microsoft/

agent-governance-toolkit

GitHub

AI Agent Governance Toolkit provides policy enforcement, zero-trust identity, execution sandboxing, and SRE capabilities for autonomous AI agents. It distributes via Python and multi-language SDKs, with a consolidated v4.1.0 line and recent releases.

5.6kstars

939forks

174issues

MITlicense

2026since

Star historydaily snapshots by VibeCrowd

Collecting history — the radar snapshots this repo daily. The trend line appears after 3 days of data (1 so far).

Alternatives & relatedmatched by topic overlap

HKUDS/

nanobot

▲ 275/wk

Ultra-lightweight, open-source, self-hosted personal AI agent framework in Python with WebUI, tools, memory, MCP, multi-agent workflows, automation, and chat apps

47k8.2kPython

mukul975/

Anthropic-Cybersecurity-Skills

▲ 470/wk

817 structured cybersecurity skills for AI agents · Mapped to 6 frameworks: MITRE ATT&CK, NIST CSF 2.0, MITRE ATLAS, D3FEND, NIST AI RMF & MITRE F3 (Fight Fraud) · agentskills.io standard · Works with Claude Code, GitHub Copilot, Codex CLI, Cursor, Gemini CLI & 20+ platforms · 29 security domains · Apache 2.0

27k3.3kPython

deepset-ai/

haystack

▲ 61/wk

Open-source AI orchestration framework for building context-engineered, production-ready LLM applications. Design modular pipelines and agent workflows with explicit control over retrieval, routing, memory, and generation. Built for scalable agents, RAG, multimodal applications, semantic search, and conversational systems.

26k3.0kPython

usestrix/

strix

▲ 2.6k/wk

Open-source AI penetration testing tool to find and fix your app’s vulnerabilities.

48k5.1kPython

QuivrHQ/

quivr

▲ 14/wk

Opiniated RAG for integrating GenAI in your apps 🧠 Focus on your product rather than the RAG. Easy integration in existing products with customisation! Any LLM: GPT4, Groq, Llama. Any Vectorstore: PGVector, Faiss. Any Files. Anyway you want.

39k3.7kPythonquiet

KeygraphHQ/

shannon

Shannon is an AI pentester for web applications and APIs. It analyzes your source code, identifies attack vectors, and executes real exploits to prove vulnerabilities before they reach production.

46k5.4kTypeScriptgiant

Compareagent-governance-toolkit vs nanobot agent-governance-toolkit vs Anthropic-Cybersecurity-Skills agent-governance-toolkit vs haystack

Reviewgenerated from repository data · Aug 5, 2026

What it is

Policy enforcement, identity, sandboxing, and SRE for autonomous AI agents. One pip install, any framework.

How it works

Agent ──► Policy Engine ──► Identity ──► Audit Log ( YAML/OPA/Cedar ) ( SPIFFE/DID/mTLS ) ( Tamper-evident ) │ │ ├── Allowed ──► Tool executes │ └── Denied ──► GovernanceDenied │ ▼ Decision Record

Every layer is optional. Start with govern() and add layers as your risk profile grows. Most teams run policy enforcement + audit logging and never need the full stack.

Getting started

Quick Start:

Prerequisites: Python 3.11+

pip install "agent-governance-toolkit[full]"

For Claude Code, add AGT as a plugin marketplace and install the governance plugin:

/plugin marketplace add microsoft/agent-governance-toolkit
/plugin install agt-governance@agent-governance-toolkit

Govern any tool function in two lines:

from agentmesh.governance import govern

safe_tool = govern(my_tool, policy="policy.yaml")   # every call checked, logged, enforced

Policy example and governance API samples are provided in the README. CLI tools include agt doctor, agt verify, agt red-team, agt lint-policy.

Full walkthrough: quickstart.md. Also available in Japanese, Simplified Chinese, and Korean.

Getting started (continued)

# policy.yaml
apiVersion: governance.toolkit/v1
name: production-policy
default_action: allow
rules:
  - name: block-destructive
    condition: "action.type in ['drop', 'delete', 'truncate']"
    action: deny
    description: "Destructive operations require human approval"

  - name: require-approval-for-send
    condition: "action.type == 'send_email'"
    action: require_approval
    approvers: ["security-team"]

>>> safe_tool(action="read", table="users")
{'table': 'users', 'rows': 42}

>>> safe_tool(action="drop", table="users")
GovernanceDenied: Action denied by policy rule 'block-destructive':
  Destructive operations require human approval

Getting started (examples)

TypeScript / .NET / Rust / Go examples are provided in the README and examples sections.

Recent releases

Latest releases include v4.1.0 (2026-06-09) with Agent OS enhancements and Escrow signing in ProofOfOutcome, and v4.0.0 (2026-06-01) introducing consolidated packages, TEE key management, and Entra JWT verification across the mesh. Earlier highlights include v3.7.0 (2026-05-18) and v3.6.0 (2026-05-12).

Traction

Stars: 5606 Forks: 939 Open issues: 174

License and prerequisites

License: MIT Prerequisites include Python 3.10+ and multi-language SDK requirements as listed in the README.

SharePost on X LinkedIn