Agent Governance Toolkit¶
Runtime governance for AI agents: deterministic policy enforcement, zero-trust identity, execution sandboxing, and SRE for autonomous agents.
13,000+Tests
8Core packages
5Languages
19Integrations
Packages¶
โ๏ธ Agent OS Policy engine, agent lifecycle, governance gate ๐ Agent Mesh Agent discovery, routing, and trust mesh ๐ก๏ธ Agent Runtime Execution sandboxing with four privilege rings ๐ Agent SRE Kill switch, SLO monitoring, chaos testing โ
Agent Compliance Audit logging, compliance frameworks ๐ช Agent Marketplace Plugin governance and trust scoring โก Agent Lightning High-performance agent orchestration ๐ Agent Hypervisor Hardware-level workload isolation
Language SDKs¶
| SDK | Install |
|---|---|
| ๐ Python | pip install agent-governance-toolkit |
| ๐ TypeScript | npm install @microsoft/agent-governance-sdk |
| ๐ท .NET | dotnet add package Microsoft.AgentGovernance |
| ๐ฆ Rust | cargo add agentmesh |
| ๐น Go | go get github.com/microsoft/agent-governance-toolkit |
Framework Integrations¶
Works with any agent framework: LangChain, CrewAI, AutoGen, Google ADK, OpenAI Agents, LlamaIndex, Haystack, Mastra, MCP, A2A, and more. See the full list.
Examples¶
| Example | Framework | What it demonstrates |
|---|---|---|
| openai-agents-governed | OpenAI Agents SDK | Policy-gated tool calls with trust tiers |
| crewai-governed | CrewAI | Multi-agent governance with role-based policies |
| smolagents-governed | HuggingFace smolagents | Lightweight agent governance |
| maf-integration | MAF | Microsoft Agent Framework integration |
| mcp-trust-verified-server | MCP | Trust-verified MCP server implementation |
Standards Compliance¶
| Standard | Coverage |
|---|---|
| OWASP Agentic AI Top 10 | All 10 risks covered with deterministic controls |
| NIST AI RMF 1.0 | Full GOVERN, MAP, MEASURE, MANAGE alignment |
| Ed25519 (RFC 8032) | Agent identity signatures |
| RFC 9334 (RATS) | Remote attestation alignment |