Show HN: Stroq – a local audit of what your coding agent did and why

Category: security

Tags: ai-agents, security, audit, local-first, hooks

Score: 7.3/10 (Innovation: 7, Technical: 8, Documentation: 8, Utility: 6)

Stroq is a local security audit and guardrail tool for AI coding agents (Claude Code, Cursor, Codex, etc.) that analyzes session transcripts to trace which commands were influenced by text the agent read and whether secrets left the machine. It combines pre-execution hooks, provenance tracking, a local console, and replay/secret-scan commands, filling a real gap in agent security observability without telemetry or accounts.

Target audience: backend devs, devops, security engineers, AI agent users

Repository: https://github.com/AGGIB/Stroq · TypeScript · Apache-2.0 · 19 stars

View on Hacker News