Alex Chernysh

bernstein

Last released Sep 20, 2026

The open-source governance layer for AI agents. No model in the coordination loop, so replaying a plan reproduces its task graph byte-identically, and run receipts are byte-identical across independent builds. Signed lineage plus an opt-in HMAC audit chain a reviewer checks offline, without rerunning it. Runs Claude Code, Codex, Gemini CLI, and 40+ CLI agents; governs any deliverable from code to research to audit evidence packs. Cluster mode, air-gap deploy.