{"repo":"permit0-ai/permit0","free":true,"listed":false,"github":"https://github.com/permit0-ai/permit0","clone":"git clone https://github.com/permit0-ai/permit0.git","description":"Stop AI agents from doing things they shouldn't. The action authorization layer — pre-execution, deterministic, policies included. Drop in. Day one.","language":"Rust","stars":186,"topics":["agent-authorization","ai-agents","ai-safety","audit-trail","compliance","eu-ai-act","mcp","policy-engine","rust","ai-governance"],"license":"Apache-2.0","category":"ai-agents","readme_excerpt":"Permit0 The policy engine for AI agent actions. The boundary between what your agent decides and what it's allowed to do. action taxonomy · default risk policies · deterministic · pre-execution · auditable. Permit0 integrates with Claude Code and OpenClaw — more integrations to come. The pilot email taxonomy is ready, with Outlook and Gmail packs. Open an issue to request the next taxonomy domain or tool pack → and ⭐ star the project. --- Use this if... Your AI agent — one you built, or one you use every day — can send email, touch a database, move money, or execute code. You've watched it do something in testing that shouldn't have happened. Or you've held it back from real work because there's no hard permission you set that actually gets enforced. Permit0 is the boundary between what the LLM decides and what actually runs. Every tool call is normalized into a canonical action, scored deterministically against risk dimensions, and decided against a policy in sub-millisecond time — with a signed audit trail an auditor can verify. The vocabulary is published. The first pack is shipped. The rest is the work. ▶ Watch the 3-minute demo → — three real attack patterns: APP fraud, card testing, insider exfiltration. --- Try it — Claude Code + Outlook/Gmail in 5 minutes On OpenClaw? Skip to integrations/permit0-openclaw/ — wrap a skill with permit0Skill(...) and gate every dispatch through the same daemon. The rest of this section is the Claude Code path. Docker brings up everything","default_branch":null,"files":null,"tree":[],"storefront":"/r/permit0-ai","claimed":false,"request_supported":{"post":"https://gitbuyer.com/r/permit0-ai/permit0/request-supported","requests":0},"note":"indexed from public GitHub; nothing is for sale on this page. Clone it from GitHub. Paid listings live at /search."}