Jev Users
← All projects

reflex

ursuciprian/reflex MIT JavaScript Coding Agent

rank#303
What it does

Pre-execution risk gate for AI coding agents (Claude Code, Codex, opencode, pi, Hermes). Blocks or asks on risky shell commands, guards against prompt injection in what agents read, escalates to System 2 and a human queue. Optional TypeSafe Jev.

Numbers
Stars
1
Forks
0
Open issues
2
Last push
today

Star history starts building from the first daily refresh.

agent-securityai-coding-agentsautonomous-agentsclaude-codeclaude-code-hookscodexcodex-clicommand-approvaldevsecopsguardrailshuman-in-the-loopjev

Open on GitHub → Homepage

More in Coding Agent