Skip to content

Agent Governance Toolkit

Governance, trust, identity, and compliance for AI agents.

The Agent Governance Toolkit (AGT) provides a comprehensive set of packages for building governed, trustworthy AI agent systems. It covers the full lifecycle: policy enforcement, identity management, runtime sandboxing, reliability engineering, compliance verification, and marketplace governance.
Quick Start Get running in 5 minutes
Packages 11 packages for every governance layer
Tutorials 40+ step-by-step guides
Deployment Azure Container Apps, Foundry, OpenClaw
Security Threat model, OWASP compliance, scanning

Packages at a Glance

Package Purpose
Agent OS Core policy engine and agent lifecycle management
Agent Mesh Agent discovery, routing, and trust mesh
Agent Runtime Execution sandboxing with privilege rings
Agent SRE Reliability: kill switch, SLO monitoring, chaos testing
Agent Compliance Audit logging, compliance frameworks, evidence collection
Agent Marketplace Plugin governance and marketplace trust
Agent Lightning High-performance agent orchestration
Agent Hypervisor Hardware-level isolation for agent workloads

Examples

Governed examples for popular AI agent frameworks:

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
openshell-governed OpenShell Sandboxed shell execution governance
mcp-trust-verified-server MCP Trust-verified MCP server implementation
maf-integration MAF Microsoft Agent Framework integration
marketplace-governance Marketplace Plugin governance and trust scoring
atr-community-rules ATR Community-contributed governance rules

Standards