#6565th of 82 in Agent frameworks and SDKs
agent-governance-toolkit
Policy enforcement, identity and audit for AI agent tool calls
- Stars
- 6.5k
- License
- MIT
- Last commit
- Oct 2026
- Last release
- Jun 2026
- Language
- Python
657 on 4 Apr 20266,504 on 31 Oct 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
Intercepts agent tool calls, messages and delegations in application code and checks them against YAML, OPA or Cedar policies before they execute. Adds agent identity (SPIFFE/DID/mTLS), tamper-evident audit logs, privilege-ring sandboxing, SRE controls such as a kill switch, and an OWASP compliance CLI. SDKs exist for Python, TypeScript, .NET, Rust and Go, with adapters for LangGraph, CrewAI, AutoGen and others.
Who it is for: Teams deploying autonomous agents that need policy enforcement and audit trails
Strengths
- Deterministic deny at tool-call level, not prompt-level; two-line `govern()` wrapper to start
- SDKs in Python, TypeScript, .NET, Rust and Go, plus Claude Code and Copilot CLI plugins
- Adapters for Semantic Kernel, LangGraph, CrewAI, OpenAI Agents SDK, LlamaIndex, Haystack and others
- RFC 2119 specs with conformance tests; `agt verify` checks OWASP compliance in CI
Weaknesses
- Public preview; README warns of breaking changes before GA
- Python has the full stack; other language SDKs cover only core governance
- Packaging is in flux: 45 packages consolidated into 5, old names deprecated or stubbed
- Only governs actions routed through its hooks; unwrapped tools are not covered
What it needs
- no GPU
- Docker + Compose
- Needs Python 3.11+ (quick start), Optional Azure credentials for Azure features
- Models: Model-agnostic; governs tool calls for any agent framework
Quick answers
Is agent-governance-toolkit open source?
Yes. Its code is on GitHub under the MIT license.
Can you run agent-governance-toolkit with Docker?
Yes. Its repository has a Docker setup: a Dockerfile, a Compose file or a published image.
Does agent-governance-toolkit need a GPU?
No, it runs without one.
Also in Agent frameworks and SDKs
See all 82| Rank | Project | Score |
|---|---|---|
| 1 | ppt-masterAgent skill that turns documents into natively editable PowerPoint decks | 95 out of 100 |
| 2 | openai-agents-pythonPython SDK for multi-agent workflows with handoffs, guardrails and tracing | 90 out of 100 |
| 3 | langchainPython framework for building LLM agents and apps from interoperable components | 89 out of 100 |
| #4 | browser-usePython library that lets an LLM agent control a web browser | 89 out of 100 |
| #5 | tradingagentsMulti-agent LLM framework that simulates a trading firm's analysis process | 89 out of 100 |