← All projects
reflex
ursuciprian/reflex MIT JavaScript Coding Agent
rank#303
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.
- 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