RepoRadar
Leave a Tip
Item detail

microsoft/agent-governance-toolkit

Agent Governance Toolkit is Microsoft's MIT-licensed reference implementation for governing AI agents — ships policy enforcement (YAML / Rego-style rules), zero-trust identity (agent-to-service and agent-to-agent), execution sandboxing primitives, and reliability engineering patterns (timeouts, retries, circuit breakers, audit trail) that work with any agent framework. 4,378 stars, active 2026-06-

Open source →Back to radar
Score8.1
Popularity81.0
Risknone
TierGold
Score breakdown
Usefulness8.0
Novelty8.0
Momentum8.0
Maturity8.1
Open-source/build8.4
Evidence7.2
Workflow potential9.6
Setup ease6.4

Popularity is tracked separately. Support, ads, sponsorships, and tips never affect these signals.

Why it matters

Useful for platform and security teams that need a vendor-neutral governance layer for AI agents — covering policy, identity, sandboxing, and reliability — without committing to a single agent framework (LangChain, AutoGen, CrewAI, Microsoft Agent Framework, custom).

Who should use it

platform teams that need a vendor-neutral governance layer across multiple agent frameworks (LangChain, CrewAI, AutoGen, custom)security teams that need policy-as-code (YAML / Rego) enforcement for agent tool calls and inter-agent messagingcompliance teams in regulated industries (finance, healthcare, gov) that need zero-trust identity and audit trail for agent actionsinfra teams that need sandboxing adapters (Linux namespaces, gVisor, Firecracker) usable from any frameworkreliability engineers who need timeouts, retries, circuit breakers, and structured audit logs that work across frameworks

Who should skip it

Skip if the source link, docs, or setup requirements do not match your workflow.

Risk explanation

No inherent user-impacting risk is flagged from the captured evidence.

Evidence links

Closest alternatives / related signals

governancepolicy-as-coderegozero-trustidentitysandboxinggvisorfirecracker