agent-governance-toolkit
6,590AI Agent Governance Toolkit — policy enforcement, zero-trust identity, and execution oversight.
Activity band details
Activity band A to F: a bin of a score that adds GitHub stars (log scale), a push to the upstream repository in the 12 months before `as_of`, the number of declared integration surfaces and, where the catalogue records them, citing papers and benchmark evaluations. It measures popularity and activity. It is not a level of evidence: no band means a paper cites the tool or that it was measured. Recency is judged as of 2026-11-22.
Computed band: D
(raw score 4.53).
Shown band: D
.
Facets:
documented_in=0evaluated_on=0integration_surfaces=1paper_citations=0recent_push=2stars=1.53
Source of truth: pipeline/maturity/score.py
Description
Microsoft's AI Agent Governance Toolkit is a reference implementation of zero-trust governance for enterprise AI agents. Provides identity binding, policy engine, execution audit, and approval workflows. Designed as a template for enterprise deployments rather than a drop-in library.
Why it's included
Enterprise governance cell: layers zero-trust identity and policy-engine primitives onto agent deployments, complementing runtime guardrails with organizational controls.
Addresses failure modes
These tags are the catalog's claim about what agent-governance-toolkit is built to catch or prevent. A tag is not a test result. SAICA-Bench has not measured agent-governance-toolkit, so none of these tags is tested here.
- Security vulnerability — Insecure patterns, injection flaws, weak cryptography, secret leakage.
- Scope creep — Actions outside declared task boundary.
- Supply-chain attack — Slopsquatting, typosquatting, compromised MCP servers.
- Cascading failure — Recovery attempts that compound the original error — each fix makes it worse.