Every Jev app the community has catalogued

The Top 100 ranks by GitHub stars. This is the wider index: every project named by the community's 13 curated awesome-jev lists, ranked by how many of them agree it belongs. Small, useful tools that stars bury show up here.

1. 13x 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. 11.1k★
2. 13x 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… 284★
3. 12x 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. 396★
4. 12x RomanSlack/jev-drone in Top 100 Home & IoT Experimental MuJoCo quadrotor control loop with Jev in the decision path. 83★
5. 12x supercorp-ai/supercov in Top 100 Coding Agent Code quality and coverage for coding agents. 71★
6. 12x AboveColin/HA-Jev Other Expose `Noul`, `Choice`, and `Score` answers as automation entities and actions for household workflows.
7. 11x 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… 4.9k★
8. 11x fhshaik/typesafe-mario in Top 100 Other Uses structured emulator state and typed decisions for game control. 295★
9. 11x pithings/advocaat in Top 100 SDK & Runtime Data tooling: small type-safe client for asking Jev questions about a dataset. 85★
10. 11x shitianfang/jev-use 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…
11. 11x 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…
12. 10x 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. 1.5k★
13. 10x jkudish/jev-mcp in Top 100 Coding Agent Give coding agents typed claim verification, content screening, and semantic ranking tools. 147★
14. 10x 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. 142★
15. 10x itsmostafa/typesafe-mcp in Top 100 Coding Agent Go MCP server and CLI for exposing typed Jev decisions to coding agents and automation. 130★
16. 10x 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. 110★
17. 10x OmniJev/PlayJev Other 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.
18. 10x 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.
19. 10x aowang-ai/jev-trade Eval & Align 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…
20. 10x iammrduncan/typesafe-ai-benchmark Routing A benchmark project for TypeSafe-shaped decisions; record whether a run uses the official API, a gateway, or an adapter.
21. 10x phyous/tsai-sc Other Gaming: drives original StarCraft shareware through keyboard and mouse with Jev action probabilities recorded per decision.
22. 10x shiftynick/jev-axi Search Command-line primitives for picking, rating, checking, ranking, triaging, and guarding actions.
23. 10x typesafe-ai/skills Other Official agent skills repository
24. 10x typesafe-ai/typesafe-sdk-js SDK & Runtime See the official Python SDK, official JavaScript SDK, and Quick start for the supported client options.
25. 10x typesafe-ai/typesafe-sdk-python SDK & Runtime See the official Python SDK, official JavaScript SDK, and Quick start for the supported client options.
26. 10x 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.
27. 10x 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…
28. 10x 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.
29. 10x 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.
30. 10x yusukebe/hono-jev-router Routing Web frameworks: Hono middleware that routes HTTP requests by meaning rather than by method and path, deciding with Jev.
31. 9x 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. 1.1k★
32. 9x 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. 422★
33. 9x 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. 264★
34. 9x 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. 243★
35. 9x 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.
36. 9x Butochnikov/laravel-typesafe-jev Other PHP ecosystem: unofficial Laravel integration for Jev with typed responses, async requests, scoped dependency injection, and testing fakes.
37. 9x 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…
38. 9x awlevin/typesafe-computer-use Computer Use macOS computer-use experiment using OCR plus bounded Jev action selection.
39. 9x blakestone-x/jev-mcp 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.
40. 9x 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…
41. 9x dannote/jev SDK & Runtime (Elixir) - Elixir ecosystem: GenServer client that replies with Jev's answer so callers can pattern match on it directly.
42. 9x 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…
43. 9x kylemclaren/jevql Data Adds Jev `Noul`, `Choice`, and `Score` filters, probability sorts, and choice groups to semantic SQL over Postgres.
44. 9x leepokai/jev-guard Other Experimental tool-call risk scoring with explicit deny, ask, and allow outcomes.
45. 9x socai-io/jev-social 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…
46. 9x 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.
47. 9x 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…
48. 8x 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… 102★
49. 8x 0xNatoshi/jev-codex-router in Top 100 Computer Use Per-turn Codex model, reasoning, and speed-mode routing. 80★
50. 8x ChetasLua/jevmeter in Top 100 Other Scores every sentence in a video and renders the result as an overlay. 73★
51. 8x 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. 59★
52. 8x AkashPriyadarshii/jev-seo Coding Agent Zero-cost agent-first SEO and GEO search radar CLI and MCP server.
53. 8x Stumble/jev-go SDK & Runtime Go ecosystem: community Go SDK for Jev.
54. 8x anessbelbati/jev-rerank-bench Eval & Align Reranking comparison with raw provider responses, scoring code, dataset-level results, uncertainty intervals, and documented limitations.
55. 8x bitnovus/jev-spam-eval Eval & Align Spam filtering: zero-shot spam classification with Jev `Boolean` questions, benchmarked against TF-IDF baselines.
56. 8x ellipsis-dev/blink Awesome List Navigates file and directory names with Jev-guided walkers to find codebase paths for a natural-language query.
57. 8x jamesward/zio-typesafe-ai SDK & Runtime Scala ecosystem: ZIO client for TypeSafe AI with a typed DSL over Jev decisions.
58. 8x luantak/is-malicious Other Scans source, configuration, build, and CI files with Jev `Noul`, `Score`, and `Choice` questions; code-owned thresholds trigger a second pass and determine report severity.
59. 8x reachjalil/jevlogs Eval & Align Annotate OpenTelemetry/log records with Jev decisions and optionally skip expensive analysis for low-value traces.
60. 8x 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…
61. 7x 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. 1.3k★
62. 7x realZachi/pg-jev in Top 100 Data PostgreSQL extension for asking typed semantic questions over table data. 236★
63. 7x NiazMorshed2007/jev-review in Top 100 Coding Agent MCP plugin - Local-first continuous software-quality review for coding agents. 177★
64. 7x 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. 96★
65. 7x mrnugget/jev-shell-history in Top 100 Search Ranks existing zsh history entries for inline completion; accepting a suggestion does not execute it. 69★
66. 7x 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. 46★
67. 7x jexp/neo4jev in Top 100 Other Navigates a Neo4j graph one hop at a time, asking Jev which relationship to follow next. 45★
68. 7x 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. 44★
69. 7x 24601/Augustus 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…
70. 7x AbdelStark/typesafe-rs SDK & Runtime Latency-focused Rust transport SDK designed around behavioral parity with the official clients.
71. 7x AboveColin/jevclient SDK & Runtime Async Python client for typed Jev questions and probabilities.
72. 7x AkashPriyadarshii/jev-scout Coding Agent Open-source repository and crate scout powered by Jev scoring, with Rust, CLI, and MCP surfaces.
73. 7x 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…
74. 7x 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.
75. 7x 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.
76. 7x Twister915/typesafe-ai SDK & Runtime Rust client with asynchronous and blocking transports, typed responses, observable retries, and inspectable errors.
77. 7x brainstormity/Jev-Moderation-Bot 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…
78. 7x 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…
79. 7x kieranklaassen/ruby_llm-typesafe Other TypeSafe provider for RubyLLM 2 with offline model metadata and typed responses.
80. 7x nshkrdotcom/typesafe_sdk SDK & Runtime Elixir SDK for TypeSafe AI and Jev with typed Choice, Score, and Noul structs, configurable retries, and upstream API parity.
81. 7x reachjalil/jev-tree Routing Hierarchical decision-tree workflow for routing high-cardinality categories with Jev.
82. 7x zhihz/openjev SDK & Runtime Open research: independent local preview that answers bilingual probability questions from context, questions, and candidate answers, inspired by TypeSafe Jev.
83. 6x 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. 800★
84. 6x 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… 222★
85. 6x 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. 213★
86. 6x 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. 179★
87. 6x 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. 123★
88. 6x 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. 105★
89. 6x Dicklesworthstone/skillranker in Top 100 Coding Agent Rust CLI that ranks agent skills against live session context and can abstain. 87★
90. 6x giuliosmall/pg_typesafe in Top 100 Data Pre-alpha PostgreSQL C extension exposing Choice, Noul, Score, and batched judgments from SQL. 79★
91. 6x bnsd55/jevmlx in Top 100 SDK & Runtime Jev-style parallel decisions on MLX for local experimentation; compare semantics and calibration separately from hosted Jev. 44★
92. 6x AbdelStark/jev-benchmarks Eval & Align Useful for comparing decision quality and operational behavior; inspect the dataset and protocol before reusing a number.
93. 6x AkashPriyadarshii/jev-superpowers Other Agentic software-development framework upgraded with TypeSafe Jev typed decisions.
94. 6x FirasSX914/Janus Routing Measures calibration and confidence-based routing, with raw JSONL and figures committed for inspection.
95. 6x Gaurav-Gosain/jev-go SDK & Runtime A Go TypeSafe System One client with typed questions, answers and batching helpers.
96. 6x 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.
97. 6x Kevthetech143/super-jev Other Decision harness: turns a Jev answer into a bounded action instead of leaving the caller to interpret it.
98. 6x 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.
99. 6x compozy/yoshi Coding Agent Context management: proxy for Claude Code and Codex where Jev judges which conversation history is still needed before pruning.
100. 6x devanshbatham/commit-miner Other Classifies Git diffs and commit messages into change types and candidate security-fix/CWE labels for inspection.
101. 6x gilljon/typesafe-ai-rs SDK & Runtime An independently maintained Rust SDK with async and blocking clients, retries and response metadata.
102. 6x 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…
103. 6x 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.
104. 6x 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…
105. 6x legacybridge-tech/pi-typesafe-jev 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.
106. 6x 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.
107. 6x noplan-inc/limpet Other Coding agents: Stop hook that keeps an agent from finishing too early by judging plain-language completion rules with Jev.
108. 6x prismhq/jev-router Routing (prismhq) - LLM infrastructure: open-source LiteLLM-based router where a Jev decision picks which model serves each request.
109. 6x romaluev/jev-ego Browser A browser Agent for ego lite that numbers actionable elements for Jev to choose the next step.
110. 6x shantanugoel/ask-jev-skill Coding Agent A skill for Hermes and other agents to query TypeSafe Jev for bounded option judgments and confidence escalations.
111. 6x sharziki/semdecide Search Typed semantic decisions for Unix pipelines and CI.
112. 6x sorrycc/typesafe-snake Other Real-time game control: code generates legal moves and exact state facts, while Jev chooses one move per tick.
113. 6x sufianetaouil/every Search Semantic code search CLI that asks a yes/no question of every function and ranks the resulting probabilities.
114. 6x teyhouse/jev-secret-detection Eval & Align Benchmark and tool evaluating how well TypeSafe Jev identifies real secret credentials in file snippets.
115. 6x 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…
116. 6x 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.
117. 6x zhuyansen/jev-search-rerank-eval Search Chinese/English retrieval evaluation comparing Jev reranking with lexical, embedding, and fusion baselines, including judge-circularity analysis.
118. 5x 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. 2.3k★
119. 5x 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. 371★
120. 5x 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… 328★
121. 5x 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. 238★
122. 5x ekzhang/openjev-sglang in Top 100 SDK & Runtime Jev-inspired/open-model infrastructure; it is not the hosted TypeSafe Jev model. 213★
123. 5x 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. 167★
124. 5x 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. 146★
125. 5x 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. 78★
126. 5x 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. 44★
127. 5x 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.
128. 5x 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…
129. 5x AbdelStark/s1-rs Other Rust derive layer for Choice, Score, Noul, typed question sets, confidence gates, and network-free testing.
130. 5x AkashPriyadarshii/jev-git Other Rust pre-commit and pre-push gate that screens staged diffs for secrets and destructive commands using Jev Noul checks.
131. 5x Butochnikov/typesafe-sdk-php SDK & Runtime A community TypeSafe SDK for PHP 8.2+, with synchronous calls and Guzzle-based async requests.
132. 5x 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…
133. 5x 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…
134. 5x EugeneBoondock/jevsql Data SQL-like filtering, ranking, classification, and scoring with natural-language predicates.
135. 5x Gaurav-Gosain/jev-sec-bench Other Blind benchmarks for prompt injection and vulnerable-code detection.
136. 5x GhalebDweikat/winnow Coding Agent Judges tool results before admitting them into Claude Code context.
137. 5x GodsBoy/jev-agent-skill-router Coding Agent Agent infrastructure: routes agent skill selection through typed, confidence-aware Jev decisions so weak matches are declined instead of guessed.
138. 5x 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.
139. 5x Nyarlathoteppppp/pi-heed SDK & Runtime Runtime constraints: checks every side-effecting tool call from the Pi agent against what the user actually asked for.
140. 5x 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…
141. 5x TarunTomar122/jev-askable-arm Home & IoT Uses Jev to chain predefined skills for English-language goals in a ManiSkill robot-arm simulation.
142. 5x TheoOliveira/pi-jev Coding Agent (TheoOliveira) - Coding agents: semantic tool routing and typed System One decisions for the Pi coding agent.
143. 5x TokenTrim/jev-agent-failure-benchmark Eval & Align A benchmark using Jev to attribute multi-Agent failures to an Agent, step and error type.
144. 5x 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.
145. 5x ainame/swift-typesafe SDK & Runtime A community Swift TypeSafe client with typed questions, dynamic questions and response parsing.
146. 5x andrelandgraf/safer-with-jev Routing Cloud infrastructure: Neon Function proxy for the Neon AI Gateway that routes decisions with Jev.
147. 5x anpicasso/hermes-jev-approvals 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.
148. 5x 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…
149. 5x cephalization/jev-triage Other typeful-triage - Open-source maintenance: multiplayer triage dashboard where Jev answers a fixed set of typed questions per issue
150. 5x 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…
151. 5x 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…
152. 5x gamesonrblx/Jevbridge Other Agent integration bridge that makes Jev decisions available alongside coding-workflow tools.
153. 5x 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.
154. 5x harshil1712/slidepilot Other Experimental Slidev controller that judges speech transcripts for slide completion, with deterministic checks and manual navigation.
155. 5x ikermoel/open-alternative-jev Other Open alternative: runs a Jev-shaped decision model locally on your own GPU.
156. 5x 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…
157. 5x jomatsu/pi-jev-auto-mode Other Adds rule checks to Pi commands and file operations, then uses Jev to assess cases that need further judgment.
158. 5x kavehmz/typesafe-playground Computer Use Interactive playground: small Jev experiments that put the decision on screen, from routing a support message to steering a car in a 3D world.
159. 5x 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.
160. 5x lbotinelly/jev-little-airways Routing An island-airport simulator using Jev for routes, yielding, emergency broadcasts and landing order.
161. 5x 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.
162. 5x lukaske/jev-doom-agent Browser A browser Doom experiment comparing Jev-controlled players from the same initial state.
163. 5x 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…
164. 5x 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…
165. 5x 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.
166. 5x phyous/tsai-civ2 Browser An experimental harness where TypeSafe Jev plays classic Civilization II in a browser, computing live action probability distributions.
167. 5x 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…
168. 5x siroccomask/snake-jev SDK & Runtime Real-time Snake game driven by parallel Jev assessments, deciding optimal turns in a single API call per tick.
169. 5x tumf/jev-cli Other Developer tooling: small dependency-free CLI for Jev.
170. 5x 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.
171. 5x 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…
172. 4x OpenByteInc/QuantDinger in Top 100 Coding Agent 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… 11.8k★
173. 4x 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. 289★
174. 4x razorback16/openjev in Top 100 SDK & Runtime (DiffusionGemma) - Independent Jev-compatible server over DiffusionGemma/vLLM; the documented setup requires custom vLLM patches. 179★
175. 4x 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. 115★
176. 4x 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. 112★
177. 4x 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. 110★
178. 4x devagrawal09/stanley-code in Top 100 Other Coding agents: bounded Jev workflows that keep agent judgments typed instead of free-form. 96★
179. 4x 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… 64★
180. 4x 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. 45★
181. 4x AlbionaHoti/refgarden SDK & Runtime A visual-reference gallery drawing from The Met, NASA and Cosmos, with Jev in local Explore mode.
182. 4x AntonioCoppe/jev-harness Eval & Align Confidence gates, shadow mode, recipes, and evals; reports Claude CLI at 48.9 s against Jev at 1.3 s on the same row-filter job.
183. 4x Brainwires/jevwire Coding Agent MCP tools, an embeddable decision library, and advisory or restrictive Claude Code hooks; judgments do not grant native permissions.
184. 4x Dimweaker/jev-libero Other 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.
185. 4x 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…
186. 4x 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.
187. 4x Nasrallah-AL/jev-cli Other The jevctl command-line tool connects verification, classification and scoring questions to text input and scripts.
188. 4x 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.
189. 4x Tangerg/typesafe-sdk-go SDK & Runtime A Go TypeSafe SDK for defining typed questions and reading Jev choices, scores, and probabilities.
190. 4x anisselbd/jev-phishing-bench Eval & Align Jev against Claude Haiku on 2,000 phishing emails: accuracy, calibration, latency, cost.
191. 4x asfarsadewa/human-compiler Other Paste text, get diagnostics, like a compiler for prose.
192. 4x choxos/jev-reviewer Other Research-document extraction aid where Jev selects and verifies source lines for verbatim quotes; findings require human review and are not clinical decisions.
193. 4x 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.
194. 4x 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.
195. 4x hev/reranker Other A Python reranker that packs a query and up to 30 candidates into one Jev state, with one Noul relevance question per document.
196. 4x iamvatsalpatel/tiershift Routing Policy-bounded model routing for TypeScript and Python.
197. 4x inanna-malick/jev-dsl Other Early-alpha Haskell DSL that encodes typed question packets and decodes answers; HTTP transport is left to the caller.
198. 4x jomatsu/zod-jev Search Pairs local Zod shape validation with Jev semantic validation.
199. 4x keeltrace/hermes-jev Other An asynchronous Jev companion for Hermes Agent covering relevance, completion, recovery and optional admission decisions.
200. 4x keltokhy/jgrep Other Filters text, structured records, functions, and diff hunks against plain-English descriptions using Jev Noul judgments.
201. 4x kikoncuo/jevfire SDK & Runtime Parallel decisions for CUDA LLMs through a vLLM API, with game-agent examples and benchmarks.
202. 4x mahlernim/jev-korean-benchmark Eval & Align A language-specific benchmark candidate; treat results as workload evidence rather than a general multilingual guarantee.
203. 4x markjaquith/typesafe-ai-playground Other Rust CLI experiments for health-information screening, comment review, tone analysis and business or occupation classification.
204. 4x monteduro/killmyidea Eval & Align Startup-idea evaluator that chooses kill, fix, or ship.
205. 4x qkal/Canny Other Evidence ledger that challenges unsupported "done" claims from coding agents.
206. 4x r-ms/mini-jev SDK & Runtime Local reproduction: implements Jev's typed-decision interface on top of a local LLM.
207. 4x 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.
208. 4x saibimajdi/typesafeai-dotnet-sdk Eval & Align Community .NET SDK for TypeSafe AI and Jev, providing asynchronous typed evaluation for Choice, Score, and Noul primitives.
209. 4x samtay32/jev-system-architect Other Finds the fuzzy judgment in a system and turns it into small Choice, Score, and Noul primitives.
210. 4x santos-sanz/jev-audio-beeper Other Low-latency audio censorship proof of concept: Jev typed decisions drive ffmpeg.
211. 4x tacticocc/Jevbridge Coding Agent Agent bridges: ACP and MCP adapter that exposes Jev typed decisions to Codex, Claude, Grok, and other LLMs.
212. 4x tontoko/jev-browser Browser Playwright browser automation with Jev decisions through a shared CLI, MCP server and TypeScript SDK.
213. 4x wondertwins/jev-benchmark Eval & Align Benchmarks Jev on chess moves and identifying which game NPC a player addresses.
214. 4x zadescoxp/Jev-Trades SDK & Runtime A dashboard combining live crypto market data with Jev-guided paper trading; no broker or live-order API is connected.
215. 4x zhirschtritt/typesafe-go SDK & Runtime Idiomatic Go SDK for the TypeSafe API.
216. 3x 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. 444★
217. 3x notque/vexjoy-agent in Top 100 Coding Agent An optional Jev routing path that matches VexJoy requests to specialist Agents, skills and workflows. 421★
218. 3x 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. 218★
219. 3x 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. 151★
220. 3x 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. 124★
221. 3x 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. 83★
222. 3x 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… 81★
223. 3x 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. 54★
224. 3x 3clyp50/a0-typesafe-ai Other Typed tools and probability cards for Agent Zero.
225. 3x 4esv/jev-eval Eval & Align Independent Jev versus GPT-5.6 Terra comparison on three labeled classification tasks, reporting accuracy, calibration, latency, and cost.
226. 3x BYK/jev-mcp Coding Agent An eval-first MCP server for Jev, that returns typed judgments (noul, choice, score) with probabilities instead of generated text.
227. 3x Bud-ro/jev-demos Other Maze experiments comparing Jev single-step choices with multi-step lookahead.
228. 3x 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…
229. 3x DECRUX9812/typesafe-skill-router Coding Agent An opt-in Hermes Agent plugin that asks Jev to suggest one relevant skill before a model call.
230. 3x 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.
231. 3x Foadsf/jev-for-engineers Routing Eight mechanical and electrical engineering experiments using Jev for task routing, log checks and component selection.
232. 3x 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…
233. 3x 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…
234. 3x Heman10x-NGU/Verdict-open-jev Browser Non-autoregressive decision engine on ModernBERT with calibrated uncertainty and an in-browser WebGPU playground.
235. 3x JoshuaSP/open-jev Other Typed JSON inference with DiffusionGemma, benchmarked against Jev.
236. 3x MrJev/awesome-jev Awesome List selective list behind a 10-star bar, paired with hands-on reviews at mrjev.com that record what each tool sends and where.
237. 3x 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.
238. 3x PistachioAIHQ/jev-synergy-screening Other A Jev title-and-abstract screening experiment compared with Cohen Abstract Triage labels for an ADHD review.
239. 3x ShivamPansuriya/jev-skill-gate Coding Agent Ranks Claude Code skills for the current project to reduce the descriptions loaded by default.
240. 3x Skyvern-AI/jevscape Other RuneBench-based RuneScape harness that maps Jev choices to a bounded game-action catalog and records tick-level results.
241. 3x 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.
242. 3x TypeSafeAI/typesafe-playground Other Community playground for TypeSafe AI and Jev featuring 110 real-world scenarios, dilemmas, and interactive experiments.
243. 3x Vicente-MD/jev-resilience Other A Spring WebFlux integration that detects error messages hidden in HTTP 200 response bodies.
244. 3x 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.
245. 3x 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.
246. 3x 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.
247. 3x carldaws/hunch 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…
248. 3x chopratejas/invalidate Other Gives every stored agent memory a lease and asks Jev whether new evidence ends it; live demo.
249. 3x 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…
250. 3x 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…
251. 3x colliber/duckdb-jev Data DuckDB extension that exposes Jev judgments as SQL values with return types derived from the declared criteria.
252. 3x 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.
253. 3x devagrawal09/jev-code Other Helps coding Agents locate code, check change intent, triage test failures, and organize review findings.
254. 3x 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.
255. 3x docxology/daf-jev Coding Agent A Python toolkit for Jev requests, batch evaluation, calibration and MCP access.
256. 3x emrickgarrett/OneVOneJev Browser A browser-based 1v1 shooter where Jev reads structured match state and chooses movement, aim, and firing.
257. 3x fatwang2/jev-review-action Other A configurable GitHub Action that reviews catalog submissions or classifies PRs and updates a templated comment.
258. 3x fazlerocks/jevmail Other Read-only Gmail triage that stores messages locally and asks Jev for bounded category, urgency, and human-sender probabilities.
259. 3x 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…
260. 3x genai-craft/openvons Other Open decision layer for finite options across text, images, and Japanese voice commands.
261. 3x hamakyo/jev-starter Eval & Align TypeScript patterns for thresholds, fallbacks, human review and evaluation on top of the TypeSafe SDK.
262. 3x haseeb-heaven/jev-system-one Other A terminal Q&A app where OpenAI writes answers and Jev sets response policy and reviews drafts.
263. 3x 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…
264. 3x huntedman/JevLint Search Configurable semantic linting with file-level Noul judgments.
265. 3x 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…
266. 3x jmanhype/jev-dspy-lab Eval & Align Reproducible calibration and selective-risk benchmarks for Jev decisions in DSPy.
267. 3x joevidev/ui-generator-instinct-jev Other Turns UI descriptions into selections from existing shadcn/ui components, fields and styles.
268. 3x joshlarsen/jev-t-rex-runner Browser Chrome dinosaur game played by Jev.
269. 3x jtsang4/jev-cli Other A CLI for asking Jev classification, yes/no and scoring questions over text or JSON input.
270. 3x 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…
271. 3x 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.
272. 3x keltokhy/jselect Search Research and retrieval: selects source-linked evidence within a token budget using Jev Noul relevance judgments and local diversity-aware selection.
273. 3x keltokhy/jsort Search Text measurement: ranks text along a plain-English criterion using pairwise Jev Noul comparisons and a locally fitted Bradley-Terry scale.
274. 3x kevinpita/pi-jev-context Other Opt-in Pi extension that filters older messages from model requests while preserving the original session history.
275. 3x kitze/pagegrade Other Content quality: grades page sections for clarity, writing, and on-page SEO with Jev and returns per-section scores.
276. 3x maker-KK/todo-jev Coding Agent A task-routing experiment combining skill conditions and environment checks to suggest rules, skills or a large model.
277. 3x manifoldor/xtags Other Labels every post in your X timeline with what it wants you to do.
278. 3x matthewp/flue-jev-demo Routing Agent routing: routes a Flue agent's work with Jev through Cloudflare AI Gateway.
279. 3x mattn/sqlite3-jev Data SQLite C extension enabling TypeSafe Jev judgments as native SQL functions for semantic scoring and choices.
280. 3x 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.
281. 3x 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.
282. 3x myc0576/SmartMoney-Cub Other , Read-only trading journal and review harness with Jev judging entries against the evidence.
283. 3x noelzappy/tripwire Routing AI SDK middleware and proxy that runs seven Jev checks on every LLM response before the user sees it; no accuracy numbers yet, and it says so.
284. 3x phureewat29/jev-got Other A Game of Thrones text-adventure demo where a language model writes the story and Jev labels the scene.
285. 3x 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.
286. 3x 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…
287. 3x 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…
288. 3x 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…
289. 3x sosopop/jev_stock 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.
290. 3x 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…
291. 3x 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.
292. 3x unicodeveloper/jevocks 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.
293. 3x 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.
294. 3x vinilana/live-jev Browser A browser-based top-down driving simulator using Jev for lane and speed choices, with an optional chat-model comparison.
295. 3x y0usaf/typesafe-cli Other Noul, choice, and score answers as numbers from the shell.
296. 3x 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…
297. 3x 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…
298. 3x 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.
299. 2x 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… 2.8k★
300. 2x samuelfaj/distill in Top 100 Computer Use , Lightweight coding-agent harness and TUI that routes its small decisions through Jev. 678★
301. 2x 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. 616★
302. 2x 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). 194★
303. 2x lakeday-org/perch in Top 100 Coding Agent Semantic code linter that evaluates code units against configurable Jev questions. 162★
304. 2x 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. 155★
305. 2x 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. 67★
306. 2x 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. 59★
307. 2x 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. 46★
308. 2x 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. 45★
309. 2x EliaAlberti/jev-rules in Top 100 Other Scores your standing rules against each prompt and delivers only the ones that apply, once per session. 43★
310. 2x 0xPlaygrounds/rig Other Rust `rig-typesafeai` crate with typed Choice, Score, and Noul queries, response validation, examples, and fixtures.
311. 2x AshutoshVJTI/progressgate Search Detects semantic stagnation in agent loops: Jev judges the trajectory; code returns CONTINUE / WARN / REPLAN / HALT
312. 2x BerriAI/litellm Routing Jev-backed complexity routing and an optional relevance guardrail for compacting tool results before they return to an agent.
313. 2x BorisLeMeec/jev Coding Agent A Go Claude Code plugin using Jev to find files, answer bounded questions across code and handle large reads.
314. 2x Charlyhno-eng/jev-document-classification Other JEV Document Classification enables the rapid and cost-effective classification of text-based documents using AI, leveraging TypeSafe's "System One" model.
315. 2x 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.
316. 2x DanielKillenberger/jev-predict-skill Coding Agent An Agent skill recipe that predicts another skill’s closed-set outcome from its rules and evidence.
317. 2x DomMonte/n8n-nodes-typesafe-ai Other n8n community node for yes/no, choice, and score questions.
318. 2x HackSing/jev-report Other Independent Chinese research report: 52 pages, 50 reproducible tests, 143 traceable data rows.
319. 2x Icohen007/jev-play-ping-pong Browser Uses Jev to choose serve direction, return angle and pace in a browser table-tennis game.
320. 2x 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.
321. 2x Little-Planet-Labs/jev-playground Other A web playground for entering state and decision questions, then inspecting Jev answers and probability distributions.
322. 2x Nainish-Rai/jev-frontend-qa Browser Frontend QA that uses Jev to choose browser actions and checks contracts through DOM, HTTP and database evidence.
323. 2x 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…
324. 2x Query-farm/vgi-typesafe Data DuckDB worker that exposes choice, noul, and score as lateral-joinable table functions in SQL.
325. 2x 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.
326. 2x RiskAverseTech/toolgate Coding Agent a calibrated tool-call firewall powered by TypeSafe Jev. Ships as a Claude Code hook.
327. 2x RyanKung/rotom Routing Local gateways: OpenAI- and Anthropic-compatible API gateway that carries Jev through its model catalog and evaluation path.
328. 2x SamuelSacco/jev-exploration Eval & Align A research repository tracking Jev claims and limitations, with calibration experiments and runnable examples.
329. 2x 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.
330. 2x ShuhanSun/jev-oas-sentinel Search Catch breaking API behavior hidden in OpenAPI prose with deterministic checks and TypeSafe JEV System One semantic review.
331. 2x 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.
332. 2x 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.
333. 2x 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.
334. 2x XieChengYuan/jev-gomoku Other A nine-board, 15×15 Gomoku workbench comparing how two Jev players respond to different input representations.
335. 2x Zaious/jev-capability-atlas SDK & Runtime Jev Capability Atlas - Bilingual evidence map with recorded API runs and reusable suites that separates its own tests, third-party benchmarks, and editorial synthesis.
336. 2x aaronshaf/opencode-jev-orchestrator Coding Agent Keeps an OpenCode parent model fixed and uses Jev difficulty judgments to delegate harder turns to temporary subagents.
337. 2x 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.
338. 2x 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.
339. 2x adhyaay-karnwal/jev-chat Other A research chat decoder that repeatedly asks Jev to choose words or phrases and assembles them in code.
340. 2x agent-labs-dev/fastbrowse Browser Browser agents: Jev picks each action from what is on the page while an LLM reads and plans.
341. 2x agentgateway/agentgateway Other A Jev guardrail example in Agentgateway using a webhook to inspect model requests and responses.
342. 2x ajensenwaud/hermes-jev-plugin Routing Four Hermes tools for atomic checks, routing, and rubric scoring; listed in the Hermes plugin catalog.
343. 2x altryne/jevify Coding Agent An Agent Skill for finding suitable Jev decision points and designing questions and comparison experiments.
344. 2x 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.
345. 2x ax-llm/ax SDK & Runtime Native TypeSafe client and Ax provider for Boolean, Choice, Score, and raw Jev questions, with answer validation and examples.
346. 2x backmeupplz/jev_antispam_bot Other Minimal grammY Telegram anti-spam bot powered by TypeSafe Jev.
347. 2x baronunread/leanest Other Adds Jev-based selection before an existing test runner using diffs and test source.
348. 2x bestagentkits/jev-skillful Coding Agent Per-prompt router over skills, MCP servers, agents, and commands, and it measures whether the injection helped.
349. 2x buchmark/claude-jev Coding Agent Adds Jev checks to Claude Code review findings, debugging hypotheses, design options and search results.
350. 2x buluoray/JevOnly Other Pure Jev that can "type" and drive towards task completion.
351. 2x burnigtm/jev-mcp 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.
352. 2x 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.
353. 2x cocktailpeanut/jevthoven Other Symbolic-music studio where Jev chooses plans, instruments, and bar patterns, and code renders editable music and MIDI.
354. 2x codeitlikemiley/typesafe-sdk-rust SDK & Runtime A Rust client for TypeSafe with asynchronous and optional blocking calls plus typed question and answer wrappers.
355. 2x cole-gillespie/typesafe-go SDK & Runtime An unofficial Go SDK with typed answers, retries and context cancellation.
356. 2x dakdevs/decide-mcp Coding Agent MCP ecosystem: configurable decision server with percentage scores and bias-profile routing on top of Jev.
357. 2x 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.
358. 2x davila7/claude-code-templates Coding Agent A community Claude Code Templates mod that uses Jev to suggest subagent models and reasoning levels.
359. 2x 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.
360. 2x dzhng/duet-agent Routing Agent harness: keeps a Jev-backed routing table for deciding which model should serve a request.
361. 2x edgardcham/huncho Routing 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…
362. 2x fgn/jevgo SDK & Runtime A community Go client with a standard-library core and optional Langfuse tracing.
363. 2x guillemus/jev-go SDK & Runtime A small unofficial Go SDK for Jev calls and model listing.
364. 2x hellogumbo/should-ai-kill-us-all Other Asks Jev the question every ten minutes, using the actual headlines.
365. 2x himomohi/aside-jev Browser An MCP server and skill adding Jev decisions to Aside browser Agents.
366. 2x hqman/JevScout 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.
367. 2x ilkerulusoy/pi-jev-compact Coding Agent Selective, verbatim context compaction for Pi using Jev model.
368. 2x 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.
369. 2x 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.
370. 2x jcpsimmons/jev-macos-loop Computer Use A native macOS automation loop using local OCR and accessibility information with Jev action selection.
371. 2x jekozyra/pi-typesafe-router Routing Coding agents: routes Pi's work through typed Jev decisions.
372. 2x jerryfane/omp-jev-compaction Coding Agent An Oh My Pi extension that prunes tool history verbatim and reuses decisions to limit prefix rewrites.
373. 2x 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
374. 2x justinhe16/trade-jev Other Backtests Jev as a buy, sell, or hold trader on NQ order-book data.
375. 2x jvsteiner/jevex Coding Agent An Agent experiment where Jev directs a tool loop, a chat model fills arguments and prose, and MCP tools execute.
376. 2x 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.
377. 2x kevinbadi/jev-voice Computer Use Talk to your Mac. Local whisper.cpp + one Jev (TypeSafe) call per command + macOS automation.
378. 2x khordoo/jev-reflex-autonomy-lab Home & IoT Drone autonomy: a multi-drone lab where Jev supplies the reflex decisions, with an optional slower strategy layer guiding them.
379. 2x kubet/azdaja Other Bare, open-source RLM layer for existing coding agents
380. 2x 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.
381. 2x kunobi-ninja/kunobi-jev SDK & Runtime Rust client for the System One API.
382. 2x kxzk/typesafe-jev-drone-demo Home & IoT Simulation: Three.js drone simulator with a Python backend where Jev drives the navigation decisions.
383. 2x langchain-ai/langchain Routing Python `TypeSafeClassifier` Runnable with batched typed questions plus model-routing and risky-tool middleware.
384. 2x langchain-ai/langchainjs Routing LangChain.js - JavaScript/TypeScript classifier Runnable and middleware for bounded routing and tool-call checks.
385. 2x luxus/ha-conversation-jev Routing A Home Assistant conversation integration routing simple lighting commands to services and other requests to Grok.
386. 2x marandaneto/typesafe-sdk-swift SDK & Runtime Unofficial, experimental Swift client with typed answers, async/await, and Swift Package Manager support.
387. 2x mateonunez/jod Other Zod-style schemas over Jev: validate the state locally, then project typed answers.
388. 2x 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.
389. 2x mithalouni/system-one-open Eval & Align Typed calibrated decisions in one forward pass on Gemma 4 E2B and Gemma 3 270M.
390. 2x 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.
391. 2x 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.
392. 2x morcoan/JevSeek Routing Local coding workspace and agent decoupling tool routing via Jev from detailed argument generation via DeepSeek.
393. 2x n3ndor/n8n-nodes-typesafe-jev Other Community n8n node for asking multiple typed questions over workflow state.
394. 2x nekuda-ai/WindTunnel Browser Browser-agent benchmark: measures WebMCP against other browser-agent interfaces, with Jev appearing as one of the compared configurations.
395. 2x omni-/ask-jev Coding Agent A Windows PowerShell tool for auditing recorded Codex execution evidence with :jev.
396. 2x opaielsheikh/typesafe-migration-guard Data Reviews database migrations for safety before they run.
397. 2x pambrose/jev4k SDK & Runtime Kotlin DSL and client.
398. 2x parth-kp/jev-mail-classifier Other Classify your inbox with Jev (TypeSafe's System One model)
399. 2x paulsmith/computer-use-jev Computer Use A Go-based macOS controller that asks Jev to choose controls and actions from the accessibility tree.
400. 2x 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.
401. 2x pydantic/pydantic-ai Routing Pydantic AI - TypeSafe model provider that derives Jev questions from Pydantic output types and supports typed routing and fallback workflows.
402. 2x qddegtya/qualm SDK & Runtime A TypeScript wrapper for Jev decisions with an explicit unsure branch.
403. 2x raihankhan-rk/jevarena Browser Two Jev Agents play Snake in side-by-side browser panes with visible per-step choices.
404. 2x 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.
405. 2x rajivkuriakose/typesafe-jev-examples 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.
406. 2x 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.
407. 2x rashedInt32/jev-mcp Coding Agent An MCP server and Claude Code plugin for Jev classification, scoring, checks and batched questions.
408. 2x ryanwaits/secondlayer Other Fault triage: self-hosted Stacks data service whose Slack gate and fault-triage paths both run on Jev decisions.
409. 2x saibimajdi/typesafe-dotnet-sdk SDK & Runtime .NET SDK - Community client for typed questions and confidence-scored answers.
410. 2x scale-venture-partners/riff Other Ruff-style rule codes for writing.
411. 2x 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…
412. 2x shamazharikh/qwen-rlcd Eval & Align Jev-style calibrated decision model (Choice/Score/Noul) on Qwen3.5-0.8B.
413. 2x silverstein/minutes Eval & Align Meeting notes: local-first transcription app whose live voice path runs its evaluations through Jev.
414. 2x simota/tenbin Coding Agent Documentation, an MCP server and a Skill for designing Jev judgments with question linting, batch evaluation and calibration.
415. 2x smithersai/smithers Other Agent frameworks: TypeScript workflow framework with a Jev session checker wired into its workflows.
416. 2x sriganesh/jevibe-check Other Live tone labels for Bluesky posts and drafts.
417. 2x trycua/cua Browser ’s preview jev-use example pairs Driver observation and execution with bounded Jev browser-action choices.
418. 2x tyler-dot-earth/patdown Other Typesafe's jev as a "fuzzy linter". give your code an ocular patdown.
419. 2x 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…
420. 2x useopencompany/opencompany Other Agent workspace: runs its approval review through Jev so workspace actions are gated by a typed decision.
421. 2x utk2103/jev-studio Other If you're experimenting with jev it will be easier from here.
422. 2x vclic/smoking-extraction-benchmark Eval & Align Smoking-history extraction benchmark - 1,000 synthetic notes: Jev vs OpenAI structured outputs on accuracy, cost, and latency
423. 2x vercel-labs/ai-python Routing Python ecosystem: the official Vercel AI SDK for Python carries Jev through its evaluation operation and Gateway examples.
424. 2x 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.
425. 2x vinnie357/typesafe_sdk_ex SDK & Runtime Typesafe AI SDK in Elixir using Req
426. 2x vlad-terin/jev-browser Browser Jev Browser (Vlad Terin) - Agent skill + runtime: Codex plans, Jev selects elements, a runner acts and verifies each step.
427. 2x vmendes90/jev-shield Browser A Chrome ad-filtering extension that uses Jev to assess promotional intent in feed elements.
428. 2x win4r/jev-skill-suggester Coding Agent Coding agents: recommends which installed skills apply to a request, keeping the recommendation bounded and letting Jev decide.
429. 2x wundercorp/loki Routing optionally adds Jev typed-judgment tools and routes a new session to a model within the selected gateway.
430. 2x wustep/jev-playground Other by wustep - Can a System One model steer a music composition through typed classify, score, and pick decisions alone.
431. 2x y0usaf/jev-lm Other A word-level generation experiment that asks Jev to select words or verify locally drafted continuations.
432. 2x yikangy873-gif/jev-desktop 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.
433. 2x 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.
434. 1x 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. 573★
435. 1x wuyoscar/jev-skill in Top 100 Coding Agent An awesome collection of Jev use cases, workflows, and agent skills. 98★
436. 1x 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. 56★
437. 1x hyperspaceai/jevcache in Top 100 Other memoize decisions so repeats are free, deterministic, and shareable. One 2 MB binary. 48★
438. 1x 0x7067/jev-browse Browser (0x7067) - Browser automation with Jev (TypeSafe) as decision model.
439. 1x 0xArx/jevegis SDK & Runtime (site) - Guardrails for LLM apps in one API call. Prompt injection, jailbreaks, leaks, unsafe content. Built on TypeSafe Jev. MIT.
440. 1x 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.
441. 1x 0xtrou/rubikjev Other (site) - Challenge the Jev's intelligence in Rubik Cube puzzles.
442. 1x 1jehuang/jev-pr-labeler Search Semantic GitHub PR labels using Jev's typed decisions, with conceptual scope instead of line counts.
443. 1x 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.
444. 1x 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。
445. 1x 4anti/jev-broadcast-lab Other A Jev experiment workbench centered on chess, with additional classification and matching exercises.
446. 1x 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…
447. 1x AmoghCreator/doom-jev Other A ViZDoom Agent that uses Jev to choose movement, targets and firing from structured game state.
448. 1x Argos1111/jev_local SDK & Runtime Replicating Jev with a local LLM.
449. 1x 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.
450. 1x Bewinxed/jevgpt Other A chatbot built on a model that cannot generate text (TypeSafe AI's Jev, driven autoregressively).
451. 1x Biztactix/n8n-nodes-typesafe Other n8n community node for TypeSafe System One noul/choice/score questions over workflow text or JSON. Project guide.
452. 1x 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…
453. 1x CorieW/JevTest Browser (site) - Bounded exploratory browser testing with Jev, deterministic assertions, and replayable evidence.
454. 1x 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.
455. 1x DDnim/jev-tweet-radar Browser A Chrome extension that scores each X timeline post with one Jev Noul batch for engagement value and optional tags.
456. 1x DeepBlueDynamics/typesafe-arena Other A playground for TypeSafeAI's Jev Model.
457. 1x Devin-AXIS/jev-dsh-decision 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。
458. 1x 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…
459. 1x Dimesio/typesafe-chess Other (Dimesio) - FUn little experiment with Typesafe AI Jev Model playing chess against stockfish :).
460. 1x 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.
461. 1x 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.
462. 1x 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…
463. 1x 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.
464. 1x GPT-AGI/OpenJev Other (GPT-AGI) - Jev-compatible System 开源Jev.
465. 1x 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.
466. 1x 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.
467. 1x GhrezaKh74/JevTicktRouter Other A .NET 10 and React 19 application for fast, structured AI-powered ticket triage using TypeSafe Jev.
468. 1x Hardel-DW/jev.mods Routing Minecraft mod where Jev tries to finish the game from scratch without a scripted route.
469. 1x Hexdigest123/typesafe-comment Eval & Align Small Python package that uses typesafe.ai to evaluate code comments on certain heuristics.
470. 1x InsaneArts/typesafe-sdk-swift SDK & Runtime Swift SDK for TypeSafe AI.
471. 1x 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.
472. 1x JacobLinCool/jev-paper-judge Other (site) - Feedback on your paper in seconds.
473. 1x 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.
474. 1x JanOstrowka/typesafe-assist Home & IoT Home Assistant Assist conversation agent powered by TypeSafe's Jev (System One) model.
475. 1x JedimEmO/typesafe-client SDK & Runtime Unofficial typed async Rust client for the TypeSafe System One API.
476. 1x 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.
477. 1x KamilPostrozny/pi-fast-jev-compaction Coding Agent (KamilPostrozny) - Fast JEV compaction extension for pi.
478. 1x KamilPostrozny/pi-jev-code Search Single-agent Pi coding coprocessor with Jev semantic gates, baseline-to-current diff review, and append-only observability telemetry.
479. 1x 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.
480. 1x Kiln-AI/jev_jsonschema SDK & Runtime Run a JSON Schema through TypeSafe's Jev API, and get JSON back.
481. 1x 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.
482. 1x KyleKreuter/jev2048 Other Let Jev (TypeSafeAI) solve 2048.
483. 1x 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…
484. 1x MachineLearning-Nerd/jev-tetris Other A visual TypeSafe demo where Jev chooses verified Tetris placements.
485. 1x MahmoudAdelbghany/jev-browser Browser ~300ms decisions, no LLM tokens in the loop. Benchmark vs Playwright MCP included.
486. 1x 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…
487. 1x Menny1337/jev-lab Eval & Align TypeScript experiments, evaluations, and latency benchmarks for TypeSafe's Jev model.
488. 1x 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.
489. 1x MongLong0214/jev-gate Coding Agent Not every coding task needs your best model. Experimental Jev-powered model routing for Claude Code
490. 1x NSStudent/JevSwiftSDK SDK & Runtime An independent, type-safe Swift SDK for TypeSafe Jev, with async/await, batching, retries, and SPM support.
491. 1x NicolasMontone/jev-tool-permissions SDK & Runtime Adds tool-call approval and tool-list pruning to the Vercel AI SDK.
492. 1x Nolane-x/JEV-language Other (site) - Give your Jev language.
493. 1x NorbertBodziony/guard-jev Other (site) - Comment-moderation playground: paste a comment, Jev decides what to do with it.
494. 1x Nyarlathoteppppp/pi-jev-context Other —
495. 1x Olli0103/openclaw-typesafe-ai Other An independent OpenClaw plugin registering one explicitly invoked typesafe\_decide tool.
496. 1x Olti1947/jev-java SDK & Runtime Idiomatic Java SDK for TypeSafe AI Jev System One decision engine.
497. 1x OmniJev/awesome-jev Eval & Align OmniJev/awesome-jev - Papers, open reproductions, independent evaluations, and technical lineage.
498. 1x 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.
499. 1x PyModel/typesafe-mcp Coding Agent , MCP adapter that exposes Jev decisions as tools.
500. 1x 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.
501. 1x RubyBrewsday/jevcumber Other (site) - Write Cucumber tests with just the .feature file. No step definitions
502. 1x STRML/omp-jevens-classifier Other Jev-powered model-judged permission gate for OMP (TypeSafe System One).
503. 1x SergeAx/typesafe-sdk-go SDK & Runtime —
504. 1x Shifty-Eye-Games/foreman-jev Coding Agent An experimental Jev supervisor for Codex workers with programmer-selected acceptance commands.
505. 1x Solido/jev_dart SDK & Runtime Jev Dart SDK to build cli, server and Flutter apps.
506. 1x SoundBlaster/Jev4Mellea Other Jev adapter to Mellea.
507. 1x 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.
508. 1x TanayPadar/gpt-vs-jev Other (site, post) - Compare GPT generated language with JEV structured Noul decisions on the same input.
509. 1x 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…
510. 1x TheBous/jev-flash-review Coding Agent An MCP review engine that evaluates Agent-supplied diffs against explicit rules.
511. 1x 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.
512. 1x TholeG/typesafe-chess Other Chess where both players are TypeSafe's Jev model: every move is a typed Choice decision.
513. 1x TokenTrim/jev-routing-experiment Routing Benchmarking TypeSafe's Jev decision model as a cost-efficient LLM router on RouterArena.
514. 1x 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.
515. 1x TypeSafeAI/typesafe-ui Other (site) - Shadcn-style reusable components and blocks for using TypeSafe AI.
516. 1x Wang-auspicious/codex-jev-compaction Coding Agent Curates Codex handoff context by using Jev to select old tool records while retaining selected text verbatim.
517. 1x Wang-auspicious/pi-jev-compaction Coding Agent Extractive context compaction for Pi that keeps selected original tool records instead of generating a summary.
518. 1x Waxmell114514/jev-trade Other A simulated crypto trading loop that sends BTC and ETH market features to Jev and models execution costs and latency.
519. 1x 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.
520. 1x WebGrga/btc-jev-signal Other Experimental multi-horizon BTC signal generator using TypeSafe Jev probabilities and Binance market data.
521. 1x WebGrga/jev-board-lab Other Interactive explorer and Jev question workspace for Jev Board datasets.
522. 1x Wizhill05/typesafe-image-diffusion Other (post) - Diffusion-style pixel art out of a classifier: 256 parallel per-pixel Jev questions plus refinement passes.
523. 1x X0EF/jev_projects Awesome List (site) - List of projects that use typesafe's jev.
524. 1x Yasserbhb/Agent-JEV-Tetris Other Using the new model JEV to play the game tetris.
525. 1x 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…
526. 1x Zahrannnn/zcode-jev Other gates from PRD to ship. Jev-ready, provider-agnostic.
527. 1x 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.
528. 1x abeatrix/cline-plugin-jev-browser Browser A Cline plugin using an isolated Playwright browser and Jev decisions through Vercel AI Gateway.
529. 1x achimala/jev-paint Browser Jev Paint - Local browser app that turns batched per-pixel Jev distributions into paintings; prompts describe pixels and regions rather than sending raw images.
530. 1x adammichaelwood/jev-music-theory-1 Other Explores Jev on harmony exercises and music-theory questions, alongside a piano demo driven by chord choices.
531. 1x adtyavrdhn/pydantic-jev-examples Other Pydantic AI capabilities made stronger with Jev: small runnable demos, one file each.
532. 1x aliaihub/awesome-jev-usecases Awesome List (aliaihub) - Evidence-backed use cases, patterns, and guidance for building with Jev, TypeSafe AI's System One model. Every claim is labeled and sourced.
533. 1x amberwhitehead/jevscript Other An early language experiment whose current implementation is a Jev request-batching spike.
534. 1x 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…
535. 1x anandi1989/awesome-jev-usecases Search (site) - Evidence-backed index of real-world Jev (TypeSafe AI System One) use cases: repos, patterns, benchmarks, and measured results.
536. 1x andrelandgraf/typesafe-on-neon Routing Cloud: typesafe-on-neon - Neon Function proxy for the Neon AI Gateway.
537. 1x 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…
538. 1x anilsenay/jev SDK & Runtime Unofficial Go client for TypeSafe's System One API and its model, Jev.
539. 1x 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…
540. 1x 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.
541. 1x 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.
542. 1x ashaazami/river-run-typesafe Other River shooter game in Python, inspired by Atari's River Raid, played by a TypeSafe AI pilot.
543. 1x atarikcaliskan/jevball 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.
544. 1x atharvamhaske/typesafe-sdk-go SDK & Runtime (atharvamhaske) - Unofficial go sdk for typesafe ai.
545. 1x awun8191/jev-resume-analyzer Eval & Align CV diagnostics and job alignment with TypeSafe Jev, React and FastAPI.
546. 1x az9713/jev-model-router Routing (site) - Jev (TypeSafe) model router on the Vercel AI Gateway.
547. 1x 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…
548. 1x bestagentkits/typesafe-demo-mcp Coding Agent MCP server exposing TypeSafe System One judgments (noul, choice, score) as agent tools.
549. 1x binnash/typesafe-sdk SDK & Runtime (binnash) - PHP & Laravel SDK for TypeSafe AI's JEV Model series.
550. 1x 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.
551. 1x bojansandhaus/jev-decisions Other (site) - Safety checks for Hermes and other AI agents before they act, ask for approval, or verify a change.
552. 1x 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.
553. 1x brudarko/jev-mac-voice Computer Use English full-duplex voice control for macOS with OpenAI Realtime, native Accessibility, and Jev.
554. 1x ca7ai/jev-prompt-sentry Routing Anthropic Messages reverse proxy that screens jailbreaks/injections with one batched TypeSafe Jev call (PolyForm Noncommercial). Project guide.
555. 1x cablehead/jev.nu Eval & Align Nushell module for the TypeSafe System One API: typed decisions with calibrated probabilities.
556. 1x caiovicentino/jev-align Eval & Align Calibrated alignment verifier for LLM responses and agent plans
557. 1x cardotrejos/jev-ad-preflight Other Typesafe/Jev public X demo.
558. 1x cardotrejos/jev-should-i-apply Other Typesafe/Jev public X demo.
559. 1x cardotrejos/jev-user-jury Other Typesafe/Jev public X demo.
560. 1x carlsonchik/judging-with-typesafe Other Скилл для агентов Letta: суждения по критериям через TypeSafe System One (Jev).
561. 1x chenmingtang830/jevarena Other (chenmingtang830) (site) - Open-source BYOK arena for Jev and other AI judges. Find failures, compare quality, cost, and latency.
562. 1x chez-shanpu/typesafeai-go SDK & Runtime Go SDK for TypeSafe AI API
563. 1x choxos/jevchess Other (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.
564. 1x chris-wozniczek/jev-voice-control Computer Use Menu-bar Swift app turning spoken commands into Jev typed decisions and macOS actions.
565. 1x ckaraca/awesome-jev Awesome List (ckaraca) - A curated list of tools, integrations, and experiments built on Jev, TypeSafe AI's System One model for fast, typed decisions.
566. 1x cobusgreyling/Jev Other Unofficial TypeSafe Jev showcase
567. 1x colinmcdermott/emoji-jev Other Emoji autocomplete at the speed of typing. TypeSafe AI Jev on a Whop-hosted TanStack Start app.
568. 1x 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.
569. 1x collapseindex/jev-ultralightspeed Other (site) - BRRRRRRRRRRRRRRRRRRRRRR.
570. 1x 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…
571. 1x 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.
572. 1x danielgshea/jev-as-a-judge Eval & Align Using Jev as an evaluator.
573. 1x danvega/jev-spring-boot-starter Other A simple Spring Boot 4 starter for TypeSafe Jev using Spring MVC and RestClient.
574. 1x 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…
575. 1x 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.
576. 1x dougsong/jev-android Mobile Kotlin Android UI-agent SDK: TypeSafe Jev or DeepSeek selects accessibility actions; local Maven sample (not on Maven Central). Project guide.
577. 1x 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…
578. 1x 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.
579. 1x erendikmenn/jev-rag-benchmark Search Reproducible benchmark for measuring Jev reranking quality, latency, and cost in RAG.
580. 1x erhanmeydan/jev2048 Other (erhanmeydan) - TypeSafe'in Jev karar modeli gerçek bir online 2048 sitesinde oynuyor
581. 1x ethanplusai/jev-chat-for-twitch Other —
582. 1x everyinfra/jev-radar Other The world's most comprehensive tracker of the Jev (TypeSafe AI System One) ecosystem
583. 1x felpsdev/jev-classifier Coding Agent A local Jev tool-routing gateway for coding Agents, with an MCP suggestion interface.
584. 1x florian-hoenicke/jev-gpt Other Cascaded Choice questions that make Jev pick the next word from a word tree instead of generating text.
585. 1x fstandhartinger/jevbench Eval & Align JevBench v1 - a benchmark for Jev-class typed decision models: smart, cheap, fast, reliable, open.
586. 1x geilt/typesafe-cli Coding Agent (geilt) - CLI and agent skill for TypeSafe System One (Jev): typed Choice, Score, and Noul judgments.
587. 1x goodrahstar/jev-column-race Other (site) - Jev vs Gemini 3.8 Flash: labelling 1,000 app reviews, 4.1× faster and 7× cheaper.
588. 1x 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.
589. 1x 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.
590. 1x 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.
591. 1x gudcks0305/jev-java Routing (gudcks0305) - Unofficial Java SDK for TypeSafe Jev and Vercel AI Gateway, with Spring Boot and WebClient support.
592. 1x 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…
593. 1x heiwa4126/jev-bun1 SDK & Runtime TypeSafe の Jev を TypeScript SDK で使ってみる最初の 1 歩.
594. 1x hemanth/jev-chess Eval & Align (site) - Chess moves, evaluations, persona opponents, and game classification with TypeSafe AI System One.
595. 1x heyjunpenn/awesome-jev Awesome List (heyjunpenn) (site) - A verified, community-maintained catalog of 485 open-source projects built with Jev.
596. 1x hfiguera/typesafe_ai SDK & Runtime (hfiguera) - A supervised Mint client for the TypeSafe AI System One API.
597. 1x hifizz/jev-finance-benchmark Eval & Align Typesafe.ai model jev finance benchmark.
598. 1x hnegishi/typesafe-ai-ruby SDK & Runtime A stdlib-only Ruby client that sends Choice, Score, or Noul questions to TypeSafe System One.
599. 1x hugo-alves/jev-router-playground Routing A model-routing playground where Jev picks a candidate and users compare the resulting answers.
600. 1x i2cjak/RISC-jeV Other I tortured Jev into being a RISC-V CPU.
601. 1x 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.
602. 1x ibrahemid/git-jev-stage Other Select Git changes for staging with a plain-language description.
603. 1x ibrahemid/jevprune Other Filter command output for coding agents using a task description.
604. 1x iefnaf/pi-jev Coding Agent (iefnaf) - Pi extension suite powered by Jev: selective context compaction and model routing.
605. 1x 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.
606. 1x imMamdouhaboammar/fable-jev Other ⚡ Sub-100ms cognitive reflexes for autonomous coding agents. Powered by TypeSafe AI's Jev & get-fable.
607. 1x ishantanu/jevmetrics Other Experimental OpenTelemetry Collector metrics processor: TypeSafe Jev assesses instrument metadata for retention; deterministic keep/reduce policy with caching (alpha). Project guide.
608. 1x 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.
609. 1x jaibhasin/jev-yt-time-saver Browser A Chrome extension that covers distracting YouTube videos with Jev. Show anyway whenever you want.
610. 1x jammaru/jev-lab Other hundred - 100 AI NPCs live in a tiny town. Jev chooses the next action; the world writes the story.
611. 1x jeffloo886/jev-notion Computer Use 🚀 Blazing-fast native macOS menu bar companion for Notion. Pure Swift & SwiftUI (<3MB), 8 languages.
612. 1x jeiel85/jevscope SDK & Runtime Local-first visual workbench and JSONL regression testbench for TypeSafe Jev projects. Project guide.
613. 1x jevbook/jevscan Coding Agent An EVM Token screening tool with library, CLI and MCP interfaces for market-feature-based risk judgments.
614. 1x 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…
615. 1x jon-devlapaz/jev-me Other A grill-me style interrogation of your idea, with Jev doing the grilling.
616. 1x 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.
617. 1x 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.
618. 1x jujumilk3/jev-calibration-audit Eval & Align Audits Jev calibration, option-wording effects and Korean judgments through public APIs and datasets.
619. 1x kesku/jev-freeform Other An observable raw-character chat experiment powered entirely by TypeSafe Jev Choice.
620. 1x 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.
621. 1x 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.
622. 1x krzyzanowskim/TypeSafe Eval & Align (Swift) - SwiftPM client for TypeSafe System One Noul/Choice/Score questions, aligned with the official JS SDK shape. Project guide.
623. 1x kt3k/jevchat Other A chat-style Jev demo whose answers are selected from predefined or custom options rather than generated prose.
624. 1x 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.
625. 1x kyrylosyzonenko/jev-browse Browser Drives a real browser with Jev making every decision and Vercel's agent-browser performing every action, with a benchmark.
626. 1x 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.
627. 1x 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.
628. 1x lambertsj/beatjev Browser (site, post) - Browser game: try to beat Jev at spotting a spam message.
629. 1x larguesa/jev-search Search (larguesa) - Experimental semantic line search with TypeSafe Jev via OpenRouter. Python CLI with no runtime dependencies.
630. 1x lavallee/mk-jev-fly-brain Other Compares a fly-connectome spiking simulation, Jev and rule policies in the mk.js fighting game.
631. 1x leftspace89/JevBird Routing A Python Flappy Bird game where code simulates candidate routes and Jev picks one.
632. 1x logicrw/ask-jev Other Ultra-fast, fail-open advisory decisions and verbatim extractive reading view for AI coding agents and CLI pipelines
633. 1x 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.
634. 1x maddygoround/typesafeai-cli Computer Use Python `typesafe` CLI for TypeSafe Jev ask/decide/screen/verify flows for humans and agents. Project guide.
635. 1x madeye/pi-jev Search Jev-assisted file retrieval and request caching for faster Pi workflows.
636. 1x malDuffin/typesafe-3d-chess Other 3D chess powered by TypeSafe AI (Jev). AI vs AI by default, or play either side. Multiple difficulty levels.
637. 1x 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.
638. 1x mattneel/typesafe SDK & Runtime An idiomatic Elixir client for the TypeSafe AI API.
639. 1x mattneel/typesafe.zig SDK & Runtime An idiomatic Zig client for the TypeSafe AI API.
640. 1x minghanminghan/jev-demo Routing A customer-service routing demo that batches Jev questions before following the resulting route.
641. 1x 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…
642. 1x 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.
643. 1x mittal-parth/jev-experiments Browser Uses Jev to play Chrome Dino and a local shooter arena while Python executes structured decisions.
644. 1x mizchi/jev-lint Search Ast-grep + TypeSafe Jev natural-language semantic linter (name/body drift, stale comments, weak tests); distinct from huntedman/JevLint. Project guide.
645. 1x mizchi/jev-playground Other A MoonBit and TypeScript Jev playground covering games, browsers, command risk and small languages.
646. 1x mizzlelover/jev-hub Other X 上关于 TypeSafe AI「系统一模型」Jev 的长文与演示视频聚合（保留原链与作者）｜ 谁是专家 出品.
647. 1x mkotlikov/jev-grug Other Helping JEV speak <3.
648. 1x 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.
649. 1x 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.
650. 1x muhammedilyasy/jev-mail Browser Chrome extension that triages Gmail with TypeSafe's Jev model: category, priority, spam % and reply % on every email.
651. 1x 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.
652. 1x myokoym/misereru-slide-jev Other (site) - Ongoing Japanese research deck on Jev and System One models, maintained as Markdown slides.
653. 1x 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.
654. 1x 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）.
655. 1x narulaskaran/jev-data-questions Other Jev Gamecast (site) - Jev Gamecast: replay-first React app that asks Jev typed questions about live sports data.
656. 1x ndolinschi/jevplay Other custom Choice/Score/Noul builder with live distributions.
657. 1x neddes/sloppy-jevs-extension Browser Open-source Chrome extension that filters AI-generated prose and ads with Jev.
658. 1x 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…
659. 1x 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.
660. 1x 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.
661. 1x okinaaudio/live-jev Computer Use `BYOK`. Early macOS Ableton Live controller: hotkey bar + TypeSafe Jev picks typed mixer/device actions from short EN/JP phrases. Project guide.
662. 1x omkarghugarkar007/actiongate-jev SDK & Runtime Runtime authorization and guardrails for AI-agent tool calls with deterministic policy and TypeSafe Jev via OpenRouter.
663. 1x openroboto-ai/jev-robot-control 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.
664. 1x ozers/jevsome-projects Awesome List A Jev project directory and discovery pipeline that stores integration evidence and can use Jev for classification.
665. 1x phd-peter/ego-jev Browser Connects Ego Lite snapshots and browser actions to a bounded Jev decision loop.
666. 1x philippdubach/pi-jev-router Routing Pi extension: TypeSafe Jev classifies tasks and local policy routes OpenRouter models (Pareto profiles; shadow mode default). Project guide.
667. 1x poponline63/hermes-jev-north-star Coding Agent A Hermes goal-checking skill that saves requirements, creates a run prompt and checks completion evidence.
668. 1x rainbowpuffpuff/jev-builder-loop Coding Agent Grok skill: Jev as a judgment sensor in a builder-agent loop (priors × probabilities → next act).
669. 1x rbalch/typesafeai-review Other Using Typesafe.AI to generate diff reviews.
670. 1x 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.
671. 1x 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.
672. 1x rhighs/jev-code Other An experimental coding CLI where Jev selects AST productions for Python or Bash, with a separate command-line decision mode.
673. 1x safzanpirani/pong-jev Other TypeSafe's Jev plays Atari Pong. One typed Choice question per frame, no coordinates sent to the model.
674. 1x samdotmak/jev-recall Search Retrieve by relevance, not resemblance: filter an AI assistant's memories with TypeSafe's Jev.
675. 1x 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…
676. 1x shantanugoel/jev-games Other Visual Jev lab for multiple games and emulator platforms.
677. 1x shantanugoel/mario-jev Other Python prototype that plays NES Super Mario Bros. from structured RAM observations, with Jev answering focused movement and jump questions.
678. 1x sherajdev/jev-research Routing A Jev and Herdr integration guide with a prototype for routing tasks to different Agents.
679. 1x 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.
680. 1x siddicky/omp-typesafe Coding Agent TypeSafe AI (Jev) adversarial reviewer and typesafe_ask tool for the omp coding agent.
681. 1x sightmap/jev-turbo Browser turbo - Jev-powered semantic browser use.
682. 1x simxnherrera/jevr SDK & Runtime Native R client for typed questions and provider-independent answers through TypeSafe or OpenRouter.
683. 1x skeptrunedev/jev-recruiter Other A Jev powered LinkedIn recruiting agent. Watch it browse relevant profiles, save links, and review evidence against your hiring brief.
684. 1x 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.
685. 1x soderlind/ai-provider-for-jev Other Connect WordPress to TypeSafe's Jev System One model for structured decisions (choice, score, noul).
686. 1x 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.
687. 1x 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.
688. 1x teempai/jev-in-codex Coding Agent Codex MCP tools for TypeSafe Jev-ranked capability selection, workspace search, and output triage (experimental MVP). Project guide.
689. 1x terryds/jevplayground Browser (site) - Browser-only playground for Jev (TypeSafe AI's decision model) via Vercel AI Gateway.
690. 1x thelau/jev-tetris Other —
691. 1x 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.
692. 1x thesammykins/jev_ampcode Other An Amp plugin for comparing supplied alternatives against supplied evidence and priorities.
693. 1x thiago-ss/jev-review Eval & Align (thiago-ss) - Autonomous Jev pull-request review with typed decisions, calibrated approval gates, and trusted-owner escalation.
694. 1x 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.
695. 1x 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).
696. 1x ticofab/scala-jev-sdk SDK & Runtime —
697. 1x tinyhumansai/tinyjevclient Other An integration with jev by typesafe.ai in Rust.
698. 1x 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.
699. 1x trophee-bot/typesafe-oracles Eval & Align Evaluating TypeSafe's System One primitives (Choice/Score/Noul)
700. 1x trungdq88/jev-tetris Other (trungdq88) (site) - Jev play Tetris in real-time against other AI models.
701. 1x tryaksh/jev-pick-and-place-study Other A small reproducible MuJoCo pilot comparing Jev, Claude Haiku, and reactive rules for pick-and-place.
702. 1x twilwa/pi-typesafe SDK & Runtime Pi coding-agent extension built on the TypeSafe AI System One API (Jev).
703. 1x tylerjharden/harden-jev-decides Other JEV picks which stream idea becomes the live MVP. TypeSafe System One decision board.
704. 1x 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.
705. 1x typesafeainate/dspy-typesafeify Routing , Decorator that routes DSPy typed Signatures to Jev where the signature is a pure decision.
706. 1x typesend/typesafe_ai SDK & Runtime (typesend) (site) - Unofficial Elixir SDK for the TypeSafe AI API.
707. 1x ufec/typesafe-sdk-kotlin SDK & Runtime —
708. 1x unownone/jevsume Other A resume-review app that checks general writing and structure or compares a resume with a specific job description.
709. 1x ussyverse/hermes-jev-router Routing Experimental Hermes plugin: Jev-assisted model routing plans with budget and capability constraints. API access pending.
710. 1x valksor/typesafe-sdk-go SDK & Runtime 1:1 parity with the official JS and Python SDKs. Not affiliated with TypeSafe AI.
711. 1x valksor/typesafe-sdk-php SDK & Runtime 1:1 parity with the official JS and Python SDKs. Not affiliated with TypeSafe AI.
712. 1x vehas/thaiexam-jev-charts Eval & Align Charts: TypeSafe Jev evaluated on Thai standardized exams vs 110 other models.
713. 1x 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.
714. 1x vinilana/jev-browser Browser (vinilana) - Hybrid browser harness: an LLM turns goals into verifiable subgoals, Jev chooses each action and DOM field, Playwright acts.
715. 1x 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…
716. 1x yzfly/awesome-jev-zh Awesome List (site) - Jev / TypeSafe System One 中文精选列表：官方资料、SDK、爆款应用、Agent 工具、开源复现与独立评测，附中文上手指南，每日自动收录 GitHub 热门项目。
717. 1x zbush/jev-context Coding Agent A Codex search plugin that filters ripgrep passages through Jev before returning relevant code.
718. 1x 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.
719. 1x zefir1990/openjev-experiments SDK & Runtime (site) - Experiments with openjev, an open Jev-style option-logit runner, on local models.
720. 1x zhangxaochen/dsh-jev Other Jev (System One decision model) plugin suite for DeepSeek Harness (dsh).

The count on the left is how many independent lists include that project. Star counts appear for projects also tracked in the Top 100. Something missing? Submit it.