TypeScript SDK で使ってみる最初の 1 歩. Picked by hellogumbo, heyjunpenn
  684. 2of 31 hemanth/jev-chess Eval & Align (site) - Chess moves, evaluations, persona opponents, and game classification with TypeSafe AI System One. Picked by hellogumbo, RadRebelSam
  685. 2of 31 hemanth/pkg-gate Other (site) - Pre-install security gate for npm lifecycle scripts using TypeSafe System One. Picked by hellogumbo, heyjunpenn
  686. 2of 31 hfiguera/typesafe_ai SDK & Runtime (hfiguera) - A supervised Mint client for the TypeSafe AI System One API. Picked by hellogumbo, heyjunpenn
  687. 2of 31 hide-G/magi-system-on-jev Other MAGI system (Neon Genesis Evangelion) recreated with Jev, TypeSafe AI's System One model. 3 sages deliberate your question. Picked by JohnDotOwl, RadRebelSam
  688. 2of 31 i2cjak/RISC-jeV Other I tortured Jev into being a RISC-V CPU. Picked by hellogumbo, heyjunpenn
  689. 2of 31 iJ03l/jear Routing Rust Jev-routed client for NEAR AI Cloud inference and IronClaw agents using budget/quality/sensitivity decisions. Project guide. Picked by AppitStudio, walidboulanouar
  690. 2of 31 ibrahemid/jevprune Other Filter command output for coding agents using a task description. Picked by hellogumbo, RadRebelSam
  691. 2of 31 ickas/battleship-vs-jev Eval & Align ickas/battleship-vs-jev** - A 60-game benchmark of TypeSafe's Jev evaluation model playing Battleship. The model matches plain code; it does not beat it. Picked by RadRebelSam, dog-last
  692. 2of 31 ilkerulusoy/pi-jev-compact Coding Agent Selective, verbatim context compaction for Pi using Jev model. Picked by cobanov, logicrw
  693. 2of 31 ilyamk/jev-gmail-ai-spam-filter-and-labeling Other Self-hosted AI email classifier for Gmail powered by Jev. Create custom labels, organize your inbox, and filter spam with confidence and cost controls. Picked by hellogumbo, RadRebelSam
  694. 2of 31 imMamdouhaboammar/fable-jev Other ⚡ Sub-100ms cognitive reflexes for autonomous coding agents. Powered by TypeSafe AI's Jev & get-fable. Picked by hellogumbo, RadRebelSam
  695. 2of 31 innocentdiaz/s1_ruby Other Ruby ecosystem: makes System One measurement, and the collapse that follows it, a Ruby primitive, with a TypeSafe provider behind its own spec suite. Picked by yibie, v-modal
  696. 2of 31 irfndi/prism-liquidity-agent Other A Solana liquidity Agent with Jev shadow judgments compared against rule-based decisions. Picked by logicrw, MrJev
  697. 2of 31 islee23520/omo-jevlike-router Coding Agent Skill routing: shrinks the skill catalog in a system prompt with one forward pass over a frozen Qwen, routing each request Jev-style. Picked by yibie, v-modal
  698. 2of 31 jaibhasin/jev-yt-time-saver Browser A Chrome extension that covers distracting YouTube videos with Jev. Show anyway whenever you want. Picked by hellogumbo, RadRebelSam
  699. 2of 31 jammaru/jev-lab Other hundred - 100 AI NPCs live in a tiny town. Jev chooses the next action; the world writes the story. Picked by hellogumbo, heyjunpenn
  700. 2of 31 jason-allen-oneal/openclaw-plugin-typesafe-ai Coding Agent TypeSafe AI (Jev System One) plugin for OpenClaw - sub-100ms group triage, tool safety guardrails, compaction curation, and model routing. Picked by JohnDotOwl, RadRebelSam
  701. 2of 31 jekozyra/pi-typesafe-router Routing Coding agents: routes Pi's work through typed Jev decisions. Picked by yibie, v-modal
  702. 2of 31 jevbook/jevscan Coding Agent An EVM Token screening tool with library, CLI and MCP interfaces for market-feature-based risk judgments. Picked by logicrw, RadRebelSam
  703. 2of 31 jiawei686/jev-ultrafast-mcp Browser (site) - Hand the browser work off: an MCP server where a decision model drives the page for your agent, so a flow costs one tool call instead of a turn per click. Ref-based element tables… Picked by hellogumbo, RadRebelSam
  704. 2of 31 jms-dcksn/jev-pii-guardrail Other jms-dcksn/jev-pii-guardrail** - A UiPath coded agent with a custom PII detection guardrail on the LLM boundary, built on the TypeSafe Jev model as a LangChain awrap_model_call middleware. Picked by RadRebelSam, dog-last
  705. 2of 31 juancamiloqhz/roverlab Other A 3D planetary rover sandbox for experimenting with autonomous decisions using TypeSafe AI. Picked by hellogumbo, heyjunpenn
  706. 2of 31 juanegido/jev-pr-judge Other Typed pull-request verdicts via one parallel TypeSafe Jev call, code-owned policy profiles, Next.js UI, and a sticky-comment GitHub Action. Project guide. Picked by AppitStudio, JohnDotOwl
  707. 2of 31 juanlentino/jev-connector SDK & Runtime WordPress connector for the TypeSafe System One API (Jev): typed questions, confidence-scored answers, core Connectors API key management. Picked by rhc98, RadRebelSam
  708. 2of 31 jxucoder/mimicry Other Rewrite AI drafts in your own voice with a bounded TypeSafe feedback loop. Picked by hellogumbo, heyjunpenn
  709. 2of 31 kazz187/jev-sdk-go SDK & Runtime Go 1.27 client for TypeSafe AI's Jev (System One) API: typed questions, typed answers. Picked by JohnDotOwl, RadRebelSam
  710. 2of 31 kesku/jev-freeform Other An observable raw-character chat experiment powered entirely by TypeSafe Jev Choice. Picked by hellogumbo, heyjunpenn
  711. 2of 31 komikat/psearch Search Parallel web search for terminals and agents, with local Chromium and Jev-guided exploration. Picked by hellogumbo, heyjunpenn
  712. 2of 31 krw82/jev-playwright-mcp Browser page-state triage, prompt-injection shielding, goal-based snapshot pruning, risky-action gating. Drop-in wrapper around @playwright/mcp for any coding agent. Picked by hellogumbo, heyjunpenn
  713. 2of 31 krzyzanowskim/TypeSafe Eval & Align (Swift) - SwiftPM client for TypeSafe System One Noul/Choice/Score questions, aligned with the official JS SDK shape. Project guide. Picked by AppitStudio, MrJev
  714. 2of 31 kubet/azdaja Other Bare, open-source RLM layer for existing coding agents Picked by logicrw, valentynkit
  715. 2of 31 kuhung/understanding-jev Other 深入解读 Jev 模型：毫秒级判定与工程边界 - Chinese deep-dive: examines Jev's millisecond judgments and, more usefully, where its engineering boundaries lie. Picked by yibie, v-modal
  716. 2of 31 kuldeepsinh19/jev-decision-gateway Routing A gateway that asks Jev continue / tool / verify questions and invokes a generative LLM only when policy says generation is needed. Picked by logicrw, RadRebelSam
  717. 2of 31 kunchenguid/compact-adviser Other "Work appears completed or recorded. Run /compact to save tokens." Picked by yzfly, MrJev
  718. 2of 31 kyrylosyzonenko/jev-browse Browser Drives a real browser with Jev making every decision and Vercel's agent-browser performing every action, with a benchmark. Picked by hellogumbo, heyjunpenn
  719. 2of 31 kyu1204/jgrep Search kyu1204/jgrep** - grep for what code does, not what it's called. Semantic code search powered by TypeSafe Jev. Picked by AbdelStark, RadRebelSam
  720. 2of 31 lab-dados/jev-anotacao-sentencas Other (site) - Jev (TypeSafe) vs. Gemini 3.8 Flash vs. GPT-5.6 Luna na anotação estruturada de sentenças do TJSP: qualidade, tempo e custo. Picked by hellogumbo, heyjunpenn
  721. 2of 31 lambertsj/beatjev Browser (site, post) - Browser game: try to beat Jev at spotting a spam message. Picked by hellogumbo, heyjunpenn
  722. 2of 31 langchain-ai/langchain Routing Python `TypeSafeClassifier` Runnable with batched typed questions plus model-routing and risky-tool middleware. Picked by cobanov, logicrw
  723. 2of 31 langchain-ai/langchainjs Routing LangChain.js - JavaScript/TypeScript classifier Runnable and middleware for bounded routing and tool-call checks. Picked by cobanov, logicrw
  724. 2of 31 laravel/ai Other Laravel AI - Provides typed classification and a TypeSafe provider for Laravel applications, with fake responses for application testing. Project guide. Picked by AppitStudio, jtnkminimal
  725. 2of 31 leftspace89/JevBird Routing A Python Flappy Bird game where code simulates candidate routes and Jev picks one. Picked by logicrw, RadRebelSam
  726. 2of 31 lmvdz/rpg-jev Other A living-world RPG whose NPCs are decided by TypeSafe's Jev judge model; code owns rules, numbers and state. Picked by JohnDotOwl, RadRebelSam
  727. 2of 31 lucianfialho/jev-model-router Routing (lucianfialho) - Cost-optimized OpenRouter model router using TypeSafe's Jev, with a live full-catalog scorer instead of a hardcoded model list. Picked by hellogumbo, RadRebelSam
  728. 2of 31 luxus/ha-conversation-jev Routing A Home Assistant conversation integration routing simple lighting commands to services and other requests to Grok. Picked by logicrw, fatwang2
  729. 2of 31 m0rphtail/triagedy Other Security alert triage as a Unix filter: JSONL alerts in, typed decisions out. Picked by MrJev, RadRebelSam
  730. 2of 31 maddygoround/typesafeai-cli Computer Use Python `typesafe` CLI for TypeSafe Jev ask/decide/screen/verify flows for humans and agents. Project guide. Picked by AppitStudio, RadRebelSam
  731. 2of 31 madeye/pi-jev Search Jev-assisted file retrieval and request caching for faster Pi workflows. Picked by hellogumbo, RadRebelSam
  732. 2of 31 marandaneto/typesafe-sdk-swift SDK & Runtime Unofficial, experimental Swift client with typed answers, async/await, and Swift Package Manager support. Picked by AbdelStark, logicrw
  733. 2of 31 marcus/frost Routing (site) - A flexible and configurable CLI model router using TypeSafe Jev. Picked by hellogumbo, heyjunpenn
  734. 2of 31 meetr1912/jev-sonar Eval & Align TypeSafe Jev plays Battleship: one ~100-question typed fan-out per turn returns a calibrated hit-probability heatmap that is also the move policy. Picked by rhc98, RadRebelSam
  735. 2of 31 miniLV/Jev-Auto-Router Coding Agent Jev Auto Router - Coding agents: per-call Codex GPT routing where Jev makes one typed Choice over host-available (model, effort) pairs; a local Responses proxy keeps the tool loop… Picked by yibie, RadRebelSam
  736. 2of 31 minorun365/jev-cloud-quiz Other (site) - 三大クラウドの機能名を、TypeSafe AI の System One モデル Jev が確率つきで判定するデモ. Picked by hellogumbo, RadRebelSam
  737. 2of 31 misbahsy/doc-router Computer Use Routes PDF pages between local text extraction and OCR using optional Jev judgments, with a Rust CLI and Python bindings. Project guide. Picked by AppitStudio, MrJev
  738. 2of 31 mmastrac/djev-spark Other DiffusionGemma NVFP4 structured decisions on a DGX Spark: container recipe Picked by yzfly, jtnkminimal
  739. 2of 31 moezubair/check-risk Other A CLI and GitHub Action that assesses code-change risk using deterministic rules and TypeSafe Jev, recommending checks and reviewers before merge. Picked by hellogumbo, heyjunpenn
  740. 2of 31 monotykamary/pi-fabric SDK & Runtime Pi’s programmable runtime includes an optional Jev loop for observing state, making decisions and running bounded actions. Picked by logicrw, ckaraca
  741. 2of 31 mstf-svndk/jev-windows-voice Browser Türkçe ve İngilizce doğal konuşmayla Windows 10/11 bilgisayar kontrolü: OpenAI Realtime, local Whisper, Jev, UI Automation ve Playwright. Picked by hellogumbo, RadRebelSam
  742. 2of 31 muhammedilyasy/jev-mail Browser Chrome extension that triages Gmail with TypeSafe's Jev model: category, priority, spam % and reply % on every email. Picked by hellogumbo, RadRebelSam
  743. 2of 31 muse0509/jev-preflight Coding Agent Claude Code Stop-hook risk check: TypeSafe Jev scores eight axes over a redacted turn diff, with optional one-shot reinspection. Project guide. Picked by AppitStudio, RadRebelSam
  744. 2of 31 myokoym/misereru-slide-jev Other (site) - Ongoing Japanese research deck on Jev and System One models, maintained as Markdown slides. Picked by hellogumbo, heyjunpenn
  745. 2of 31 mzainzulifqar/jev-php-sdk Eval & Align (site) - PHP SDK for TypeSafe's Jev: send text and typed questions, get typed answers with calibrated confidence. PHP 8.1+, works with any PSR-18 client, Laravel 8–13. Picked by hellogumbo, RadRebelSam
  746. 2of 31 n-yokomachi/jev-dev Routing 同じ発言を jev と LLM の両方に判定させ、感情の変動値のズレと応答速度を1画面で見比べるデモ（affectus + Vercel AI Gateway）. Picked by hellogumbo, heyjunpenn
  747. 2of 31 narulaskaran/jev-data-questions Other Jev Gamecast (site) - Jev Gamecast: replay-first React app that asks Jev typed questions about live sports data. Picked by hellogumbo, heyjunpenn
  748. 2of 31 ndolinschi/harnessjudge Other ok / retry / escalate / stop via TypeSafe Jev. Picked by hellogumbo, heyjunpenn
  749. 2of 31 ndolinschi/hiresignal Other resume first-pass fit+interview via TypeSafe Jev. Picked by hellogumbo, heyjunpenn
  750. 2of 31 ndolinschi/mcpmatch Coding Agent (site) - Match user goals to MCP catalog (two-stage) via TypeSafe Jev. Picked by hellogumbo, heyjunpenn
  751. 2of 31 ndolinschi/spendbrake Other continue / downgrade_model / stop via TypeSafe Jev. Picked by hellogumbo, heyjunpenn
  752. 2of 31 ndolinschi/swarmrouter Browser (site) - Route tasks to research/code/browser/support/writer agents via TypeSafe Jev. Picked by hellogumbo, heyjunpenn
  753. 2of 31 ndolinschi/trustgate Other indie media T&S gate via TypeSafe Jev. Picked by hellogumbo, heyjunpenn
  754. 2of 31 neddes/sloppy-jevs-extension Browser Open-source Chrome extension that filters AI-generated prose and ads with Jev. Picked by hellogumbo, heyjunpenn
  755. 2of 31 newuser7171/antivirus SDK & Runtime A file scanner that sends extracted features to Jev for a verdict, a 0–4 severity score, and Noul indicators, then applies local quarantine or review rules. Picked by logicrw, AiPersonacademy
  756. 2of 31 nexibeo/jev-organize Coding Agent (site) - Throw in a pile of company files and get them classified and organized by department, type, sensitivity, date, counterparty and PII, with an index for AI agents. Powered by… Picked by hellogumbo, RadRebelSam
  757. 2of 31 nican2018/shade-arena-jev-monitor Eval & Align Evaluating TypeSafe's Jev as a fast monitor and action gate for agent sabotage in SHADE-Arena, compared with Gemini 2.5 Flash/Pro. Picked by hellogumbo, heyjunpenn
  758. 2of 31 nitoba/questions SDK & Runtime A TypeScript decision library that asks typed questions via Zod or native batches, defaulting to TypeSafe Jev, with optional Vercel or generative adapters. Picked by logicrw, jtnkminimal
  759. 2of 31 onionminionops-beep/pdoom-protocol Other co-op platform shooter where TypeSafe Jev plays alongside you. Picked by hellogumbo, heyjunpenn
  760. 2of 31 picaye/jev-compaction Coding Agent Agent tooling (13):** tenet, jev-belay, jev-commit, pi-fast-jev-compaction, jev-flash-router, pi-jev, pi-jev-helm, stepwarden, AskJev-MCP, jev-compaction, jev-plugins, jevkeep, pi-jev-router Picked by heyjunpenn, jtnkminimal
  761. 2of 31 poponline63/hermes-jev-north-star Coding Agent A Hermes goal-checking skill that saves requirements, creates a run prompt and checks completion evidence. Picked by logicrw, RadRebelSam
  762. 2of 31 pydantic/pydantic-ai Routing Pydantic AI - TypeSafe model provider that derives Jev questions from Pydantic output types and supports typed routing and fallback workflows. Picked by cobanov, logicrw
  763. 2of 31 rainbowpuffpuff/jev-builder-loop Coding Agent Grok skill: Jev as a judgment sensor in a builder-agent loop (priors × probabilities → next act). Picked by hellogumbo, heyjunpenn
  764. 2of 31 rbalch/typesafeai-review Other Using Typesafe.AI to generate diff reviews. Picked by hellogumbo, heyjunpenn
  765. 2of 31 realZachi/jevtest Search (site) - Semantic test matchers for Vitest and Jest, powered by TypeSafe's Jev model. Write expectations in plain English, get calibrated probabilities back. Picked by hellogumbo, RadRebelSam
  766. 2of 31 rhighs/jev-code Other An experimental coding CLI where Jev selects AST productions for Python or Bash, with a separate command-line decision mode. Picked by logicrw, RadRebelSam
  767. 2of 31 rnjsxodyd90/jev-relay SDK & Runtime A typed Jev decision gate, local-voice interpreter workbench, and reproducible Jev vs Qwen research. Picked by rhc98, RadRebelSam
  768. 2of 31 rsdkrasen/hermes-jev-router Routing rsdkrasen/hermes-jev-router. TypeSafe/Jev router plugin for Hermes Agent , compact tool results, suppress duplicate tools, skip unnecessary main-model calls. 1 stars. Picked by walidboulanouar, RadRebelSam
  769. 2of 31 safzanpirani/pong-jev Other TypeSafe's Jev plays Atari Pong. One typed Choice question per frame, no coordinates sent to the model. Picked by hellogumbo, heyjunpenn
  770. 2of 31 sawzhang/jev-demo Other Jev (TypeSafe System One) 学习与实测：概念文档 + 5 个可运行 demo + 可复现压测。实测 jev-1.13.0：扇出几乎免费，40 问与 1 问等延迟。. Picked by rhc98, RadRebelSam
  771. 2of 31 scienthoon/luce Eval & Align Open recipe for Jev-style decision models: a task description, an LLM teacher that writes the data, then LoRA plus a decision head on Qwen3-4B-Base returning calibrated choice, score, and… Picked by yibie, AbdelStark
  772. 2of 31 sgoedecke/system-one Other Batched single-token choice inference for open language models, compatible with TypeSafe. Picked by hellogumbo, heyjunpenn
  773. 2of 31 shaharia-lab/jev-cli Coding Agent (shaharia-lab) - Command-line tool for TypeSafe AI's Jev model. Ask yes/no, multiple-choice and rubric questions about any text and get calibrated probabilities back. Answers become exit… Picked by hellogumbo, RadRebelSam
  774. 2of 31 shantanugoel/jev-games Other Visual Jev lab for multiple games and emulator platforms. Picked by hellogumbo, heyjunpenn
  775. 2of 31 sherajdev/jev-research Routing A Jev and Herdr integration guide with a prototype for routing tasks to different Agents. Picked by logicrw, JohnDotOwl
  776. 2of 31 shibadogcap/kyotsu-ai-bench Eval & Align AI benchmark on Japan's 2026 Common Test: Jev vs luna-none vs luna-low (static dashboard). Picked by hellogumbo, heyjunpenn
  777. 2of 31 shivam2003-dev/typesafe-triage-guard Other Three composable judgment pipelines on TypeSafe's Jev: support-ticket triage, observability alert triage, and a deploy-risk gate. Picked by hellogumbo, heyjunpenn
  778. 2of 31 siliconkernel/vllm-jev-decison SDK & Runtime 给 vLLM 加「只分类」模式：有限 schema 候选打分 + 概率 Picked by yzfly, RadRebelSam
  779. 2of 31 silverstein/minutes Eval & Align Meeting notes: local-first transcription app whose live voice path runs its evaluations through Jev. Picked by yibie, v-modal
  780. 2of 31 simxnherrera/jevr SDK & Runtime Native R client for typed questions and provider-independent answers through TypeSafe or OpenRouter. Picked by cobanov, RadRebelSam
  781. 2of 31 sontakey/awesome-jev Awesome List sontakey/awesome-jev. Unofficial list of insanely useful TypeSafe AI Jev / System One projects. 1 stars. Picked by walidboulanouar, JohnDotOwl
  782. 2of 31 stephanj/parallelConstraintDecoding SDK & Runtime Java and llama.cpp experiments in parallel constrained decoding. Picked by cobanov, yzfly
  783. 2of 31 sypherin/jev-trace-classifier SDK & Runtime Application of TypeSafe Jev (noul judgment primitive) on the collusion.wiki corpus: agent vs human page authorship, head-to-head vs local Qwen3.8-Flash-Next. Picked by hellogumbo, heyjunpenn
  784. 2of 31 terryds/jevplayground Browser (site) - Browser-only playground for Jev (TypeSafe AI's decision model) via Vercel AI Gateway. Picked by hellogumbo, RadRebelSam
  785. 2of 31 themsquared/jev-benchmark Eval & Align by themsquared - Tool-call risk classification with the run-to-run variance reported; every wrong answer came with hedged confidence. Picked by valentynkit, JohnDotOwl
  786. 2of 31 thezem/jev-one SDK & Runtime thezem/jev-one. A vocabulary-driven TypeScript runtime for safe, stateful applications powered by TypeSafe AI Jev. 1 stars. Picked by walidboulanouar, RadRebelSam
  787. 2of 31 thodoh1/FinancialPredictionJev Other Using Jev to test how well it predicts financial markets(just like most llms as of september 2026, it doesnt do that good). Picked by hellogumbo, heyjunpenn
  788. 2of 31 ticofab/scala-jev-sdk SDK & Runtime ticofab/scala-jev-sdk** - Scala SDK for Jev. No effect system bundled. Picked by AbdelStark, RadRebelSam
  789. 2of 31 timpratim/macbrow Browser `BYOK`. Experimental macOS voice assistant using Jev to route commands to AppleScript tools and Chrome browser tasks. Project guide. Picked by AppitStudio, MrJev
  790. 2of 31 tirukovelamanoj/jev-plays-doom Other A System One model driving the game through structured state, no pixels. Picked by JohnDotOwl, RadRebelSam
  791. 2of 31 tonyzdev/PiJ Coding Agent A Pi-based terminal coding Agent whose main model handles reasoning, edits and tools while Jev provides advice. Picked by logicrw, JohnDotOwl
  792. 2of 31 tonyzdev/pijev Search Jev ranks the repository's files before the first call, picks skills and triages failures; your coding model writes the code. Built on Pi. Picked by hellogumbo, RadRebelSam
  793. 2of 31 tpaulshippy/shady-town Other Shady Town: social-deduction party game for the living room TV, moderated by TypeSafe Jev. Picked by hellogumbo, heyjunpenn
  794. 2of 31 trophee-bot/typesafe-oracles Eval & Align Evaluating TypeSafe's System One primitives (Choice/Score/Noul) Picked by hellogumbo, heyjunpenn
  795. 2of 31 trungdq88/jev-tetris Other (trungdq88) (site) - Jev play Tetris in real-time against other AI models. Picked by hellogumbo, RadRebelSam
  796. 2of 31 tryaksh/jev-pick-and-place-study Other A small reproducible MuJoCo pilot comparing Jev, Claude Haiku, and reactive rules for pick-and-place. Picked by hellogumbo, heyjunpenn
  797. 2of 31 tylergibbs1/sift Browser Chrome extension that re-ranks Google results with TypeSafe Jev and folds away sales pages and SEO filler. Picked by hellogumbo, heyjunpenn
  798. 2of 31 typesafe-ai/daggerverse Other Official (2):** TypeSafe Daggerverse, TypeSafe Overwatch Picked by heyjunpenn, JohnDotOwl
  799. 2of 31 typesafeainate/dspy-typesafeify Routing , Decorator that routes DSPy typed Signatures to Jev where the signature is a pure decision. Picked by OmniJev, ozers
  800. 2of 31 uezo/aiavatarkit Other An optional AIAvatarKit component uses Jev to judge turn endings from speech transcripts. Picked by logicrw, jtnkminimal
  801. 2of 31 us/jev-local Eval & Align Local reproduction: Jev-compatible `POST /v1/systemone` server answering typed `Choice`/`Score`/`Noul` questions with confidence from open weights, verified as an official-SDK drop-in with… Picked by yibie, v-modal
  802. 2of 31 ussyverse/hermes-jev-router Routing Experimental Hermes plugin: Jev-assisted model routing plans with budget and capability constraints. API access pending. Picked by hellogumbo, heyjunpenn
  803. 2of 31 vehas/thaiexam-jev-charts Eval & Align Charts: TypeSafe Jev evaluated on Thai standardized exams vs 110 other models. Picked by hellogumbo, heyjunpenn
  804. 2of 31 vercel-labs/ai-python Routing Python ecosystem: the official Vercel AI SDK for Python carries Jev through its evaluation operation and Gateway examples. Picked by yibie, v-modal
  805. 2of 31 vercel-labs/fx Coding Agent Coding agent: ships a `typesafe_permission_reviewer` builtin so the agent's permission decisions run through Jev rather than an LLM call. Picked by yibie, v-modal
  806. 2of 31 vercel/ai Eval & Align The TypeSafe provider in AI SDK lets TypeScript applications call Jev through the shared evaluate interface. Picked by logicrw, ckaraca
  807. 2of 31 virattt/ai-hedge-fund Other An educational AI hedge-fund prototype with an optional Jev adapter for structured judgments in fund decision workflows. Picked by logicrw, ckaraca
  808. 2of 31 vnmoorthy/siege Eval & Align (site) - SIEGE: 200 people vs one agent. A typed action gate (TypeSafe System One) that learns from every breach, evaluated by W&B Weave, hardened by a defender loop. Built at CoreWeave… Picked by hellogumbo, heyjunpenn
  809. 2of 31 willprout/magic-8-ball Other Magic-8-Jev - Ask a question, one choice over twenty answers picks the reply and shows the click-to-answer latency; live demo. Picked by valentynkit, jtnkminimal
  810. 2of 31 yairshy/decido Browser Probabilistic decisions for Python. Use Jev or bring your own provider; crawl with Playwright. Picked by hellogumbo, heyjunpenn
  811. 2of 31 yonatangross/orchestkit Other can optionally use Jev to classify coding sessions and set their colors when confidence meets a threshold. Picked by logicrw, ckaraca
  812. 2of 31 youkiti/tiab-review-plugin Other youkiti/tiab-review-plugin: title/abstract screening for systematic reviews across labeled medical datasets. *Unique: evidence-synthesis triage at scale (95% recall @ 16,645 records).* Picked by anandi1989, aliaihub
  813. 2of 31 zhuyansen/jev-news-cold-start Other Cross-domain check on MIND news: a zero-shot Jev headline prior is worth ~500 labelled articles, adds +0.069 ρ as features, and lifts a Thompson-sampling… `★ 0` Picked by jtnkminimal, RadRebelSam
  814. 2of 31 zmtomorrow/TypeAR Other Type-safe one-decision-per-token decoding engine for autoregressive LLMs, inspired by Jev. Picked by heyjunpenn, jtnkminimal
  815. 2of 31 zsoXi/FeedGate Browser Precision-first Chrome feed filter (v2.1.0) using TypeSafe Jev judgments: promotional posts are kept unless independently strong spam or ad evidence… `★ 0` Picked by jtnkminimal, JohnDotOwl
  816. 2of 31 zsoXi/agent-handoff-gate Other (post) - Experimental protocol for evidence-aware agent handoffs, with Jev-assisted review before results reach the lead agent. Picked by hellogumbo, heyjunpenn
  817. 1of 31 wuyoscar/jev-skill in Top 100 Coding Agent An awesome collection of Jev use cases, workflows, and agent skills. Picked by hellogumbo 127★
  818. 1of 31 wobsoriano/oxlint-plugin-jev in Top 100 Other wobsoriano/oxlint-plugin-jev** - No description provided. Picked by RadRebelSam 36★
  819. 1of 31 SAGAR-TAMANG/sarvam-jev in Top 100 Browser SAGAR-TAMANG/sarvam-jev** - Generation-free typed decisions on Indic LLMs. An open Jev-style inference engine on sarvam-1: constrained logit readout instead of autoregressive JSON. Runs… Picked by RadRebelSam 29★
  820. 1of 31 NanmiCoder/jev-arena in Top 100 Data NanmiCoder/jev-arena** - Jev 模型介绍与实测：通过 Choice / Score / Noul 将自然语言转为带类型的判断与概率，用于分类、评分和路由；支持与 DeepSeek 等模型对比评论打标、速度与结果，含 CSV/Excel 导入、原速回放与离线报告。 Picked by RadRebelSam 27★
  821. 1of 31 philippdubach/pi-jev-router in Top 100 Routing Pi extension: TypeSafe Jev classifies tasks and local policy routes OpenRouter models (Pareto profiles; shadow mode default). Project guide. Picked by AppitStudio 14★
  822. 1of 31 intikhab49/open-jev-typed-decision-engine in Top 100 Routing intikhab49/open-jev-typed-decision-engine** - Open reproduction of TypeSafe Jev: a 150M typed decision engine (noul/choice/score in one non-autoregressive pass, calibrated confidence)… Picked by RadRebelSam 10★
  823. 1of 31 kushals256/jevcache in Top 100 Search kushals256/jevcache (skip the LLM when intent matches) Picked by dog-last 3★
  824. 1of 31 Ashadeepa/typesafe-jev-model-use-cases in Top 100 Other Ashadeepa/typesafe-jev-model-use-cases** - Runnable demos of TypeSafe's System One model (Jev) Picked by RadRebelSam 1★
  825. 1of 31 Mawfyy/jev-router.nvim in Top 100 Routing Mawfyy/jev-router.nvim** - An intent router for Neovim that classifies AI commands with Jev (TypeSafe's System One model) via the OpenRouter Decisions API, then routes execution to the… Picked by RadRebelSam 1★
  826. 1of 31 caijinchun/nanojev-arena in Top 100 SDK & Runtime caijinchun/nanojev-arena** - NanoJev Snake Arena: 1v4 human-vs-AI battleship + 100-agent swarm simulator. Local demo of Jev System-One model (open-source mini replica). Picked by RadRebelSam 1★
  827. 1of 31 danielhirt/jev-lab in Top 100 Other Experiments on TypeSafe Jev (System One decision model) via OpenRouter: repeatability, perturbation, and LLM baseline comparison. Picked by JohnDotOwl 1★
  828. 1of 31 dougsong/jev-android in Top 100 Mobile Kotlin Android UI-agent SDK: TypeSafe Jev or DeepSeek selects accessibility actions; local Maven sample (not on Maven Central). Project guide. Picked by AppitStudio 1★
  829. 1of 31 jkrup/jeveryword in Top 100 Other jkrup/jeveryword** - Text extraction with Jev: field extraction, PII detection and exact quotes, built on TypeSafe's Jev. Picked by RadRebelSam 1★
  830. 1of 31 kierandotai/jev-client in Top 100 Routing kierandotai/jev-client** - Zero-dependency TypeScript client for TypeSafe Jev (System One decision model) Picked by RadRebelSam 1★
  831. 1of 31 naveenreddy61/jev-experiments in Top 100 Other naveenreddy61/jev-experiments** - experiments with system one model jev Picked by RadRebelSam 1★
  832. 1of 31 wenchenxi/jev-console in Top 100 Eval & Align wenchenxi/jev-console** - Local console + CLI for TypeSafe's Jev (System One) model: send a state and typed questions, get calibrated probabilities back. Picked by RadRebelSam 1★
  833. 1of 31 Charlyhno-eng/jev-codex-pilot in Top 100 Coding Agent Charlyhno-eng/jev-codex-pilot** - A Codex overlay incorporating JEV to make the best decisions regarding model selection and depth of reasoning. All while automating the process via an… Picked by RadRebelSam 0★
  834. 1of 31 JackZH26/Jev-Live in Top 100 SDK & Runtime JackZH26/Jev-Live** - Open-source virtual streaming studio for your Steam library: add/select games, manual or JEV-assisted play, and YouTube/Twitch streaming. Windows alpha; game support… Picked by RadRebelSam 0★
  835. 1of 31 allenporter/home-assistant-typesafe in Top 100 Routing allenporter/home-assistant-typesafe** - Home Assistant conversation integration powered by the Jev / TypeSafe AI API for fast, structured intent routing and device control Picked by RadRebelSam 0★
  836. 1of 31 ctmx/openrouter-jev-mcp in Top 100 Coding Agent A Python decision gateway and Model Context Protocol (MCP) server exposing TypeSafe's Jev model through OpenRouter's decisions endpoint to Claude Code, Codex, and Cursor agents. Picked by logicrw 0★
  837. 1of 31 goodruizhan/pi-jev-control in Top 100 Coding Agent goodruizhan/pi-jev-control** - System-One control plane for Pi Coding Agent powered by TypeSafe Jev. Picked by RadRebelSam 0★
  838. 1of 31 khaledsAlshibani/jev-ci-classifier in Top 100 Other khaledsAlshibani/jev-ci-classifier** - CI example using Jev to classify failed PR checks and return structured decisions with probabilities. Picked by RadRebelSam 0★
  839. 1of 31 mkruglikov/droidjev in Top 100 Mobile (screenshot-free, ports the jev-ultrafast pattern) Picked by dog-last 0★
  840. 1of 31 priyankark/jev-state in Top 100 Eval & Align priyankark/jev-state** - Open-source studio for Jev state machines, multi-turn conversations, evaluations, and hosted subscriptions Picked by RadRebelSam 0★
  841. 1of 31 019ec6e2/pi-jev-compact Other 019ec6e2/pi-jev-compact** - No description provided. Picked by RadRebelSam
  842. 1of 31 0xShin0221/openpoke-meets-jev Search OpenPoke fork that moves email screening, a tool-call guardrail, and search reranking onto Jev, with an A/B against the Sonnet call it replaced and an adversarial run on the injection gate. Picked by valentynkit
  843. 1of 31 0xnairb/jevpot Other AI-powered jackpot number predictor and intelligence oracle built with TypeSafe System One (Jev). `★ 0` Picked by jtnkminimal
  844. 1of 31 2389-research/typesafe-go SDK & Runtime A TypeSafe System One client that uses only the Go standard library to send Jev questions and read structured answers. Picked by logicrw
  845. 1of 31 33Audits/jev-auto Coding Agent 33Audits/jev-auto** - Per-turn model routing for Claude Code. Cheapest tier that can do the job, no API key required, and it calibrates itself from what actually happened. Picked by RadRebelSam
  846. 1of 31 404priyanshu/zsh-jev-suggest Search 404priyanshu/zsh-jev-suggest** - zsh history autosuggestions ranked by Jev (TypeSafe System One) Picked by RadRebelSam
  847. 1of 31 4esv/jev-joust Other 4esv/jev-joust** - TypeSafe Jev vs Jev in NES Joust, bring your own ROM Picked by RadRebelSam
  848. 1of 31 7starsseeker/dsh-jev-guard Other 7starsseeker/dsh-jev-guard** - DeepSeek Harness (DSH) 执行前安全阀门:bash/pwsh 真正执行前先经静态规则 + TypeSafe Jev 语义判定,破坏性操作按 允许/修正/拦截/上报人工 四态处置,含额度降级与审计日志。 Picked by RadRebelSam
  849. 1of 31 AStheTECH/mewcp-jev Coding Agent AStheTECH/mewcp-jev** - JEV MCP server by MewCP Picked by RadRebelSam
  850. 1of 31 Aben25/jev-sim Computer Use Aben25/jev-sim** - Fast mobile-simulator computer-use: sim-use + TypeSafe Jev (Cua jev-use pattern for iOS/Android sims) Picked by RadRebelSam
  851. 1of 31 Adibrill1/jev-factorio Other Adibrill1/jev-factorio** - Jev picks what, code owns how - a System One Factorio agent driven by TypeSafe's Jev on FLE Picked by RadRebelSam
  852. 1of 31 Adilmp/does-jev-confidence-mean-anything Eval & Align Adilmp/does-jev-confidence-mean-anything** - A calibration audit of TypeSafe's Jev: does a decision model's stated confidence mean what it claims? 8,000 judgments against human annotations… Picked by RadRebelSam
  853. 1of 31 AiPersonacademy/Jev-Video-Hook-Studio Eval & Align Terminal workbench & SQLite benchmark suite for 3s retention odds, LF8 & policy risk Picked by AiPersonacademy
  854. 1of 31 AlexBabescu/ActionJev Coding Agent Structured code review for GitHub and Gitea Actions, powered by TypeSafe Jev and written in Rust. Picked by JohnDotOwl
  855. 1of 31 Alexandre-Borghi/jev-ncr-demo Other Alexandre-Borghi/jev-ncr-demo** - AI defect code suggestions for Non-Conformance Reports, powered by TypeSafe AI's Jev model Picked by RadRebelSam
  856. 1of 31 AmoghCreator/doom-jev Other A ViZDoom Agent that uses Jev to choose movement, targets and firing from structured game state. Picked by logicrw
  857. 1of 31 Amrit-Nigam/jev-royal Other Games & simulations (8):** jev-plays-pokemon-red, jev-royal, beat-jev, f1, jev-atari-lab, jev-plays-pokemon, JevArena, naimono-lab Picked by heyjunpenn
  858. 1of 31 AnthusAI/Jev-Calibration Eval & Align AnthusAI/Jev-Calibration** - Does Jev's confidence mean what it says? Calibrating Jev (TypeSafe System One) with Platt scaling and isotonic regression. Picked by RadRebelSam
  859. 1of 31 AntonioCoppe/openclaw-jev-harness Other AntonioCoppe/openclaw-jev-harness** - OpenClaw plugin: jev-harness DecisionHarness as System One decide layer (policy/confidence/shadow) Picked by RadRebelSam
  860. 1of 31 Arohtea/jev-readout Other Arohtea/jev-readout** - 把一段内容交给 TypeSafe AI 的 Jev 模型，得到带概率分布的结构化判断 Picked by RadRebelSam
  861. 1of 31 Ashadeepa/typesafe-showcase Other Ashadeepa/typesafe-showcase** - Next.js UI showing off TypeSafe's System One model (Jev) Picked by RadRebelSam
  862. 1of 31 Astro-Han/jev-harness Coding Agent Astro-Han/jev-harness** - A coding agent that filters every tool result through Jev before the model sees it, with an A/B harness measuring pass@1 and cost against the unfiltered control Picked by RadRebelSam
  863. 1of 31 Atikpui007/jev-sift Coding Agent Atikpui007/jev-sift** - Keep Claude Code context clean: tool results filtered through Jev before the model sees them Picked by RadRebelSam
  864. 1of 31 AutoPasha/jevcode Coding Agent AutoPasha/jevcode** - Coding agent driven by a model that cannot write text Picked by RadRebelSam
  865. 1of 31 BUNYOD0987/jev-vs-llm Routing BUNYOD0987/jev-vs-llm** - TypeSafe AI's Jev vs GPT-5.6 Luna vs Claude Sonnet 5 on support-ticket triage (Vercel AI Gateway) Picked by RadRebelSam
  866. 1of 31 Baran3575/jev-voice-android Mobile Turkish voice-command app; one parallel Jev call → dial/SMS/alarms, confidence-gated at 0.60 Picked by dog-last
  867. 1of 31 Barba-Tech-CO/jev-claude-skill Coding Agent Barba-Tech-CO/jev-claude-skill** - Claude Code skill for TypeSafe's Jev decision model Picked by RadRebelSam
  868. 1of 31 Barry2llen/agent-jev-approval Other Barry2llen/agent-jev-approval** - No description provided. Picked by RadRebelSam
  869. 1of 31 Bechi29/jev-dify-tool-plugin Other Bechi29/jev-dify-tool-plugin** - Dify Tool plugin for TypeSafe System One (Jev) typed decisions. Picked by RadRebelSam
  870. 1of 31 Biztactix/n8n-nodes-typesafe Other n8n community node for TypeSafe System One noul/choice/score questions over workflow text or JSON. Project guide. Picked by AppitStudio
  871. 1of 31 Brainwires/jev-mcp Coding Agent Jev decision layer for agents: MCP server, embeddable DecisionModel library, and an escalate-only Claude Code plugin (TypeSafe AI's Jev). Picked by rhc98
  872. 1of 31 Bravim-Ketan-Purohit/jev-city Other Bravim-Ketan-Purohit/jev-city** - A traffic city where every car is driven by TypeSafe's Jev model, benchmarked against a rule-based driver. Picked by RadRebelSam
  873. 1of 31 BunsDev/typesafe-ui Other Shadcn-style reusable components and blocks for using TypeSafe AI. Picked by heyjunpenn
  874. 1of 31 ClemannD/jev-playground Routing ClemannD/jev-playground** - Interactive playground for learning how TypeSafe's Jev model works (via Vercel AI Gateway) Picked by RadRebelSam
  875. 1of 31 Code-Forge-AU/jev-llm Other Code-Forge-AU/jev-llm** - No description provided. Picked by RadRebelSam
  876. 1of 31 CodeCampusCo/jev-mcp Coding Agent CodeCampusCo/jev-mcp** - MCP server exposing one tool: ask Jev a typed question and get a short answer back. Picked by RadRebelSam
  877. 1of 31 DECRUX9812/openjev Other Benchmarks & research (4):** openjev, paper-package, jev-vs-luna, typed-decisions Picked by heyjunpenn
  878. 1of 31 DECRUX9812/openjev-lm Routing Cheapest entry point: LoRA on CPU in 89 min at $0, 92.9% answer agreement with the API Picked by dog-last
  879. 1of 31 DM010727/jev-superpowers-review Coding Agent DM010727/jev-superpowers-review** - Cross-agent parallel code review skill powered by Superpowers workflows and Shengsuanyun Jev Decisions. Picked by RadRebelSam
  880. 1of 31 Dakai/omp-jev-web Browser Dakai/omp-jev-web** - OMP browser tool that drives any page from one goal using TypeSafe Jev (System One) decisions instead of the main model. Picked by RadRebelSam
  881. 1of 31 Danu28/pi-jev-harness Routing pi-model tool-based calibrate + plan + git, zero deps, no fallback Picked by RadRebelSam
  882. 1of 31 Deepender25/chess-with-jev- Browser Deepender25/chess-with-jev-** - An empirical experiment fusing TypeSafe AI's non-autoregressive Jev model (System 1) with a high-performance 0x88 alpha-beta search engine (System 2)… Picked by RadRebelSam
  883. 1of 31 Dharundp6/jev-sortwell Coding Agent Dharundp6/jev-sortwell** - An inbox with judgment. MCP server that files every note, link and meeting line by itself: TypeSafe's Jev decides the kind, the project, the urgency and the… Picked by RadRebelSam
  884. 1of 31 Dillettant/jev-test Other Dillettant/jev-test** - Playground for TypeSafe's Jev System One model (Next.js) Picked by RadRebelSam
  885. 1of 31 DowLucas/browser-jev Browser DowLucas/browser-jev** - Adversarial browser testing: personas explore your web app while Jev judges every page state Picked by RadRebelSam
  886. 1of 31 Dujaydis/JevSysUno Other Applications (7):** jev.nvim, github-star-organizer-jev, jev, JevSysUno, jev-trader, newsscore, trading-bot-jev Picked by heyjunpenn
  887. 1of 31 Eliovp-BV/Jev-Radar SDK & Runtime `BYOK`. Local research workspace where Jev steers investigation over public sources with inspectable decisions and optional text-model drafting. Project guide. Picked by AppitStudio
  888. 1of 31 EmilLindfors/jev-horingssvar-eval Eval & Align Norwegian hearing documents: equal accuracy to DeepSeek V4.1 Flash at **$0.22 vs $3.08 / 1k docs**, 0.32 s vs 26 s median Picked by dog-last
  889. 1of 31 Eniip/jev-game-tools Other Eniip/jev-game-tools** - No description provided. Picked by RadRebelSam
  890. 1of 31 Eric-Zhou-0302/jev-A-share-trader Other Eric-Zhou-0302/jev-A-share-trader** - A Jev-powered technical analysis workspace for China A-shares, supporting AKShare/Tushare, market scans, and Buy/Hold/Sell assessments with time… Picked by RadRebelSam
  891. 1of 31 EthanThatOneKid/zocomputer-jev Coding Agent EthanThatOneKid/zocomputer-jev** - A Zo skill for situational script writing and execution using Vercel AI Gateway and TypeSafe AI Jev. Picked by RadRebelSam
  892. 1of 31 EtienneLescot/jev-router Routing EtienneLescot/jev-router** - Typed judgments in, control flow out: two Jev calls route a support ticket to an agent, then pick its model tier and reasoning depth. Picked by RadRebelSam
  893. 1of 31 FBddcz/agentic-jev Other 推荐智能体实验室。搜索 × 推荐 × 广告，Jev / MiniCPM / GPT / Claude 多模型决策与生成式组合对照。 Picked by RadRebelSam
  894. 1of 31 Fatpandac/pi-fast-jev-compaction Coding Agent Fatpandac/pi-fast-jev-compaction** - pi extension that replaces the default compaction with fast-jev-compaction Picked by RadRebelSam
  895. 1of 31 FazalAAli/jev-robotics-demo SDK & Runtime A MuJoCo arm demo where local code proposes candidate moves and Jev chooses the target, grasp or release, and completion. Picked by logicrw
  896. 1of 31 Fox-Islam/typesafe-sdk-php SDK & Runtime Community PHP 8.3 client for TypeSafe's System One API with typed Noul, Choice, and Score questions, a one-call switch between TypeSafe and OpenRouter's decisions endpoint, retries and… Picked by AbdelStark
  897. 1of 31 FrancoisChastel/jev-code Coding Agent FrancoisChastel/jev-code** - Jev, TypeSafe's System One classifier, as a tool inside Claude Code, Codex, Pi, and OpenCode: typed classify, check, score, rank, and ask, plus one-command… Picked by RadRebelSam
  898. 1of 31 Frank-ZY-Dou/awesome-jev Home & IoT (Frank-ZY-Dou) - Public examples of Jev used for robot control, 3D modeling and adjacent control tasks, with sources and archived media. Picked by hellogumbo
  899. 1of 31 GitHub30/OpenJev Eval & Align GitHub30/OpenJev** - Open-weight System One model (Jev-compatible): calibrated noul / choice / score decisions in one forward pass, no text generation. Works with TypeSafe's typesafe-sdk… Picked by RadRebelSam
  900. 1of 31 Hari31416/typesafe-demo-finance-tracking-app Other Hari31416/typesafe-demo-finance-tracking-app** - A demo of personal finance tracker powered by TypeSafe AI's Jev model Picked by RadRebelSam
  901. 1of 31 HermeticOrmus/jev-claim-verify Other HermeticOrmus/jev-claim-verify** - Jev claim verify Picked by RadRebelSam
  902. 1of 31 HermeticOrmus/jev-confidence-routing Routing HermeticOrmus/jev-confidence-routing** - Jev confidence routing Picked by RadRebelSam
  903. 1of 31 HermeticOrmus/jev-context-screen Computer Use HermeticOrmus/jev-context-screen** - Jev context screen Picked by RadRebelSam
  904. 1of 31 HermeticOrmus/jev-grok-bot Other HermeticOrmus/jev-grok-bot** - Jev + Grok Bot wiring (extends ormus-jev hub) Picked by RadRebelSam
  905. 1of 31 HermeticOrmus/jev-mcp-setup Coding Agent HermeticOrmus/jev-mcp-setup** - Jev MCP setup Picked by RadRebelSam
  906. 1of 31 HisuiKoh/jev-vtuber-ime-core Other HisuiKoh/jev-vtuber-ime-core** - 読み→VTuber表記を Web検索の根拠 + Jev で解決。辞書データなし。 Picked by RadRebelSam
  907. 1of 31 Hiwoniu/Jev-Case Awesome List Other lists (5):** awesome-jev-by-typesafe, awesome-jev, awesome-jev-typesafe, jevusecases, Jev-Case Picked by heyjunpenn
  908. 1of 31 Hol1kgmg/jev-trpg Other Hol1kgmg/jev-trpg** - jev aiを使ったショートTRPG Picked by RadRebelSam
  909. 1of 31 HorusJiang/dsh-jev-tools Coding Agent pruning oversized tool output to the segments relevant to the request, screening fetched pages for instructions aimed at the model, and picking which skill fits the next step Picked by fatwang2
  910. 1of 31 Hoyant-Su/JevSpawn Other Let a small model decide when to spawn another agent. `★ 1` Picked by jtnkminimal
  911. 1of 31 InfamousCube/JevPilot Other droidjev (screenshot-free, ports the jev-ultrafast pattern) Picked by dog-last
  912. 1of 31 IslamBaraka90/jev-typesafe-real-financial-use-cases Other IslamBaraka90/jev-typesafe-real-financial-use-cases** - Fifty real-world financial use cases for TypeSafe's Jev model: typed, structured LLM answers over ledgers, fraud, portfolios, trades… Picked by RadRebelSam
  913. 1of 31 JLegends/opencode-jev-compaction Coding Agent JLegends/opencode-jev-compaction** - opencode plugins that replace lossy compaction with Jev decisions: score every tool call and result, drop or truncate the stale ones, keep everything… Picked by RadRebelSam
  914. 1of 31 JabbaKadabra/JevDotNet SDK & Runtime JabbaKadabra/JevDotNet** - DotNet Wrapper for the Jev Model Picked by RadRebelSam
  915. 1of 31 JacquesGariepy/Essentiel-Jev Coding Agent JacquesGariepy/Essentiel-Jev** - AI-assisted email, calendar, tasks and documents: TypeSafe Jev gives typed, probability-backed judgments; LLMs draft (OpenAI-compatible APIs, local models… Picked by RadRebelSam
  916. 1of 31 JaelChen/obsidian-jev-archiver Other JaelChen/obsidian-jev-archiver** - Sort Obsidian inbox notes into folders with TypeSafe Jev; LLM steps in only when Jev is unsure Picked by RadRebelSam
  917. 1of 31 JanDalhuysen/jev-clash-royale-test Other A Clash Royale-style sandbox whose Jev bot decides play-or-hold, card, lane, and depth in one System One call. Picked by logicrw
  918. 1of 31 JayDoubleu/cc-mod-jev Coding Agent JayDoubleu/cc-mod-jev** - Claude Code mod: Jev-scored context pruning through OpenRouter. Verbatim compaction, an optional gate on oversized tool outputs, tests and evals. Picked by RadRebelSam
  919. 1of 31 JularDepick/Jev-Examiner Other JularDepick/Jev-Examiner** - An AI content moderation workflow powered by the TypeSafe/Jev model. Picked by RadRebelSam
  920. 1of 31 JustinRoderick/jev-test Other Testing typesafe.ai new model Jev. Picked by JohnDotOwl
  921. 1of 31 KamilPostrozny/pi-fast-jev-compaction Coding Agent (KamilPostrozny) - Fast JEV compaction extension for pi. Picked by hellogumbo
  922. 1of 31 KouyamaCreate/jevtetris Other KouyamaCreate/jevtetris** - No description provided. Picked by RadRebelSam
  923. 1of 31 LYchoon/paper-radar-jev Search An automated research paper radar that fetches the latest papers from arXiv, evaluates their relevance to a configurable research profile using TypeSafe AI, and ranks them by relevance… Picked by logicrw
  924. 1of 31 LakshyaChaudhry/jev-label-desk Other LakshyaChaudhry/jev-label-desk** - weekend project using Jev to automate trace / data labeling for a provided labeling taxonomy. Picked by RadRebelSam
  925. 1of 31 LamplighterPaul/jev-piano Other LamplighterPaul/jev-piano** - Jev cannot generate a single note. Given a piano and the right questions, it improvises anyway. Picked by RadRebelSam
  926. 1of 31 MayankBansal12/game-theory-with-jev Other MayankBansal12/game-theory-with-jev** - jev plays into the prisoner’s dilemma: 40 matches against 8 opponents Picked by RadRebelSam
  927. 1of 31 MayankBansal12/jev-plays-pinball Other MayankBansal12/jev-plays-pinball** - watch jev play real-time pinball Picked by RadRebelSam
  928. 1of 31 Mrlyk/jev-browser Browser Mrlyk/jev-browser** - Browser automation CLI for AI agents, powered by the Jev model's millisecond decisions and near-zero inference costs Picked by RadRebelSam
  929. 1of 31 NeetigyaShah/jev-gate-extension Browser NeetigyaShah/jev-gate-extension** - Jev-gated browser agent in your side panel. Jev decides, code executes, you approve. Picked by RadRebelSam
  930. 1of 31 NemanjaManic/ci-gatekeeper-bot-jev Routing NemanjaManic/ci-gatekeeper-bot-jev** - GitHub Action that uses Jev (TypeSafe AI via Vercel AI Gateway) to cheaply triage pull requests before expensive LLM/human review Picked by RadRebelSam
  931. 1of 31 NicolasMontone/jev-evals Eval & Align Rubric-based eval harness cheap enough to run on every PR, powered by typesafe-ai/jev. Picked by JohnDotOwl
  932. 1of 31 Nixz0824/rag-jev Search 国服《英雄联盟》版本更新公告的本地 RAG 问答：数字只来自公告，Jev（TypeSafe System One）负责候选重排与回答自检. Picked by rhc98
  933. 1of 31 Nolane-x/JEV-language Other (site) - Give your Jev language. Picked by hellogumbo
  934. 1of 31 Obrais-cloud/typesafe-mcp Coding Agent MCP server exposing TypeSafe (Jev/System One) to the fleet: judge, rerank, systemone. Picked by JohnDotOwl
  935. 1of 31 Obrais-cloud/typesafe-translate SDK & Runtime Escribe lenguaje natural y un LLM local lo compila a variables de TypeSafe (state + questions) y las ejecuta (Jev / System One). Picked by JohnDotOwl
  936. 1of 31 Pinutss/jev-model-router Routing Pinutss/jev-model-router** - Route among multiple LLMs and multi-model provider keys without leaking secrets. Picked by RadRebelSam
  937. 1of 31 Pinutss/jev-plugins Coding Agent Agent tooling (13):** tenet, jev-belay, jev-commit, pi-fast-jev-compaction, jev-flash-router, pi-jev, pi-jev-helm, stepwarden, AskJev-MCP, jev-compaction, jev-plugins, jevkeep, pi-jev-router Picked by heyjunpenn
  938. 1of 31 RadixILS-Dev/typesafe-sdk-go SDK & Runtime RadixILS-Dev/typesafe-sdk-go** - A typesafe.ai client written in golang Picked by RadRebelSam
  939. 1of 31 RahulBalakavi/claude-code-jev Coding Agent RahulBalakavi/claude-code-jev** - Experimental Jev permission gate for Claude Code via OpenRouter, with reproducible latency and cost benchmarks Picked by RadRebelSam
  940. 1of 31 Reindeer-AI/pi-jev-guard Other Reindeer-AI/pi-jev-guard** - Check Pi code edits against repository Markdown rules with TypeSafe Jev Picked by RadRebelSam
  941. 1of 31 RudyJunyu/Jev-MCP Coding Agent RudyJunyu/Jev-MCP** - Jev MCP Hub is a small Go gateway that exposes TypeSafe's Jev model through the Model Context Protocol. Picked by RadRebelSam
  942. 1of 31 Shashank-H/jev-trader Other Shashank-H/jev-trader** - An automated trader using SystemOne model - TypesafeAI Jev Picked by RadRebelSam
  943. 1of 31 Shashank-H/pi-jev-model-router Routing Shashank-H/pi-jev-model-router** - Model router for pi with Jev Picked by RadRebelSam
  944. 1of 31 Shifty-Eye-Games/foreman-jev Coding Agent An experimental Jev supervisor for Codex workers with programmer-selected acceptance commands. Picked by logicrw
  945. 1of 31 SiliconLabAI/OpenJev Other SiliconLabAI/OpenJev** - OpenSource Jev Picked by RadRebelSam
  946. 1of 31 SomeshSampat2/jev-android-super Mobile On-device Kotlin/Compose agent; "open YouTube and subscribe to MrBeast" in 17 steps / ~32 s, ships an APK Picked by dog-last
  947. 1of 31 SongMarco/jev-jstris SDK & Runtime Jev chooses Tetris placements; a local controller plays Jstris through keyboard input. Picked by rhc98
  948. 1of 31 Spykoninho/trading-bot-jev Other Applications (7):** jev.nvim, github-star-organizer-jev, jev, JevSysUno, jev-trader, newsscore, trading-bot-jev Picked by heyjunpenn
  949. 1of 31 SqaaSSL/openclaw-jev-compaction Coding Agent Verbatim context compaction for OpenClaw: a context engine powered by TypeSafe's Jev. Drops stale tool calls and results, never summarizes. Picked by rhc98
  950. 1of 31 SuchintK/jev-call-screener Other `BYOK`. Self-hosted call screening: TypeSafe Jev classifies caller transcripts; Go policy forwards or rejects (Twilio adapter; fail-open defaults). Project guide. Picked by AppitStudio
  951. 1of 31 T-moz/typesafe-ai-dart SDK & Runtime T-moz/typesafe-ai-dart. A pure Dart sdk wrapper around Typesafe AI API and JEV. 0 stars. Picked by walidboulanouar
  952. 1of 31 Thanh-Mathieu95/jev-model-tokengate Routing tokengate (jev-model-tokengate) - Streaming OpenAI-compatible proxy that buffers tokens and runs TypeSafe Jev safety criteria before release, aiming for zero UI leakage vs post-hoc… Picked by AppitStudio
  953. 1of 31 TheBous/jev-flash-review Coding Agent An MCP review engine that evaluates Agent-supplied diffs against explicit rules. Picked by logicrw
  954. 1of 31 TheOnlyArtz/JevIsraeliElections Search יועצת בחירת מפלגה. Hebrew/RTL React app ranking the 14 Knesset-26 lists against your ideology. `★ 1` Picked by jtnkminimal
  955. 1of 31 TheWebDevel/jev-fanout Other TheWebDevel/jev-fanout** - Does asking Jev more questions in one call change its answers? 250 calls measuring TypeSafe's speculative fan-out pattern and whether Jev is deterministic. Picked by RadRebelSam
  956. 1of 31 TickerDev/jevfanity-api SDK & Runtime TickerDev/jevfanity-api** - API for jevfanity, a profanity detector using Jev by TypeSafe AI Picked by RadRebelSam
  957. 1of 31 Trecto34/openjev-fighting-ring Other puts Diffusion/RLCD/Block-Causal/NLI approaches in one arena Picked by dog-last
  958. 1of 31 TypeSafeAI/typesafe-ui Other (site) - Shadcn-style reusable components and blocks for using TypeSafe AI. Picked by hellogumbo
  959. 1of 31 TyrellD1/typesafe-ai_smoke-test Data Smoke test: route prompts to a work or life database with TypeSafe AI (Jev), 30-case eval. Picked by JohnDotOwl
  960. 1of 31 Umbylicus/umby-jev-stack Coding Agent Umbylicus/umby-jev-stack** - Portable agent skill: TypeSafe Jev as a cheap code-review classifier (HTTP + optional jev-review MCP) Picked by RadRebelSam
  961. 1of 31 WallerChen/jev-measured SDK & Runtime WallerChen/jev-measured** - Measured cost, latency and raw output from the live Jev API (TypeSafe AI System One model) across 8 use cases Picked by RadRebelSam
  962. 1of 31 Wany-i/jev-decision-layer Other Wany-i/jev-decision-layer** - 把决策模型（typesafe/jev-1.13，经 OpenRouter 的 decisions 端点调用）封装成业务决策工具：注册表驱动，带置信度门控与硬约束。非官方项目。 Picked by RadRebelSam
  963. 1of 31 Waxmell114514/jev-trade Other A simulated crypto trading loop that sends BTC and ETH market features to Jev and models execution costs and latency. Picked by logicrw
  964. 1of 31 X0EF/jev_projects Awesome List (site) - List of projects that use typesafe's jev. Picked by hellogumbo
  965. 1of 31 XieChengYuan/jev-observatory Coding Agent Jev 活动看板：自动接入 MCP，实时查看真实输入、判断结果与用量。Local-first, passive MCP observability. Picked by rhc98
  966. 1of 31 Xopher00/jevdevice Other droidjev (screenshot-free, ports the jev-ultrafast pattern) Picked by dog-last
  967. 1of 31 YehuiTang0316/jev-nlgrep Search nlgrep - Developer tooling: uses Jev `Noul` judgments to find code, docs, logs, and text satisfying natural-language conditions, with a configurable probability threshold and ranked file… Picked by yibie
  968. 1of 31 ZHUBoer/ego-jev Browser ZHUBoer/ego-jev** - Complete browser tasks with Ego Lite and actively call Jev for semantic target selection, filtering, ranking, classification and text evidence judgments. Picked by RadRebelSam
  969. 1of 31 ZHYsfl/learn-jev Other ZHYsfl/learn-jev** - a repo that helps you learn jev model. Picked by RadRebelSam
  970. 1of 31 Zogrus/jev-technical-term Other Zogrus/jev-technical-term** - YouTubeの解説動画やZoomのセミナーを聞きながら、出てきた技術用語のひとこと解説をリアルタイム表示するローカルツール(判定AIは TypeSafe AI の Jev) Picked by RadRebelSam
  971. 1of 31 aaazzam/jev Other aaazzam/jev** - No description provided. Picked by RadRebelSam
  972. 1of 31 aamanlamba/jev-explore Other aamanlamba/jev-explore** - An example repository for exploring Jev - the System One model Picked by RadRebelSam
  973. 1of 31 aarora79/jev-samples Other aarora79/jev-samples** - Runnable samples for Jev, TypeSafe AI's System One model. Send state and questions carrying their own answer options, then branch on the typed value that comes back. Picked by RadRebelSam
  974. 1of 31 abeatrix/cline-plugin-jev-browser Browser A Cline plugin using an isolated Playwright browser and Jev decisions through Vercel AI Gateway. Picked by logicrw
  975. 1of 31 acharyaanusha/magic-jev Other acharyaanusha/magic-jev** - A Magic Jev (8) Ball for pull requests. Picked by RadRebelSam
  976. 1of 31 adammichaelwood/jev-music-theory-1 Other Explores Jev on harmony exercises and music-theory questions, alongside a piano demo driven by chord choices. Picked by logicrw
  977. 1of 31 adarc8/how-sure-is-jev Other adarc8/how-sure-is-jev** - How sure is Jev? Turn TypeSafe Jev probability outputs into one honest number, with graphs. Picked by RadRebelSam
  978. 1of 31 adhamelhayek-lab/jev-connector Other Frameworks & integrations (4):** jevql, ground-zero, hiep-paseo-plugin, jev-connector Picked by heyjunpenn
  979. 1of 31 adilmoujahid/jev-banking77-demo Other adilmoujahid/jev-banking77-demo** - A single-page Next.js app that classifies PolyAI BANKING77 customer support queries with Jev, TypeSafe AI's System One model, and streams the results… Picked by RadRebelSam
  980. 1of 31 aegsrl7/jevmap Coding Agent aegsrl7/jevmap** - Map a codebase into units and let Jev (TypeSafe AI) hand an AI coding agent the ten files that matter for a task Picked by RadRebelSam
  981. 1of 31 aesaganda/jev Other aesaganda/jev** - No description provided. Picked by RadRebelSam
  982. 1of 31 agarwalpranav0711/jev-ai-testing Other agarwalpranav0711/jev-ai-testing** - Real-time message tone analyzer and autonomous maze navigation game powered by TypeSafe AI's Jev System One model & Cloudflare Workers. Picked by RadRebelSam
  983. 1of 31 ajayk/jev-go-sdk SDK & Runtime ajayk/jev-go-sdk** - Dependency-free Go client for TypeSafe AI's System One API and the Jev model Picked by RadRebelSam
  984. 1of 31 ajr-khll/fuck-around-w-jev Other ajr-khll/fuck-around-w-jev** - No description provided. Picked by RadRebelSam
  985. 1of 31 akhilsbehl/pie-jev SDK & Runtime akhilsbehl/pie-jev** - Standalone JEV client library and Pi extension exposing askJev and ask_jev Picked by RadRebelSam
  986. 1of 31 aldouus/jevium Other droidjev (screenshot-free, ports the jev-ultrafast pattern) Picked by dog-last
  987. 1of 31 alex-sun-kuo/jev-consumer-research Other Consumer research explorations using TypeSafe's Jev. Picked by JohnDotOwl
  988. 1of 31 alexj11324/open-jev-approvals SDK & Runtime every intercepted tool call is reviewed by TypeSafe JEV and composed through a versioned local policy, with scoped authorization and a tamper-audited SQLite trail. Picked by RadRebelSam
  989. 1of 31 alsoleg89/jev-bouncer Coding Agent alsoleg89/jev-bouncer** - Claude Code plugin: a 3-cent bouncer for your agent's shell. Jev typed probabilities auto-allow routine commands, deny destructive ones, and flag prompt injection… Picked by RadRebelSam
  990. 1of 31 alviso/jev-precheck Coding Agent alviso/jev-precheck** - A second signature on every write an AI agent makes into a system of record. MCP proxy: fetch the records, derive in code, Jev judges. 98.6% recall, 0 false holds on… Picked by RadRebelSam
  991. 1of 31 alxcrt/is-odd-jev Other alxcrt/is-odd-jev** - No description provided. Picked by RadRebelSam
  992. 1of 31 amberwhitehead/jevscript Other An early language experiment whose current implementation is a Jev request-batching spike. Picked by logicrw
  993. 1of 31 amithkk/jev-experiments Other Experiments with Typesafe's Jev. Picked by JohnDotOwl
  994. 1of 31 amycardoso/jev-palette Search Command-palette demo where a single Choice question over a 77-command catalog turns the returned probability distribution into the per-keystroke ranking for Portuguese or English input… Picked by cobanov
  995. 1of 31 andreaserradev-gbj/jev-access-day Eval & Align andreaserradev-gbj/jev-access-day** - A learning scaffold for TypeSafe AI's System One models: eval harness plus a measured, plain-language comparison of the Jev decision model vs an LLM… Picked by RadRebelSam
  996. 1of 31 andrelandgraf/typesafe-on-neon Routing Cloud: typesafe-on-neon - Neon Function proxy for the Neon AI Gateway. Picked by kraayenjon
  997. 1of 31 andrewsilber/JevsBistro Other Deterministic 3D restaurant sim that replays the same dinner service to compare rule-based, camera-assisted, and Jev-planned waiters, logging each decision's state, options, confidence, and… Picked by AnotiaWang
  998. 1of 31 andwaller/jev-movie-rerank-demo Other andwaller/jev-movie-rerank-demo** - No description provided. Picked by RadRebelSam
  999. 1of 31 andyhorn/jev Other andyhorn/jev** - No description provided. Picked by RadRebelSam
  1000. 1of 31 angelgalvisc/snake-arena-jev-vs-llms Other angelgalvisc/snake-arena-jev-vs-llms** - How many decisions can a model make in a minute, and what do they cost? Jev, a System One decision model, raced against six LLMs on the same Snake… Picked by RadRebelSam
  1001. 1of 31 angribot/pi-jev Other angribot/pi-jev** - Single-file pi extension for batched TypeSafe Jev judgments Picked by RadRebelSam
  1002. 1of 31 ansidium/jev-codex-bridge Computer Use ansidium/jev-codex-bridge** - Model and reasoning routing for Codex Desktop and CLI, with a Windows service and validated updates Picked by RadRebelSam
  1003. 1of 31 aoi-yoneda/haikyuBattleJev Other aoi-yoneda/haikyuBattleJev** - Jev (TypeSafe AI) が打者を判断する配球バトル野球シミュレーション Picked by RadRebelSam
  1004. 1of 31 aoprisan/jev-ts-repl SDK & Runtime jev-repl - Terminal REPL for shaping System One requests before writing code. Simulates answers when no API key is set. Picked by MrJev
  1005. 1of 31 apidance/JEVX Other apidance/JEVX** - 基于 JEV 决策器的 Twitter/X 实时垃圾推文识别与净化扩展程序 Picked by RadRebelSam
  1006. 1of 31 ashafizullah/jev-linkedin Browser ashafizullah/jev-linkedin** - Chrome extension that scores how well a LinkedIn job matches your CV Picked by RadRebelSam
  1007. 1of 31 avshalomd/longjev Other avshalomd/longjev** - Long inputs for TypeSafe AI's Jev decision model. An experiment. Picked by RadRebelSam
  1008. 1of 31 ayushkushwaha609/Jev-resume-screener Other ayushkushwaha609/Jev-resume-screener** - A resume screener built using Typesafe's new System One Model - Jev Picked by RadRebelSam
  1009. 1of 31 az9713/jev-email-triage Routing az9713/jev-email-triage** - Email triage with Jev (TypeSafe) over the Vercel AI Gateway Picked by RadRebelSam
  1010. 1of 31 bahramzada/jev-taxi-dispatch Other Real-vaxt taksi dispetçerlik simulyasiyası Picked by JohnDotOwl
  1011. 1of 31 baibizhe/jev-decision-benchmarks Eval & Align Independent evaluation of Jev on MetaTool, When2Call, and BFCL V4 agent decision tasks, focusing on tool selection, abstention, and tool-use decisions. Includes comparison tables against… Picked by cobanov
  1012. 1of 31 bigdra50/a-tour-of-jev Browser bigdra50/a-tour-of-jev** - A hands-on, A Tour of Go-style tutorial for TypeSafe AI's Jev, in Japanese. Runs locally in your browser. Picked by RadRebelSam
  1013. 1of 31 bitomule/jevi Other Ask typed questions about a text and branch on the answer. A shell front end for TypeSafe's Jev. Picked by rhc98
  1014. 1of 31 blackopsrepl/jev-team-calendar Other Resume-discovered project teams, scheduled by SolverForge. `★ 0` Picked by jtnkminimal
  1015. 1of 31 blazskufca/typesafe-sdk-go SDK & Runtime blazskufca/typesafe-sdk-go** - Community SDK for Typesafe.ai in Go Picked by RadRebelSam
  1016. 1of 31 blck-snwmn/playground-jev Other blck-snwmn/playground-jev** - Small apps for experimenting with Jev. Picked by RadRebelSam
  1017. 1of 31 bojansandhaus/jev-home-assistant-sentinel Home & IoT bojansandhaus/jev-home-assistant-sentinel** - A safety boundary for AI-assisted Home Assistant decisions, with explicit policy checks and deterministic state verification. Picked by RadRebelSam
  1018. 1of 31 bravesfan133/minuspod-jev-proxy Routing bravesfan133/minuspod-jev-proxy** - OpenAI-compatible proxy: MinusPod ad detection via Jev (TypeSafe decision model) Picked by RadRebelSam
  1019. 1of 31 capitaharlock/jev-clone Eval & Align capitaharlock/jev-clone** - Open-source Jev clone: a local System One decision model for fast, calibrated, typed decisions with dynamic options, shared-state inference and zero… Picked by RadRebelSam
  1020. 1of 31 carson-sweet/jev-plays-brogue Eval & Align carson-sweet/jev-plays-brogue** - TypeSafe's Jev model plays the roguelike Brogue live -- a hand-built expert system for System-2 reasoning, outcome-calibrated self-learning, and a web UI… Picked by RadRebelSam
  1021. 1of 31 cartermccann/typesafe-computer-use-hyprland Computer Use Hyprland/NixOS fork of typesafe-computer-use Picked by JohnDotOwl
  1022. 1of 31 catorch/jev-domain-auctions Other catorch/jev-domain-auctions** - Find underpriced GoDaddy expiry domains with deterministic market signals and TypeSafe JEV judgments. Picked by RadRebelSam
  1023. 1of 31 cbruyndoncx/AskJev-MCP Coding Agent Agent tooling (13):** tenet, jev-belay, jev-commit, pi-fast-jev-compaction, jev-flash-router, pi-jev, pi-jev-helm, stepwarden, AskJev-MCP, jev-compaction, jev-plugins, jevkeep, pi-jev-router Picked by heyjunpenn
  1024. 1of 31 cephalization/jev-oxlint Other cephalization/jev-oxlint** - Digest your skills into oxlint rules powered by jev Picked by RadRebelSam
  1025. 1of 31 chahero/tetris-jev Other jevball (22 players = 22 calls) Picked by dog-last
  1026. 1of 31 chapel/hermes-jev-skills Coding Agent Hermes plugin adding semantic skill search and turn-start suggestions. `★ 0` Picked by jtnkminimal
  1027. 1of 31 charleeagni/JevPiano Other charleeagni/JevPiano** - @typesafeai 's Jev controls the 2 hands and each finger to play the piano in real-time. Jev only "sees" what we see and plays this from the "note waterfall". It… Picked by RadRebelSam
  1028. 1of 31 chenmingtang830/jevarena Other (chenmingtang830) (site) - Open-source BYOK arena for Jev and other AI judges. Find failures, compare quality, cost, and latency. Picked by hellogumbo
  1029. 1of 31 chensirui2008/fast-jev-compaction Coding Agent Claude Code plugin that replaces the compaction summary with Jev decisions: every tool call and result is scored in one fast request, stale ones are… `★ 1` Picked by jtnkminimal
  1030. 1of 31 chenyangcun/NanoJev Other A minimal nanoGPT-style replica of Jev: parallel decisions, dynamic candidates, and an end-to-end training pipeline. Picked by rupeshpoojary9
  1031. 1of 31 christian-taillon/opencode-jev-compactor Coding Agent christian-taillon/opencode-jev-compactor** - Jev powered OpenCode compaction Picked by RadRebelSam
  1032. 1of 31 chy4pro/jev-dev-kit Other chy4pro/jev-dev-kit** - Framework for agents on TypeSafe Jev: turns candidates into valid Jev questions and answers into validated choices; loop, cross-checks, fallbacks and traces built… Picked by RadRebelSam
  1033. 1of 31 clduab11/jev-test Search clduab11/jev-test** - Pre-registered benchmark: can a 2B local model (Gemma 4 E2B) answer web questions without making things up when a decision model (TypeSafe Jev) makes every call?… Picked by RadRebelSam
  1034. 1of 31 codaaiteam/jev-mcp Coding Agent give any agent typed, calibrated decisions: classify, score, check, gate risky tool calls. Try free: jevtypesafeai.com Picked by RadRebelSam
  1035. 1of 31 codaaiteam/jev-typesafe-ai Other codaaiteam/jev-typesafe-ai** - Unofficial developer notes & examples for Jev, TypeSafe AI's System One model. Try it free: jevtypesafeai.com Picked by RadRebelSam
  1036. 1of 31 codebam/jev-guardrails Coding Agent codebam/jev-guardrails** - Jev-backed guardrails for agent tool calls: library, native OpenCode/Hermes/DeepSeek Harness hooks, and a hosted eval-credit service. Picked by RadRebelSam
  1037. 1of 31 codegirl-007/typesafe-lua SDK & Runtime codegirl-007/typesafe-lua** - A port of the Typesafe Jev SDK from typescript to Lua Picked by RadRebelSam
  1038. 1of 31 connectedGraph/claude-jev-warden Coding Agent connectedGraph/claude-jev-warden** - Real-time quality gate and Art Director Warden for Claude Code powered by TypeSafe Jev 1.13 non-autoregressive decision model Picked by RadRebelSam
  1039. 1of 31 ctaxnagomi/instruct-jev Other (site) - INSTRUCT_JEV - TypeSafe AI Jev / System One instruction corpus (choice/noul/score), compiled by DeckerGUI. 119 rows. Mirrored on HuggingFace. Picked by hellogumbo
  1040. 1of 31 cvsgireesh/jev-usher Coding Agent cvsgireesh/jev-usher** - The doorman for Claude’s context window. JEV-powered model routing and recoverable context filtering for Claude Code. Picked by RadRebelSam
  1041. 1of 31 da-vinci-noob/pi-jev-model-router Routing da-vinci-noob/pi-jev-model-router** - Route pi prompts to task-appropriate model tiers with TypeSafe Jev typed judgments. Budget-aware, with automatic fallback. Picked by RadRebelSam
  1042. 1of 31 daftAI2026/awesome-jev Awesome List GitHub projects & posts around typed decisions (typesafe.ai). `★ 2` Picked by jtnkminimal
  1043. 1of 31 dairui1/jev-lab Browser dairui1/jev-lab** - Experiments with TypeSafe's Jev: triage benchmark vs LLM, and a source study of jev-ultrafast vs Cline's jev-browser Picked by RadRebelSam
  1044. 1of 31 danvega/hello-jev-java Other danvega/hello-jev-java** - No description provided. Picked by RadRebelSam
  1045. 1of 31 danvega/jev-spring-boot-starter Other A simple Spring Boot 4 starter for TypeSafe Jev using Spring MVC and RestClient. Picked by hellogumbo
  1046. 1of 31 david1gp/jev SDK & Runtime Result-based TypeSafe System One client library and jev command-line interface. Picked by JohnDotOwl
  1047. 1of 31 davila7/jev-explained Other davila7/jev-explained** - Jev Explained Picked by RadRebelSam
  1048. 1of 31 de-niji/jev-hermes Coding Agent de-niji/jev-hermes** - Jev for Hermes: cheap intent gates + verbatim tool compaction on OpenRouter Picked by RadRebelSam
  1049. 1of 31 deep-diver/mini-jev Other deep-diver/mini-jev** - No description provided. Picked by RadRebelSam
  1050. 1of 31 dev-willbird1936/pi-jev-compact Coding Agent dev-willbird1936/pi-jev-compact** - Verbatim Jev context compaction for Pi Coding Agent Picked by RadRebelSam
  1051. 1of 31 devtooligan/jevscan-evm Other Produces a heat map of likely bugs in EVM code. The author's own warning: a proof of concept whose code they did not read. Picked by MrJev
  1052. 1of 31 dgomez04/jev-refund-agent Other dgomez04/jev-refund-agent** - A weekend project to test Jev and work out how to design agent harnesses that mix system-one models with large-language models. Picked by RadRebelSam
  1053. 1of 31 digitalfrost84/openclaw-jev-openrouter Other digitalfrost84/openclaw-jev-openrouter** - OpenClaw plugin: TypeSafe AI Jev System One via OpenRouter decisions endpoint (fork of jason-allen-oneal/openclaw-plugin-typesafe-ai) Picked by RadRebelSam
  1054. 1of 31 dirnbauer/typo3-webcon-jev Routing dirnbauer/typo3-webcon-jev** - Typed decisions from TypeSafe AI's Jev model inside TYPO3: a decision editor and playground in the backend, powermail_cond operators, and submission routing Picked by RadRebelSam
  1055. 1of 31 dizk/jev-lens Coding Agent dizk/jev-lens** - jev picks what a coding agent gets to see of large tool results: core library, pi extension and Claude Code plugin Picked by RadRebelSam
  1056. 1of 31 doronp/jevc Other Compiles natural-language agent rules and JSON Schemas into TypeSafe Jev programs (typed questions + code reducers) you can test offline. Project guide. Picked by AppitStudio
  1057. 1of 31 drowzeys/keys-MiniMax-Code-CLI-Browser-Scroll-Context-Enhancement-Pack-with-Jev-Ultrafast-Integration Browser Validated enhancement pack for MiniMax Code CLI on arm64 DGX Spark + local GLM-5.3-EXL3: TUI scrollbar + context-meter patches, compaction repair for local vLLM, Jev Ultrafast + Playwright… Picked by hellogumbo
  1058. 1of 31 dtduc-git/jev-packs Awesome List curated questions, golden cases and measured evidence for Jev-compatible decision endpoints. Picked by rhc98
  1059. 1of 31 dtduc-git/jev-table SDK & Runtime typed answers, confidence, review queue, resume and cost preview. Local-first, BYO key. Picked by RadRebelSam
  1060. 1of 31 dtduc-git/jevassert Other Record/replay regression tests for Jev (TypeSafe System One) question packs Picked by rhc98
  1061. 1of 31 dwisiswant0/typesafe-sdk-go SDK & Runtime dwisiswant0/typesafe-sdk-go** - Go SDK for TypeSafe AI. Picked by RadRebelSam
  1062. 1of 31 edwardyen724-g/jev-compactor Coding Agent edwardyen724-g/jev-compactor** - Context compaction and safety gating for AI agents via TypeSafe Jev: keeps messages verbatim, no summarization. OpenAI, Anthropic, LangChain, CLI, MCP. Picked by RadRebelSam
  1063. 1of 31 ehmpathy/rhachet-brains-typesafeai Other ehmpathy/rhachet-brains-typesafeai** - rhachet brain.atom adapter for typesafe.ai classifier models Picked by RadRebelSam
  1064. 1of 31 enderkus/zammad-jev-dispatcher Routing enderkus/zammad-jev-dispatcher** - AI ticket triage for Zammad using Jev (TypeSafe AI) - classifies and routes new tickets into the right service group automatically. Picked by RadRebelSam
  1065. 1of 31 enderzcx/spire-jev Other Slay the Spire 2 agent controller: planner models, Jev fast decisions, and verified multi-card turn execution. Picked by rhc98
  1066. 1of 31 ericmartinezr/are-you-smarter-than-jev Other ericmartinezr/are-you-smarter-than-jev** - A small app to test Jev Picked by RadRebelSam
  1067. 1of 31 exs-brady/jev-eval-evidence Eval & Align 55,347 typed judgments, Jev vs 10 LLMs + keyword/regex floors, pre-registered with a blind cross-family replication Picked by dog-last
  1068. 1of 31 eylexlive/jev-drive Eval & Align eylexlive/jev-drive** - A 3D driving simulator where Jev, TypeSafe's decision model, chooses what the car does. Code eye or Gemini camera eye, code reflexes, an evaluation harness. Picked by RadRebelSam
  1069. 1of 31 fatelei/jev-compact Coding Agent scores every tool call before compaction and restores critical tool outputs verbatim after it Picked by RadRebelSam
  1070. 1of 31 fbettag/elixir-jev Search fbettag/elixir-jev** - Typed semantic judgments and pattern matching for TypeSafe Jev and local Laya in Elixir Picked by RadRebelSam
  1071. 1of 31 fblissjr/typesafe-experiments Other fblissjr/typesafe-experiments** - tinkering and experiments with jev and typesafe ai Picked by RadRebelSam
  1072. 1of 31 felixfisher/pi-jev-compaction Coding Agent felixfisher/pi-jev-compaction** - Experimental Pi extension using TypeSafe Jev for auditable tool-history compaction Picked by RadRebelSam
  1073. 1of 31 felpsdev/jev-classifier Coding Agent A local Jev tool-routing gateway for coding Agents, with an MCP suggestion interface. Picked by logicrw
  1074. 1of 31 filippos95/cybercab-jev Other filippos95/cybercab-jev** - Three.js robotaxi game where TypeSafe's Jev model makes the driving decisions Picked by RadRebelSam
  1075. 1of 31 flaviomartil/herdr-jev Other flaviomartil/herdr-jev** - Jev-driven multi-model triage and Triad orchestration plugin for Herdr and AI-Harness Picked by RadRebelSam
  1076. 1of 31 frederickrohn/jev-harness Other frederickrohn/jev-harness** - experimenting with Jev Picked by RadRebelSam
  1077. 1of 31 gloridifice/pi-jev-router Coding Agent Agent tooling (13):** tenet, jev-belay, jev-commit, pi-fast-jev-compaction, jev-flash-router, pi-jev, pi-jev-helm, stepwarden, AskJev-MCP, jev-compaction, jev-plugins, jevkeep, pi-jev-router Picked by heyjunpenn
  1078. 1of 31 glud123/jev-assist Other one Jev call per 60 files, with recall measured against real commits. Plus convention drift and pre-commit diff gating. Picked by RadRebelSam
  1079. 1of 31 gmaxxxie/jev-cli SDK & Runtime CLI for the Jev decision model via the OpenRouter Decisions API. `★ 1` Picked by jtnkminimal
  1080. 1of 31 gnoviawan/omp-jev-tools Other gnoviawan/omp-jev-tools** - Native omp (oh-my-pi) extension: TypeSafe Jev judgment tools Picked by RadRebelSam
  1081. 1of 31 gorock007/jev-atlas Other (site) - An independent, evidence-first field guide to Jev (TypeSafe AI's System One model) Picked by JohnDotOwl
  1082. 1of 31 gowtam04/jev-prototypes Other gowtam04/jev-prototypes** - Practice lab for TypeSafe Jev prototypes Picked by RadRebelSam
  1083. 1of 31 goya4140/jev-reward-model-evaluation Eval & Align (site) - Jev 1.13 reward-model evaluation across 8 benchmark tracks, with an interactive report and 54-row SOTA comparison. Picked by hellogumbo
  1084. 1of 31 grayrepo-byte/jev_filter_for_x Browser A browser extension that scores and filters X posts in real time with Jev, folding low-signal content while keeping it expandable. Without an API key, it defaults to local mock scoring. Picked by logicrw
  1085. 1of 31 gregjonesio/jev-nfl Other gregjonesio/jev-nfl** - Before every NFL snap, a decision-only AI model (TypeSafe Jev) calls run or pass and go/punt/kick on fourth down, graded live against the coach. Picked by RadRebelSam
  1086. 1of 31 h1code2/jev-x-blocker Other h1code2/jev-x-blocker** - No description provided. Picked by RadRebelSam
  1087. 1of 31 haibt163/jev Other Applications (7):** jev.nvim, github-star-organizer-jev, jev, JevSysUno, jev-trader, newsscore, trading-bot-jev Picked by heyjunpenn
  1088. 1of 31 hamakyo/jev-mahjong-bench Eval & Align hamakyo/jev-mahjong-bench** - Reproducible riichi mahjong benchmark for Jev, GPT, Mortal, and hybrid agents using MJAI and RiichiEnv. Picked by RadRebelSam
  1089. 1of 31 hari007sh/jev Computer Use hari007sh/jev** - Local System One model: typed decisions plus a voice computer-use agent. Picked by RadRebelSam
  1090. 1of 31 harshit-d3v/jev_project Other harshit-d3v/jev_project** - pr-scope and jevjudge Picked by RadRebelSam
  1091. 1of 31 harshpuri84/slopcheck-jev Coding Agent A prose linter that catches AI writing tells. Regex settles the 18 a pattern can settle. Jev takes the 15 that need reading, as 15 Nouls in one call, 604 ms median. It ships as a Claude… Picked by logicrw
  1092. 1of 31 hatt-io/jevkeep Coding Agent Agent tooling (13):** tenet, jev-belay, jev-commit, pi-fast-jev-compaction, jev-flash-router, pi-jev, pi-jev-helm, stepwarden, AskJev-MCP, jev-compaction, jev-plugins, jevkeep, pi-jev-router Picked by heyjunpenn
  1093. 1of 31 hdkiller/jev-panerelay Browser hdkiller/jev-panerelay** - Ultra-fast browser automation using TypeSafe Jev via Panerelay and OpenRouter. Picked by RadRebelSam
  1094. 1of 31 heaven-hm/jev-system-one Other A polished OpenAI + TypeSafe Jev terminal interface for answers with transparent decision reports. Picked by JohnDotOwl
  1095. 1of 31 hfmsio/jev-wiki-watch Other hfmsio/jev-wiki-watch** - Live Wikipedia vandalism watch judged by Jev, TypeSafe AI's typed-decision model. Two files, no packages. Picked by RadRebelSam
  1096. 1of 31 hoangngochuong24947-gif/jev-figure-router Routing hoangngochuong24947-gif/jev-figure-router** - Universal Figure & Diagram Router for AI Agents powered by TypeSafe Jev / Jeb System-1 Picked by RadRebelSam
  1097. 1of 31 hoangngochuong24947-gif/jev-patent-disclosure Coding Agent hoangngochuong24947-gif/jev-patent-disclosure** - Patent disclosure and application drafting skill powered by TypeSafe Jev / Jeb System-1 Picked by RadRebelSam
  1098. 1of 31 hosseintoussi/jev-flappy-bird Other hosseintoussi/jev-flappy-bird** - A live demo of TypeSafe's Jev model playing Flappy Bird, one flap-or-wait decision at a time. Picked by RadRebelSam
  1099. 1of 31 hyspacex/jev-router Routing hyspacex/jev-router** - Route OpenAI-style chat requests to a model and reasoning effort, using TypeSafe's Jev decision model as the classifier Picked by RadRebelSam
  1100. 1of 31 ibrahemid/git-jev-stage Other Select Git changes for staging with a plain-language description. Picked by hellogumbo
  1101. 1of 31 imom39a/jev-playground Routing imom39a/jev-playground** - Local JEV experiments: route decisions, Minesweeper solvers, and drone simulation Picked by RadRebelSam
  1102. 1of 31 imserhatdemir/jevspace Other TypeSafe's System One model. Three.js world, deterministic engine, Jev picks the targets. Picked by RadRebelSam
  1103. 1of 31 indiejoseph/opencode-jev-pruner Coding Agent indiejoseph/opencode-jev-pruner** - OpenCode plugin: trim long Bash output with TypeSafe Jev before the model sees it Picked by RadRebelSam
  1104. 1of 31 inematds/jev Other Análise crítica e plano de aplicação do Jev em decisões estruturadas. Picked by rhc98
  1105. 1of 31 ingebyd/fast-jev-compaction-openrouter Coding Agent ingebyd/fast-jev-compaction-openrouter** - Fork of tamaratran/fast-jev-compaction: Jev via OpenRouter with zero data retention (zdr, data_collection: deny) Picked by RadRebelSam
  1106. 1of 31 integralmarketingmx/jev-latam-lead-triage Eval & Align integralmarketingmx/jev-latam-lead-triage** - Triage de leads de WhatsApp/CRM con Jev (TypeSafe AI): ruteo por confianza, plantilla n8n y benchmark en español. Sin dependencias. No afiliado. Picked by RadRebelSam
  1107. 1of 31 integrate-your-mind/jev-nethack Other Jev x NetHack: bounded runner, research code, and completed recording releases. Picked by rhc98
  1108. 1of 31 ishantanu/jevmetrics Other Experimental OpenTelemetry Collector metrics processor: TypeSafe Jev assesses instrument metadata for retention; deterministic keep/reduce policy with caching (alpha). Project guide. Picked by AppitStudio
  1109. 1of 31 jaibhasin/jev-flappy-bird Other jaibhasin/jev-flappy-bird** - Jev learns to play flappy-bird game with physics based context and without it Picked by RadRebelSam
  1110. 1of 31 jal-co/jev-agent-browser Browser jal-co/jev-agent-browser** - Jev policy decisions executed through Agent Browser Picked by RadRebelSam
  1111. 1of 31 jcpsimmons/jev-model-router-demo Coding Agent jcpsimmons/jev-model-router-demo** - Throwaway Jev demo: route coding tasks to Grok Build or Codex Astra Picked by RadRebelSam
  1112. 1of 31 jcressler/jev-codex-token-saver Coding Agent Codex plugin/MCP that scores bounded local evidence with TypeSafe Jev and returns selected exact excerpts (local fallback when Jev is unavailable). Project guide. Picked by AppitStudio
  1113. 1of 31 jeffloo886/jev-notion Computer Use 🚀 Blazing-fast native macOS menu bar companion for Notion. Pure Swift & SwiftUI (<3MB), 8 languages. Picked by hellogumbo
  1114. 1of 31 jeiel85/jevscope SDK & Runtime Local-first visual workbench and JSONL regression testbench for TypeSafe Jev projects. Project guide. Picked by AppitStudio
  1115. 1of 31 jflam/jev1 Home & IoT Jev (TypeSafe System One) proof of concept: smart-home assistant demo. Picked by JohnDotOwl
  1116. 1of 31 jiangkoumo/ego-jev Browser jiangkoumo/ego-jev** - Drive the ego lite browser with Jev (TypeSafe System One): one indexed element table in, one operation + target out, single process. ~2x faster than a per-step LLM… Picked by RadRebelSam
  1117. 1of 31 jkakar/typesafe-sdk-go Eval & Align jkakar/typesafe-sdk-go** - Go client for the TypeSafe AI API. Ask typed questions, get calibrated probabilities your code can act on Picked by RadRebelSam
  1118. 1of 31 jkalend/jev-cicd Routing Go backend, Go CLI, Next.js frontend. Failure classification, log triage, issue routing, notification filtering as typed decisions Picked by RadRebelSam
  1119. 1of 31 jkalend/jev-realms Other jkalend/jev-realms** - Terminal ASCII RPG where every NPC thinks with Jev (TypeSafe AI System One) Picked by RadRebelSam
  1120. 1of 31 jolehuit/jev-downloads-sorter Other jolehuit/jev-downloads-sorter** - A ~/Downloads folder that sorts itself: one Jev decision per file, launchd WatchPaths, no daemon Picked by RadRebelSam
  1121. 1of 31 jonatasperaza/jev-voice-windows SDK & Runtime jonatasperaza/jev-voice-windows** - Controle o Windows por voz: transcricao local (faster-whisper GPU) + decisoes tipadas do Jev (TypeSafe AI) Picked by RadRebelSam
  1122. 1of 31 jonymusky/jev-browser-qa Browser jonymusky/jev-browser-qa** - Browser QA where Playwright drives and films, and TypeSafe Jev judges. JSON-flow CLI for agents, run dashboard, agent skill. Picked by RadRebelSam
  1123. 1of 31 joshbla/jev-plays-2048 Other A visible 2048 experiment powered by TypeSafe. Picked by JohnDotOwl
  1124. 1of 31 joslynSmall/fast-jev-compaction-pi Coding Agent This Pi extension asks Jev whether each completed tool call and its full result should be kept, then locally retains, truncates, or drops verbatim tool evidence in the compaction summary. Picked by logicrw
  1125. 1of 31 juancristobalgd1/jevRemote Browser (site) - Reproducible text-first browser automation experiment with TypeSafe Jev and Playwright. Picked by JohnDotOwl
  1126. 1of 31 juanlentino/jev-comment-analysis Other juanlentino/jev-comment-analysis** - Backs the WordPress AI plugin's Comment Moderation with TypeSafe Jev, through Connector for TypeSafe Jev Picked by RadRebelSam
  1127. 1of 31 jumboly/jev-map-sandbox Other jumboly/jev-map-sandbox** - Jev (TypeSafe AI の System One モデル) を地図に使ってみる実験場。音声指示で地理院地図Vector のレイヤーを重要度分類する。 Picked by RadRebelSam
  1128. 1of 31 jwallio/jev-trader Other jwallio/jev-trader** - One AI trade decision every Monad block. Jev on Kuru MON-USDC. Picked by RadRebelSam
  1129. 1of 31 kaijia323/dsh-plugin-jev Other kaijia323/dsh-plugin-jev** - TypeSafe Jev (System One decision model) as a native jev_decide tool plugin for DeepSeek Harness Picked by RadRebelSam
  1130. 1of 31 karimatayuta/tiny-jev Other Demos & playgrounds (2):** forma-system1-experiment, tiny-jev Picked by heyjunpenn
  1131. 1of 31 kentaro/jev-shogi Other 判定特化モデル Jev に将棋を指させる実験（ロリポップ！AIゲートウェイ経由）. `★ 0` Picked by jtnkminimal
  1132. 1of 31 keremt-dev/jev.decide Other keremt-dev/jev.decide** - No description provided. Picked by RadRebelSam
  1133. 1of 31 kevin9327/jev-harness Other kevin9327/jev-harness** - JevHarness: TypeSafe Jev agent tool-call gate. execute / confirm / reject in code. Picked by RadRebelSam
  1134. 1of 31 kgonia/typesafe-sdk-java SDK & Runtime Zero-dependency Java client (Java 21+). Picked by MrJev
  1135. 1of 31 kierandotai/jev-scout Coding Agent MCP server that scores an agent's every search query, result, and fetched page for relevance and credibility, with session budgets, SSRF-guarded fetching, and a live decision dashboard. Picked by cobanov
  1136. 1of 31 knowlet/jev-agentworld-web-simulator Other knowlet/jev-agentworld-web-simulator** - An entire internet Picked by RadRebelSam
  1137. 1of 31 knowlet/jevlens Browser Browser & computer use (6):** jev-social, jev-skip, jevarena, jev-browser-pilot, jevlens, jev-orb Picked by heyjunpenn
  1138. 1of 31 kofanlabs/jev-browser-chrome Browser kofanlabs/jev-browser-chrome** - Fast Jev browser agent for existing signed-in Chrome tabs via a local extension bridge and MCP Picked by RadRebelSam
  1139. 1of 31 kofanlabs/typesafe-computer-use-windows Computer Use kofanlabs/typesafe-computer-use-windows** - Windows port of typesafe-computer-use with Jev decisions, local OCR/UIA, and MCP host integration Picked by RadRebelSam
  1140. 1of 31 koki-develop/fizzbuzz-jev Other koki-develop/fizzbuzz-jev** - FizzBuzz powered by Jev, TypeSafe AI's System One model. Picked by RadRebelSam
  1141. 1of 31 kokuren333/jev-jmle-benchmark Eval & Align 9 years of Japanese Medical Licensing Exams (3,556 items): **88.58%**; companion manuscript on medRxiv Picked by dog-last
  1142. 1of 31 krsna-smnt/jev-moral-dilemmas Other krsna-smnt/jev-moral-dilemmas** - Does Jev give the same answer twice? Repeatability and confidence-stability experiments on TypeSafe's Jev model Picked by RadRebelSam
  1143. 1of 31 kt3k/jevchat Other A chat-style Jev demo whose answers are selected from predefined or custom options rather than generated prose. Picked by logicrw
  1144. 1of 31 kyledickey/jev-go SDK & Runtime kyledickey/jev-go** - TypeSafe.ai Jev Go SDK Picked by RadRebelSam
  1145. 1of 31 laihenyi/pi-Jev-browser Browser Pi extension where TypeSafe Jev chooses each Playwright browser action over a structured DOM observation in a bounded loop. Project guide. Picked by AppitStudio
  1146. 1of 31 lainollll/lm-studio-typesafe-chat Other Tkinter chat and live visual narration with LM Studio, TypeSafe Jev, and Chatterbox TTS. Picked by JohnDotOwl
  1147. 1of 31 larches-technologies/openclaw-jev-router Routing larches-technologies/openclaw-jev-router** - Privacy-aware TypeSafe Jev tools and per-turn tool-family routing for OpenClaw. Picked by RadRebelSam
  1148. 1of 31 larguesa/jev-search Search (larguesa) - Experimental semantic line search with TypeSafe Jev via OpenRouter. Python CLI with no runtime dependencies. Picked by hellogumbo
  1149. 1of 31 lavallee/mk-jev-fly-brain Other Compares a fly-connectome spiking simulation, Jev and rule policies in the mk.js fighting game. Picked by logicrw
  1150. 1of 31 leepokai/llm-prompt-techniques-on-jev Other leepokai/llm-prompt-techniques-on-jev** - Chain-of-thought and self-refinement for TypeSafe's Jev: feed its typed answers back as state and ask again. Benchmarks vs TypeSafe's own cookbook… Picked by RadRebelSam
  1151. 1of 31 leesk212/JEV-CPU Other no GPU. Reads typed option probabilities straight from an open model in one forward pass, plus a web UI. Picked by RadRebelSam
  1152. 1of 31 lhotwll217/jev-cli Other SDKs & clients (1):** jev-cli Picked by heyjunpenn
  1153. 1of 31 logicrw/ask-jev Other Ultra-fast, fail-open advisory decisions and verbatim extractive reading view for AI coding agents and CLI pipelines Picked by logicrw
  1154. 1of 31 loicrg/jev-spam-lab Eval & Align loicrg/jev-spam-lab** - CLI for evaluating Microsoft Outlook email with TypeSafe AI’s Jev model. Picked by RadRebelSam
  1155. 1of 31 lookfwd/jev-fact-checker Other lookfwd/jev-fact-checker** - Uses Typesafe AI Jev to Provide A Tweet Fact Checker Picked by RadRebelSam
  1156. 1of 31 lorensation/llm-cost-optimizer-jev Routing lorensation/llm-cost-optimizer-jev** - An intelligent routing layer powered by TypeSafe AI's System One model Jev that sits in front of multiple LLM providers, analyzes each incoming… Picked by RadRebelSam
  1157. 1of 31 luiginotmario/postgres-Jev Data luiginotmario/postgres-Jev** - Natural-language PostgreSQL predicates with TypeSafe Jev. A simple search playground with randomly generated databases. Picked by RadRebelSam
  1158. 1of 31 mahavirn/mnjev-cli Other mahavirn/mnjev-cli** - CLI for JEV Model Picked by RadRebelSam
  1159. 1of 31 makefinks/jev-feed-filter Other makefinks/jev-feed-filter** - Smart, dynamic AI filtering for X and YouTube feeds using Jev Picked by RadRebelSam
  1160. 1of 31 makefunstuff/jev-lsp SDK & Runtime makefunstuff/jev-lsp** - Jev backed lsp server that uses jev inference api to steer code harnesses or detect problems while working in editor. Picked by RadRebelSam
  1161. 1of 31 mameli/jev-vs-luna Other Benchmarks & research (4):** openjev, paper-package, jev-vs-luna, typed-decisions Picked by heyjunpenn
  1162. 1of 31 manojlds/jev-review Coding Agent manojlds/jev-review** - Standalone TypeSafe Jev code-review CLI: typed decisions over a local git diff. Picked by RadRebelSam
  1163. 1of 31 marcelomar21/demo-tetris-jev Other marcelomar21/demo-tetris-jev** - Tetris arcade jogado pelo Jev da TypeSafe AI, com decisões em JSON, antecipação de jogadas e custo por partida. Picked by RadRebelSam
  1164. 1of 31 markfive-proto/typesafe-vs-deepseek Eval & Align (site) - TypeSafe (Jev) vs DeepSeek-flash: side-by-side speed/token/cost/accuracy comparison across invoice extraction, email classification, and reranking. Picked by hellogumbo
  1165. 1of 31 matthewdonsemail-lab/open-typesafe-camoufox Browser CLI that drives a headed Camoufox browser toward a plain-English goal, without sending screenshots. `★ 2` Picked by jtnkminimal
  1166. 1of 31 matthewman/jev-snake Other matthewman/jev-snake** - Jev plays Snake, with recorded games, replay, and experiments. Picked by RadRebelSam
  1167. 1of 31 meetr1912/jev-arena Eval & Align meetr1912/jev-arena** - A calibration arena for TypeSafe Jev: reliability, Brier/ECE, and confidence-gated risk-coverage on analytically-known random worlds. Picked by RadRebelSam
  1168. 1of 31 meetr1912/jev-vickrey Eval & Align meetr1912/jev-vickrey** - TypeSafe Jev bids in sealed-bid auctions: threshold fan-out reconstructs a calibrated value CDF, scored by regret and truthfulness. Picked by RadRebelSam
  1169. 1of 31 memorysaver/jev-atari-lab Other Games & simulations (8):** jev-plays-pokemon-red, jev-royal, beat-jev, f1, jev-atari-lab, jev-plays-pokemon, JevArena, naimono-lab Picked by heyjunpenn
  1170. 1of 31 mheers/typesafeai-systemone-jev-go SDK & Runtime mheers/typesafeai-systemone-jev-go** - Typed Go client for the TypeSafe System One API (Jev): structured questions and answers your code can act on. Community SDK, MIT. Picked by RadRebelSam
  1171. 1of 31 mhmdkzr/jev SDK & Runtime An unofficial Go client for TypeSafe's System One Jev model. Picked by JohnDotOwl
  1172. 1of 31 miaopj0325-collab/jev_mcp Other miaopj0325-collab/jev_mcp** - No description provided. Picked by RadRebelSam
  1173. 1of 31 micic-mihajlo/jev-tool-runner Coding Agent micic-mihajlo/jev-tool-runner** - Jev selects developer tools; Codex handles code. MCP and Jev-first execution with measured benchmarks. Picked by RadRebelSam
  1174. 1of 31 minghanminghan/jev-demo Routing A customer-service routing demo that batches Jev questions before following the resulting route. Picked by logicrw
  1175. 1of 31 minhgv/jev-mcp Coding Agent TypeSafe Jev MCP decision layer for coding agents and CI. Picked by JohnDotOwl
  1176. 1of 31 minhnghia2k3/jev-k8s-awareness Other minhnghia2k3/jev-k8s-awareness** - k8s awareness with jev Picked by RadRebelSam
  1177. 1of 31 miounet11/jevcode Other Jev (TypeSafe System One) 技术解决方案与最佳实践 Picked by rhc98
  1178. 1of 31 misaalya/snbt-jev-bench Other Jev on Indonesia's SNBT 2025 university entrance test: 159 questions, seven subtests, audited answer keys. Picked by JohnDotOwl
  1179. 1of 31 mittal-parth/jev-experiments Browser Uses Jev to play Chrome Dino and a local shooter arena while Python executes structured decisions. Picked by logicrw
  1180. 1of 31 mizuamedesu/SuperTuxKart-Jev SDK & Runtime SuperTuxKart fork with a local controller that lets Jev drive the kart. `★ 0` Picked by jtnkminimal
  1181. 1of 31 moguone/jev-lab Eval & Align moguone/jev-lab** - Small apps for evaluating TypeSafe AI's System One model (Jev). Unofficial. Picked by RadRebelSam
  1182. 1of 31 mttrbrts/jev-folio-recursive-classifier Computer Use Classifies OCR'd legal agreements through the FOLIO Document Types ontology with recursive Jev Choices, beam search, confidence-gated leaf stopping, and context-length benchmarking. Picked by valentynkit
  1183. 1of 31 munirad7s/jev-escape Other Escape Room mit Freitext-Eingabe: TypeSafes Jev urteilt als Schiedsrichter über jeden getippten Satz. Picked by rhc98
  1184. 1of 31 nabendu82/jev-reflex Other nabendu82/jev-reflex** - Multimodal Mac controller using Hand gestures and voice Picked by RadRebelSam
  1185. 1of 31 nak1b/jev-experiments Other nak1b/jev-experiments** - Small experiments with Jev by TypeSafe Picked by RadRebelSam
  1186. 1of 31 namayasai/backstage-jev-operations-support Other namayasai/backstage-jev-operations-support** - Jev-powered operations decision support for Backstage: readiness checks, incident triage, change review, template and team recommendations… Picked by RadRebelSam
  1187. 1of 31 nayan-kunwar/jev-triage Other nayan-kunwar/jev-triage** - No description provided. Picked by RadRebelSam
  1188. 1of 31 ndolinschi/jev-wave Other TypeSafe Jev research + 5 product specs. Picked by JohnDotOwl
  1189. 1of 31 nextflow-io/nf-jev Other Nextflow plugin exposing TypeSafe Jev noul/choice/score as pipeline functions (beta). Project guide. Picked by AppitStudio
  1190. 1of 31 ngallodev-software/agent-workflow-typesafe-ai Other ngallodev-software/agent-workflow-typesafe-ai** - Optional TypeSafe AI/Jev advisory decision evidence for Agent-Workflow, without transferring lifecycle authority from deterministic… Picked by RadRebelSam
  1191. 1of 31 nikotaronosuke/jev-voice-decision SDK & Runtime nikotaronosuke/jev-voice-decision** - Japanese speech → local STT → Jev typed decisions → deterministic actions. Picked by RadRebelSam
  1192. 1of 31 nirgal-soft/typesafe-rs SDK & Runtime nirgal-soft/typesafe-rs. A rust client for the TypeSafe AI API. 0 stars. Picked by walidboulanouar
  1193. 1of 31 nishioka-shinji/jev-edgar Eval & Align nishioka-shinji/jev-edgar** - Does Jev, a System One model returning calibrated probabilities, say anything useful about an earnings release before the market prices it? Picked by RadRebelSam
  1194. 1of 31 nitinnat/jev-gateway Routing nitinnat/jev-gateway** - A small local HTTP service for TypeSafe AI's Jev through Vercel Picked by RadRebelSam
  1195. 1of 31 novvoo/nanojev SDK & Runtime (single-file) - A single-file, MIT-licensed educational implementation with a small serving UI and HTTP API. Picked by rupeshpoojary9
  1196. 1of 31 nrdz-labs/fast-jev-opencode Coding Agent nrdz-labs/fast-jev-opencode** - Jev-scored context pruning for OpenCode: drops stale tool calls and truncates bulky results on the outgoing request Picked by RadRebelSam
  1197. 1of 31 nsillik/jevvin-off SDK & Runtime Prototyping against TypeSafe's Jev System One API: a one-ticket quickstart and a Bluesky Jetstream firehose demo. Picked by JohnDotOwl
  1198. 1of 31 octanevz/jev-playground-openrouter Browser octanevz/jev-playground-openrouter** - Local browser playground for TypeSafe's Jev decision model via OpenRouter. Python stdlib only. Picked by RadRebelSam
  1199. 1of 31 ojusave/beat-jev Other Games & simulations (8):** jev-plays-pokemon-red, jev-royal, beat-jev, f1, jev-atari-lab, jev-plays-pokemon, JevArena, naimono-lab Picked by heyjunpenn
  1200. 1of 31 okooo5km/jev Coding Agent okooo5km/jev** - Typed decisions from the shell: an unofficial stdlib-Python CLI and Agent Skill for TypeSafe's Jev model, via the TypeSafe API (default) or OpenRouter. Yes/no, choice and… Picked by RadRebelSam
  1201. 1of 31 oldmoldycake/jev_vampire_survivors Other oldmoldycake/jev_vampire_survivors** - TypeSafe's Jev model plays Vampire Survivors on Steam: BepInEx plugin + Python brain + live decision dashboard. Native Linux only. Picked by RadRebelSam
  1202. 1of 31 onlyoneaman/jev-eval Eval & Align TypeSafe's Jev vs gpt-5.4-mini and gpt-5.6-luna on four public classification sets: cases, per-item answers, scoring, charts. `★ 0` Picked by jtnkminimal
  1203. 1of 31 paulobueno164/jev-mcts Other Busca em arvore (MCTS/PUCT) com avaliacao tipada do TypeSafe Jev e portao humano obrigatorio. A arvore supoe, a sonda mede: marco so e concedido por codigo de saida verde. Picked by JohnDotOwl
  1204. 1of 31 pavan142/jev-experiments Other pavan142/jev-experiments** - No description provided. Picked by RadRebelSam
  1205. 1of 31 perixtar/jev-e2e Browser perixtar/jev-e2e** - Natural-language end-to-end tests for web apps, powered by Jev and Playwright. Picked by RadRebelSam
  1206. 1of 31 phd-peter/ego-jev Browser Connects Ego Lite snapshots and browser actions to a bounded Jev decision loop. Picked by logicrw
  1207. 1of 31 phuthuycoding/jev-audit Eval & Align blocks secrets, vulns & low-quality code in ~300ms. 79-case test corpus at 100% accuracy. Picked by JohnDotOwl
  1208. 1of 31 pistachiopranay/jev-synergy-screening Other Jev (TypeSafe System One) × ASReview SYNERGY abstract screening demo Picked by JohnDotOwl
  1209. 1of 31 ponyo877/jev-telop-live Other ponyo877/jev-telop-live** - No description provided. Picked by RadRebelSam
  1210. 1of 31 portlandhodl/jev-cli Other portlandhodl/jev-cli** - No description provided. Picked by RadRebelSam
  1211. 1of 31 qiaohaojie/Jev-MongoDB Other qiaohaojie/Jev-MongoDB** - Real-time FMCG customer care triage: MongoDB Change Streams + TypeSafe Jev Picked by RadRebelSam
  1212. 1of 31 realdubb/jev-playground SDK & Runtime realdubb/jev-playground** - Playground for TypeSafe AI's Jev decision model: provider-agnostic AI SDK scripts, jev-filter CLI, GitHub pruner Picked by RadRebelSam
  1213. 1of 31 recodelabs/duckdb-jev Data Natural-language WHERE clauses for DuckDB, powered by TypeSafe's Jev. Picked by JohnDotOwl
  1214. 1of 31 reiswaffel78/jev-agent-toolkit Coding Agent reiswaffel78/jev-agent-toolkit** - Jev-first portable Agent Skill and optional MCP bridge for Claude Code, Codex, Cursor and compatible agents. Picked by RadRebelSam
  1215. 1of 31 renatosousa/jev-trader Other Applications (7):** jev.nvim, github-star-organizer-jev, jev, JevSysUno, jev-trader, newsscore, trading-bot-jev Picked by heyjunpenn
  1216. 1of 31 rikkooo/jev-trade Other A market-data trading simulator powered by auditable Jev judgments. Picked by rhc98
  1217. 1of 31 rlaope/jeval Routing Measures probabilistic classifier calibration (incl. Jev confidence) and cost-optimal human hand-off thresholds; offline demo included. Project guide. Picked by AppitStudio
  1218. 1of 31 robipop22/Jev-is-odd Other Ask Jev by TypeSafe AI whether a number is odd. TypeScript, real token usage, and latency benchmarks. `★ 0` Picked by jtnkminimal
  1219. 1of 31 rolki-png/JevArena Other Games & simulations (8):** jev-plays-pokemon-red, jev-royal, beat-jev, f1, jev-atari-lab, jev-plays-pokemon, JevArena, naimono-lab Picked by heyjunpenn
  1220. 1of 31 rongxinzy/LightJev Eval & Align rongxinzy/LightJev** - Train lightweight language backbones for typed decisions and candidate probabilities. CE/Brier training, evaluation, and an offline end-to-end demo. Picked by RadRebelSam
  1221. 1of 31 rorshopping/jev-browser-local Browser rorshopping/jev-browser-local** - Run jev-browser on a fully local JEV-style decision engine (no cloud API). Warm-browser fork, VRAM guard, measured benchmarks, run traces. Picked by RadRebelSam
  1222. 1of 31 rthomas24/jev-realtime-trading Computer Use Paper trading agents on a live tape, decided every second by TypeSafe's Jev (System One). Electron desktop app. Picked by JohnDotOwl
  1223. 1of 31 samoweb3/jev-x-posts Other Sortable 48-hour X post report for Jev, TypeSafe AI and Diogo Almeida, with Jev sentiment labels. Picked by JohnDotOwl
  1224. 1of 31 sanmai/typesafe-ai-php SDK & Runtime sanmai/typesafe-ai-php** - Jev for PHP, TypeSafe AI PHP SDK Picked by RadRebelSam
  1225. 1of 31 sava-software/typesafe-client Eval & Align Java client for the TypeSafe System One API (Jev): typed questions in, calibrated probabilities out. Picked by JohnDotOwl
  1226. 1of 31 scursel/hermes-jev-fastpath Other Hermes Agent middleware using TypeSafe Jev for fail-open deterministic fast paths before LLM execution. Picked by rhc98
  1227. 1of 31 shanginn/jev-php SDK & Runtime shanginn/jev-php** - Type-safe PHP 8.5 SDK for JEV decisions on OpenRouter: choices, scores, probabilities and typed DTOs. Picked by RadRebelSam
  1228. 1of 31 shinshin86/jev-aituber-tension-sample Other shinshin86/jev-aituber-tension-sample** - A small demo that passes a viewer comment to Jev and asks whether the AITuber's tension goes up, stays the same, or goes down. The tension value… Picked by RadRebelSam
  1229. 1of 31 shivamnarkar47/Jev-testcase Other shivamnarkar47/Jev-testcase** - Validate execution plans with TypeSafe Jev (raw curl, tunable thresholds, JSON mode) Picked by RadRebelSam
  1230. 1of 31 shunshunNi/redmine_jev Other shunshunNi/redmine_jev** - Asks Jev whether a Redmine issue's tracker fits, while you fill in the form Picked by RadRebelSam
  1231. 1of 31 shunta-furukawa/jev-tick-lab Eval & Align A forward-only experiment: Jev (TypeSafe System One) making one-second trading judgments on bitbank, logged for calibration analysis. Picked by JohnDotOwl
  1232. 1of 31 simonsez9510/jev-cite-check Other simonsez9510/jev-cite-check** - AI가 조례에 대해 답한 문장이 인용한 조문에 실제로 근거하는지 Jev(TypeSafe AI)로 판정하는 게이트 실험 Picked by RadRebelSam
  1233. 1of 31 skcache/jevtrafficsim Other TypeSafe AI's first model Jev takes on an entire city's traffic. Picked by JohnDotOwl
  1234. 1of 31 stas4000/jev-clerk Computer Use A macOS desktop clerk that books supplier invoices: Jev picks each click from a closed action list; a deep model only rewrites the playbook. Picked by logicrw
  1235. 1of 31 stas4000/jev-linkmap Other stas4000/jev-linkmap** - Rebuild a site's internal link map in seconds with Jev, race Claude Opus 5 on the same queue, and let a deep model rewrite the rubric from the disagreements. Picked by RadRebelSam
  1236. 1of 31 stbenjam/jev-eight-ball Other A liquid magic eight ball powered by TypeSafe Jev decisions through OpenRouter. `★ 0` Picked by jtnkminimal
  1237. 1of 31 stbenjam/jevagotchi Other A tiny virtual pet cared for by TypeSafe Jev through OpenRouter. Picked by JohnDotOwl
  1238. 1of 31 stoopid-computers/jev-bot Computer Use stoopid-computers/jev-bot** - Computer Use Agent developed with Jev Picked by RadRebelSam
  1239. 1of 31 sudeshkar/jev-corrective-rag Search Corrective RAG demo: TypeSafe Jev typed gates for triage/grading/verify; generative LLM only writes answers. Project guide. Picked by AppitStudio
  1240. 1of 31 swap-mitra/jev-techstack-classifier Mobile swap-mitra/jev-techstack-classifier** - Describe a software project in plain English and get a probability-ranked tech stack (frontend, backend, database, hosting, mobile) from TypeSafe Jev. Picked by RadRebelSam
  1241. 1of 31 takafumikobayashi/jev-snap-lab Other takafumikobayashi/jev-snap-lab** - Tiny inputs. Instant decisions. A small experimental playground for exploring fast, probabilistic decisions with Jev. Picked by RadRebelSam
  1242. 1of 31 takezou621/jev-claude Eval & Align let a cheap evaluation-only model decide whether the work is actually done. Picked by JohnDotOwl
  1243. 1of 31 teempai/jev-in-codex Coding Agent Codex MCP tools for TypeSafe Jev-ranked capability selection, workspace search, and output triage (experimental MVP). Project guide. Picked by AppitStudio
  1244. 1of 31 tetsuya-dev-jp/jev-pacman Other tetsuya-dev-jp/jev-pacman** - Jev (TypeSafe System One) plays Pac-Man in real time: structured state in, one legal direction out. No screenshots, no fine-tuning. Picked by RadRebelSam
  1245. 1of 31 theSekyi/jevusecases Awesome List Other lists (5):** awesome-jev-by-typesafe, awesome-jev, awesome-jev-typesafe, jevusecases, Jev-Case Picked by heyjunpenn
  1246. 1of 31 thejorgg/omp-jev Routing Jev routing for Oh My Pi, with an opt-in checkpoint orchestrator. `★ 3` Picked by jtnkminimal
  1247. 1of 31 thelau/jev-tetris Other — Picked by cobanov
  1248. 1of 31 thesammykins/jev_ampcode Other An Amp plugin for comparing supplied alternatives against supplied evidence and priorities. Picked by logicrw
  1249. 1of 31 thevibeworks/awesome-typesafe-jev Awesome List Curated list of projects built on TypeSafe's Jev model, read before listed. With media and our own measurements. Not affiliated with TypeSafe AI. Picked by rhc98
  1250. 1of 31 thevilledev/typesafe-scheduler-diagnostics Other thevilledev/typesafe-scheduler-diagnostics** - Experimental out-of-tree Kubernetes scheduler plugin that uses TypeSafe's Jev model to produce typed, advisory diagnoses for unschedulable… Picked by RadRebelSam
  1251. 1of 31 thijmenkam/jev-benchmarks Eval & Align (frontier comparison harness), Harness asking Jev and frontier LLMs identical typed questions, scoring accuracy, calibration, latency and schema validity; no measured run published yet. Picked by OmniJev
  1252. 1of 31 thisisjorge/jev-control-room Eval & Align thisisjorge/jev-control-room** - A visual control room for typed AI evaluations, structured decision-making, and confidence-aware policy gating using Vercel AI SDK and TypeSafe Jev. Picked by RadRebelSam
  1253. 1of 31 tubone24/jev-practice-speed Other トランプの スピード を、CPU 側の頭脳に TypeSafe AI の Jev を使って対戦する WebGL デモアプリ。Jev の判断速度と判断精度をリアルタイムに計測して見せることが目的。. Picked by rhc98
  1254. 1of 31 tunahansahin897/what-is-jev Other A sourced, critical research file on TypeSafe's Jev (System One) model, plus a rubric-scored map of 780 public repositories. English / Türkçe. Picked by rhc98
  1255. 1of 31 tyleree/jevbot Other Options trading bot (backtest + Alpaca paper only) with TypeSafe Jev as the decision core. Picked by JohnDotOwl
  1256. 1of 31 typakon4/jev-layer Routing Portable System-1 decision layer for agent harnesses: host-owned capability routing, receipts/replay, optional supervision, demo/OpenRouter/TypeSafe providers. Project guide. Picked by AppitStudio
  1257. 1of 31 typesafe-ai/Overwatch Other Official (2):** TypeSafe Daggerverse, TypeSafe Overwatch Picked by heyjunpenn
  1258. 1of 31 ufec/typesafe-sdk-kotlin SDK & Runtime — Picked by AbdelStark
  1259. 1of 31 ufx7/jev-testbench Other ufx7/jev-testbench** - Black-box Jev test bench + a Claude/LLM-and-Jev collaboration measurement harness Picked by RadRebelSam
  1260. 1of 31 unimtx/typesafe-sdk-go SDK & Runtime unimtx/typesafe-sdk-go** - A Go SDK for the TypeSafe API, enabling quick integration with Jev. Picked by RadRebelSam
  1261. 1of 31 unownone/jevsume Other A resume-review app that checks general writing and structure or compares a resume with a specific job description. Picked by logicrw
  1262. 1of 31 uspraveen/Jev-Reranker Search uspraveen/Jev-Reranker** - A System-1 model based memory retrieval reranked using caliberated decision space instead of embeddings Picked by RadRebelSam
  1263. 1of 31 vagmi/jevlite Other vagmi/jevlite** - An attemt to recreate jev model on top of gemma Picked by RadRebelSam
  1264. 1of 31 vayungodara/jev-lint Other Lint a Markdown knowledge base (Obsidian vault or LLM wiki) for contradictions, stale claims, unresolved markers and missing pages, using TypeSafe Jev. `★ 0` Picked by jtnkminimal
  1265. 1of 31 vedssharma/jev-drive Browser vedssharma/jev-drive** - Browser-based autonomous car simulator powered by Jev: connected roads, traffic signals, pedestrians, weather, and overtaking Picked by RadRebelSam
  1266. 1of 31 vinilana/jev-gateway-bench Routing vinilana/jev-gateway-bench. Benchmark for jev-gateway: real coding agents on chess engine tasks, with Jev routing on and off. 1 stars. Picked by walidboulanouar
  1267. 1of 31 vrash/jeval Eval & Align vrash/jeval** - jeval: open-source evaluations for AI outputs and agents, judged by Jev Picked by RadRebelSam
  1268. 1of 31 vtrivedy/jev-plays-games Other vtrivedy/jev-plays-games** - Chess, Connect Four, and a decision model. Play Jev or watch Jev play itself. Picked by RadRebelSam
  1269. 1of 31 wadadanet/faq-jev-router Routing category → FAQ or not found (GitHub Pages demo). `★ 0` Picked by jtnkminimal
  1270. 1of 31 weirdstuff-dev/typesafe-ai-rust-sdk SDK & Runtime weirdstuff-dev/typesafe-ai-rust-sdk** - so you can jev in rust Picked by RadRebelSam
  1271. 1of 31 willfish/pi-observational-memory-jev Coding Agent willfish/pi-observational-memory-jev** - Jev decides what to keep. Compaction never rewrites the transcript. Picked by RadRebelSam
  1272. 1of 31 willkelly/jev-evaluation Eval & Align 9 adversarial experiments, 123,805 requests, $12.69: calibration ECE 0.075 in-domain but **fails OOD** (random 3-SAT); polite authority injection moves 147/200 answers; batching to 255… Picked by dog-last
  1273. 1of 31 win4r/jev-security-scan Coding Agent Review Agent Skills and MCP code with Jev, static evidence, and explicit coverage gaps Picked by RadRebelSam
  1274. 1of 31 wobsoriano/is-jeven Other Is it even? Ask Jev. `★ 0` Picked by jtnkminimal
  1275. 1of 31 wotai-dev/typesafe-jev-tools Coding Agent wotai-dev/typesafe-jev-tools** - A Claude Code hook that asks whether the decision you are writing needs a model at all. Includes a measured 149-row comparison of TypeSafe Jev against… Picked by RadRebelSam
  1276. 1of 31 wwwyo/jev-playground Other wwwyo/jev-playground** - Playground for TypeSafe AI's Jev: typed judgments (noul / choice / score) with probabilities Picked by RadRebelSam
  1277. 1of 31 xergioalex/jev-lab Routing AI decision trees, guardrails and routing with typed answers instead of text. Picked by rhc98
  1278. 1of 31 yangzhou-chaofan/awesome-jev-prompt Awesome List Latest top 100 showcases for jev (keep updating) from x / github / latest sources. Picked by JohnDotOwl
  1279. 1of 31 yannip1234/ask-jev Coding Agent Continuous AskJev CLI checks throughout Astra work, plus the standalone AskJev skill. `★ 0` Picked by jtnkminimal
  1280. 1of 31 yasu0903/jev-poc Other yasu0903/jev-poc** - No description provided. Picked by RadRebelSam
  1281. 1of 31 ygivenx/jev-try Other ygivenx/jev-try** - Reads a clinical note and nudges for the orders it commits to but the chart does not carry out. Built on TypeSafe jev typed judgments. Picked by RadRebelSam
  1282. 1of 31 yibie/pi-jev-browser Browser yibie/pi-jev-browser** - Isolated Playwright browser for pi, driven by Jev typed decisions through the TypeSafe API or the model pi already has configured. Picked by RadRebelSam
  1283. 1of 31 yinlu01/jev-testbench Browser browser-use/jev-ultrafast 之上的自托管测试工作台：浏览器 Agent 决策概率可视化 / 公告分拣 Speculative Fan-Out / 6 个实测应用案例集 Picked by RadRebelSam
  1284. 1of 31 yukitomoda/umigame-jev Other yukitomoda/umigame-jev** - No description provided. Picked by RadRebelSam
  1285. 1of 31 yunusey/typesafe-sdk-cpp SDK & Runtime yunusey/typesafe-sdk-cpp. Unofficial C++23 client for the TypeSafe AI API. 1 stars, C++, MIT License. Picked by walidboulanouar
  1286. 1of 31 yutkat/github-star-organizer-jev Other Applications (7):** jev.nvim, github-star-organizer-jev, jev, JevSysUno, jev-trader, newsscore, trading-bot-jev Picked by heyjunpenn
  1287. 1of 31 yzfly/edgejev Other 利益相关：**yzfly/edgejev** 是本清单维护者写的，刚发布，star 数还不够进 优质项目 那一栏。放在这里是因为它正好解决这一节的问题，数据都可以自己复现。 Picked by yzfly
  1288. 1of 31 zaferayan/jev-example Other zaferayan/jev-example** - No description provided. Picked by RadRebelSam
  1289. 1of 31 zampierid4p/n8n-nodes-typesafe Other n8n community node for asking typed questions inside workflows. Picked by MrJev
  1290. 1of 31 zbloss/jev-plays-pokemon Other Games & simulations (8):** jev-plays-pokemon-red, jev-royal, beat-jev, f1, jev-atari-lab, jev-plays-pokemon, JevArena, naimono-lab Picked by heyjunpenn
  1291. 1of 31 zbush/jev-context Coding Agent A Codex search plugin that filters ripgrep passages through Jev before returning relevant code. Picked by logicrw
  1292. 1of 31 zdenham/jev-lint Other zdenham/jev-lint** - Lint JavaScript and TypeScript against plain-English project conventions with Jev. Picked by RadRebelSam
  1293. 1of 31 zebedelu/sudoku-vs-jev Other Terminal Sudoku where Python owns the rules and Jev picks one move per turn, steady while forced moves exist and shaky once it has to guess. Picked by AnotiaWang
  1294. 1of 31 zephel01/Jev-sample Other The same decision asked as one 4-option Choice vs four precondition Nouls, with raw logs of 2,320 requests Picked by aliaihub
  1295. 1of 31 zerodegress/jevinf SDK & Runtime zerodegress/jevinf** - Jev-like model inference engine + Jev-compatible API Picked by RadRebelSam
  1296. 1of 31 zhuyansen/jev-issue-pulse Other Can a Jev-labelled GitHub issue stream catch a broken release before the fix? No at daily cadence (null, n=7). Per issue, Jev matches triage labels far… `★ 0` Picked by jtnkminimal
  1297. 1of 31 zhuyansen/jev-support-pulse Other Does a Jev-labelled support-tweet stream spike before a brand admits an outage? At equal false alarms it catches 17 vs 10 incidents (volume), ~4h ahead; a… `★ 0` Picked by jtnkminimal
  1298. 1of 31 zszz3/Pi-Jev-Guide Other Pi Jev Guard - Pi coding-agent plugin with rules configured by timing, plus risk checks, output redaction, and reminders on repeated failures. Chinese documentation. Picked by MrJev
  1299. 1of 31 zzsong1023/jev-market-reflex Other zzsong1023/jev-market-reflex** - Fast typed AI decisions on live crypto markets using TypeSafe AI Jev. Picked by RadRebelSam

Star counts appear for projects also tracked in the Top 100. Something missing? Submit it.

This page is other people's work

Everything above was hand-picked by the 31 curators below. This site only merges, counts and links — the judgement is theirs. If you maintain one of these, thank you; if you would rather not be included, say so and you will be removed.