microsoft/agent-governance-toolkit
AI Agent Governance Toolkit — Policy enforcement, zero-trust identity, execution sandboxing, and reliability engineering for autonomous AI agents. Covers 10/10 OWASP Agentic Top 10.
Provides multi-language SDKs (Python, TypeScript, .NET) with a modular architecture splitting policy enforcement (agent-os kernel), zero-trust identity (AgentMesh with SPIFFE/SVID support), sandboxing (4-tier privilege rings with saga orchestration), and SRE capabilities into separate installable packages. Integrates framework-agnostic at the action layer across 12+ stacks—LangChain, CrewAI, AutoGen, Azure AI, AWS Bedrock—via deterministic pre-execution policy evaluation (<0.1ms latency) backed by 9,500+ tests and NIST RFI alignment.
47 stars and 4,254 monthly downloads. Available on PyPI.
Stars
47
Forks
11
Language
Python
License
MIT
Category
Last pushed
Mar 13, 2026
Monthly downloads
4,254
Commits (30d)
0
Dependencies
2
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/agents/microsoft/agent-governance-toolkit"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Featured in
Related agents
ucsandman/DashClaw
🛡️Decision infrastructure for AI agents. Intercept actions, enforce guard policies, require...
mattijsmoens/sovereign-shield
AI security framework: tamper-proof action auditing, prompt injection firewall, ethical...
vstorm-co/pydantic-ai-middleware
Middleware layer for Pydantic AI — intercept, transform & guard agent calls with 7 lifecycle...
vstorm-co/pydantic-ai-shields
Guardrail capabilities for Pydantic AI — cost tracking, prompt injection detection, PII...
Pro-GenAI/Agent-Action-Guard
🛡️ Safe AI Agents through Action Classifier