agent-governance-toolkit

Agent Governance Toolkit puts deterministic policy enforcement between your AI agents and the actions they take. Every tool call, resource access, and inter-agent message gets evaluated against policy before execution. Not prompt-based safety (which fails 27% of the time in red-team tests) but application-layer enforcement with a 0% violation rate.

Works with any agent framework: LangChain, CrewAI, AutoGen, AWS Bedrock, Google ADK, Azure AI, and 20+ others. Ships with a CLI (`agt`), governance dashboard, and covers all 10 OWASP Agentic risks. SDKs for Python, TypeScript, Rust, Go, and dotnet. Sub-millisecond policy checks.

Free and open source under MIT. Solo devs building agents should use this from day one. Teams running agents in production need this or something like it. There is no excuse for shipping autonomous agents without action-level governance.

The catch: this is still in public preview, so expect breaking changes before GA. It governs agent actions, not model outputs. For prompt-level safety, you still need a separate content moderation layer.