praxen

Praxen — agent behavior verifier. Compares an AI agent's declared policy against the available evidence; reports where observed behavior diverges from declared intent.

open-agent-ai-security/praxen

View on GitHub ↗

Praxen — agent behavior verifier. Compares an AI agent's declared policy against the available evidence; reports where observed behavior diverges from declared intent.

praxen grew +6.6% in the last 30 days, ranks 796th of 872 in Evaluation & Guardrails, actively maintained, last commit today.

Star trajectory

80 days tracked
2026-09-0265 stars today2026-11-22
Momentum

+6.6% in 30d, above the Evaluation & Guardrails median of +1.4%.

Maintenance

Last commit today, fresher than the median of 15d.

How it compares in Evaluation & Guardrails

praxen
65
stars
+6.6% 30d
commit today
Evaluation & Guardrails median
235
stars
+1.4% 30d
commit ~15d ago
Leader · impeccable
114.7k
stars
+0.0% 30d
commit today

Ranked 796th of 872 by stars.

Ranked by shared tags, then keywords, then stars
  1. Adversarial AI bug hunter with auto-fix skill for Claude Code, Cursor, Codex CLI, GitHub Copilot CLI, Kiro…

    +44 (+8.3%) in 30d · Committed 23d ago · JavaScript · MIT

    Shares Agent SDK / Framework, Evaluation & Guardrails

  2. WCAG 2.2 AA accessibility review for AI coding tools: Agent Skills, an edit gate and accessibility scanners…

    +25 (+5.8%) in 30d · Committed 5d ago · JavaScript · MIT

    Shares Agent SDK / Framework, Evaluation & Guardrails

  3. Security operations toolkit for AI coding agents. Give Claude Code 25+ skills to catch vulnerabilities, scan…

    +13 (+5.8%) in 30d · Committed 220d ago · Python · Other license

    Shares Agent SDK / Framework, Evaluation & Guardrails

  4. SAIL V2 (Secure AI Lifecycle) as an agent skill — the full 91-risk catalog for AI/agent gap assessments…

    -5 (-4.5%) in 30d · Committed 137d ago · Other license

    Shares Evaluation & Guardrails, Agent SDK / Framework

  5. Observability and enforcement for AI agent harnesses. Capture every run and runtime reliability with policy…

    +4k (+67%) in 30d · Committed today · TypeScript · Other license

    Shares Agent SDK / Framework, Evaluation & Guardrails

  6. Multi-tier framework for evaluating AI agent skills and plugins with quality gates, security scanning, harness…

    +3.8k (+634%) in 30d · Committed today · Python · Apache-2.0

    Shares Evaluation & Guardrails, Agent SDK / Framework

  7. Sandbox your local AI agents so they can read/write only what they need

    +36 (+1.7%) in 30d · Committed today · Shell · Apache-2.0

    Shares Evaluation & Guardrails, Agent SDK / Framework

  8. Red-teaming and evaluation framework for AI agents, built around an OWASP-inspired ASI01–ASI10 taxonomy

    -196 (-22%) in 30d · Committed 15d ago · Python · Apache-2.0

    Shares Evaluation & Guardrails, Agent SDK / Framework

  9. Claude Code plugin for Elixir/Phoenix/LiveView — 26 specialist agents, Iron Laws enforcement, and Tidewave MCP…

    +8 (+1.4%) in 30d · Committed yesterday · Python · MIT

    Shares Agent SDK / Framework, Evaluation & Guardrails

  10. SlowMist Agent Security Skill: A comprehensive security review framework for AI agents operating in…

    +51 (+10%) in 30d · Committed 219d ago · MIT

    Shares Evaluation & Guardrails, Agent SDK / Framework

Language
HTML
License
Apache License 2.0
Contributors
8
Forks
10
Watchers
0
Open issues
39
Releases
18
Created
2026-05-20
Stars this week
+1

You've seen where praxen stands today.

Get the moves before everyone else: the 5 Evaluation & Guardrails repos climbing fastest, every Tuesday.

Free weekly digest. Double opt-in, unsubscribe anytime.

Maintain praxen?

Claim this page to add your own call-to-action.

Claim this page