{"repo":"open-agent-ai-security/praxen","free":true,"listed":false,"github":"https://github.com/open-agent-ai-security/praxen","clone":"git clone https://github.com/open-agent-ai-security/praxen.git","description":"Praxen — agent behavior verifier. Compares an AI agent's declared policy against the available evidence; reports where observed behavior diverges from declared intent.","language":"HTML","stars":59,"topics":["agent-security","ai-security","claude-code","owasp","raise-framework","agent-behavior-verifier","worker-remit","agent-scanner","llm-security","agent-sast"],"license":"Apache-2.0","category":"ai-agents","readme_excerpt":"Praxen agent behavior verifier ### Make sure your agent does its job — and only its job. That's where the risk actually lives: most agentic security and safety failures come down to an agent not doing its job — malfunctioning, misaligned, or adversarially subverted. Praxen is named for praxis (Ancient Greek πρᾶξις ), the act of turning theory into practice — which is exactly its job: verifying that an agent's declared intent (the theory) actually shows up in its observed behavior (the practice). --- 📦 Install — Praxen runs on Claude Code and OpenAI Codex (same skill, platform-specific packaging): - Claude Code: two short commands — claude plugin marketplace add open-agent-ai-security/plugins && claude plugin install praxen@open-agent-ai-security - OpenAI Codex: two short commands — codex plugin marketplace add open-agent-ai-security/plugins && codex plugin add praxen@open-agent-ai-security Full guide (including the no-marketplace path — just point any other agent at the repo): docs/installation.md. 👀 See a real report first — the live FinBot analysis report, rendered on GitHub Pages. --- Why behavior verification? Praxen is the open-source reference implementation of Agent Behavior Verification (ABV) — a proactive control model for AI agents and digital workers. The premise is the same one identity and access management applies to human employees: every actor has an authorized role, and the controls have to actually enforce it. And a misbehaving agent is hard to catch: what","default_branch":null,"files":null,"tree":[],"storefront":"/r/open-agent-ai-security","claimed":false,"request_supported":{"post":"https://gitbuyer.com/r/open-agent-ai-security/praxen/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."}