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.

55
/ 100
Established

This toolkit helps organizations manage the risks of deploying AI agents by enforcing security policies and controlling what agents can do, not just what they say. It takes in information about your AI agents and their intended actions, and outputs a secure, controlled execution environment. This is for AI solution architects, security engineers, and compliance officers who deploy and manage AI agents in production.

Available on PyPI.

Use this if you are developing or deploying AI agents and need to ensure they operate securely, comply with policies, and can't take unauthorized or dangerous actions.

Not ideal if your primary concern is filtering the content of what an AI model says or does, rather than governing the actions and resources that an AI agent can access.

AI governance Agent security Risk management Compliance Application security
Maintenance 10 / 25
Adoption 8 / 25
Maturity 20 / 25
Community 17 / 25

How are scores calculated?

Stars

47

Forks

11

Language

Python

License

MIT

Last pushed

Mar 13, 2026

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.