# microsoft/agent-governance-toolkit — health index 86/100 (Excellent)

> Inspection of the public repository microsoft/agent-governance-toolkit by inspect.software. It holds a health index of 86 out of 100, placing it in the Excellent band. The index is a signal derived from publicly visible practice, not a warranty, a security audit, or an endorsement, and it is independent of payment.

- Repository: https://github.com/microsoft/agent-governance-toolkit
- Report page: https://inspect.software/software/microsoft/agent-governance-toolkit
- Full JSON report: https://inspect.software/api/repositories/microsoft/agent-governance-toolkit/report
- Badge: https://raw.githubusercontent.com/inspect-software/badges/main/v1/m/microsoft/agent-governance-toolkit.svg
- Inspected: 2026-07-20
- Methodology: metrics 1.13.0, report schema 0.16.0 (https://inspect.software/methodology.md)

## Category summary

| Category | Weight | Index | Band |
|---|---|---|---|
| Vitality | 22% | 85/100 | Excellent |
| Community & Adoption | 18% | 87/100 | Excellent |
| Sustainability & Governance | 24% | 80/100 | Good |
| Engineering Quality | 20% | 85/100 | Excellent |
| Security | 16% | 97/100 | Excellent |
| AI Readiness | not counted | 79/100 | Good |

## Repository facts

| Field | Value |
|---|---|
| Description | AI Agent Governance Toolkit — Policy enforcement, zero-trust identity, execution sandboxing, and reliability engineering for autonomous AI agents. Covers 10/10 OWASP Agentic Top 10. |
| Primary language | Python |
| License | MIT |
| Stars | 4,869 |
| Forks | 772 |
| Created | 2026-03-02 |
| Last push | 2026-07-20 |
| Latest release | v4.1.0 |
| Commits (last year) | 2,241 |
| Bus factor | 2 |
| Topics | agent-framework, ai-agents, ai-safety, compliance, governance, microsoft, owasp, policy-engine, python, security, trust, zero-trust |

## Published packages

| Registry | Package | Latest | Monthly downloads |
|---|---|---|---|
| npm | @microsoft/agent-governance-antigravity-cli | 4.0.0 | 121 |
| npm | @microsoft/agent-governance-claude-code | 4.0.0 | 107 |
| npm | @microsoft/agent-governance-copilot-cli | 4.0.0 | 153 |
| go | github.com/microsoft/agent-governance-toolkit | v4.1.0+incompatible | — |
| npm | @microsoft/agent-governance-opencode | 4.0.0 | 122 |
| npm | @microsoft/agent-governance-sdk | 4.0.0 | 11,792 |

## Vitality — 85/100 (Excellent)

Is the project alive — is code being written and are releases shipping? Weight: 22% of the overall index.

### Development activity — 75/100 (Good)

| Criterion | Status | Points | Detail |
|---|---|---|---|
| Push recency | met | 36 / 36 | last push 0 days ago |
| Commit cadence | partial | 13.8 / 36 | 20/52 weeks with commits |
| Commit volume | met | 18 / 18 | 2241 commits in the last year |
| OpenSSF Scorecard: Maintained | excluded | 0 / 10 | OpenSSF Scorecard unavailable |

### Release discipline — 100/100 (Excellent)

| Criterion | Status | Points | Detail |
|---|---|---|---|
| Ships releases | met | 27 / 27 | 19 releases published |
| Release recency | met | 36 / 36 | latest release 40 days ago |
| Release cadence | met | 27 / 27 | a release every ~5.4 days |
| OpenSSF Scorecard: Signed-Releases | excluded | 0 / 10 | OpenSSF Scorecard unavailable |

### Abandonment — 100/100 (Excellent)

| Criterion | Status | Points | Detail |
|---|---|---|---|
| Project is still maintained | met | 100 / 100 | maintenance record not established from the collected data |

## Community & Adoption — 87/100 (Excellent)

Does the project have users, downloads, attention, and a welcoming setup for contributors? Weight: 18% of the overall index.

### Popularity & adoption — 94/100 (Excellent)

| Criterion | Status | Points | Detail |
|---|---|---|---|
| Stars | partial | 59.8 / 60 | 4,869 stars |
| Forks | partial | 24.1 / 25 | 772 forks |
| Watchers | partial | 10.1 / 15 | 66 watchers |

### Community health — 92/100 (Excellent)

| Criterion | Status | Points | Detail |
|---|---|---|---|
| README | met | 22.5 / 22.5 | — |
| License | met | 22.5 / 22.5 | recognized license (MIT) |
| CONTRIBUTING guide | met | 18 / 18 | — |
| Code of conduct | met | 13.5 / 13.5 | — |
| Issue template | not met | 0 / 7.2 | — |
| PR template | met | 6.3 / 6.3 | — |

### Ecosystem adoption (downloads) — 68/100 (Moderate)

Excluded from scoring (no data or not applicable): Registry dependents. Remaining weights renormalized.

| Criterion | Status | Points | Detail |
|---|---|---|---|
| Monthly downloads | partial | 54.5 / 80 | 12,295 downloads/month across go, npm |
| Registry dependents | excluded | 0 / 20 | not reported by this ecosystem |

## Sustainability & Governance — 80/100 (Good)

Will the project survive its people — bus factor, responsiveness, who backs it, and package upkeep? Weight: 24% of the overall index.

### Maintainer resilience (bus factor) — 58/100 (Moderate)

| Criterion | Status | Points | Detail |
|---|---|---|---|
| Bus factor | partial | 25.2 / 54 | 2 contributor(s) cover half of all commits |
| Commit distribution | partial | 13.5 / 22.5 | top contributor authored 40% of commits |
| Contributor breadth | met | 13.5 / 13.5 | 100 contributors |
| OpenSSF Scorecard: Contributors | excluded | 0 / 10 | OpenSSF Scorecard unavailable |

### Issue & PR responsiveness — 90/100 (Excellent)

| Criterion | Status | Points | Detail |
|---|---|---|---|
| Issue resolution | partial | 44.1 / 46.8 | 94% of issues closed |
| PR acceptance | partial | 32.2 / 38.2 | 2140/2543 decided PRs merged |
| OpenSSF Scorecard: Code-Review | excluded | 0 / 15 | OpenSSF Scorecard unavailable |

### Ownership & stewardship — 80/100 (Good)

| Criterion | Status | Points | Detail |
|---|---|---|---|
| Ownership backing | met | 30 / 30 | organization-owned |
| Verified domain | not met | 0 / 20 | — |
| Owner reach | met | 25 / 25 | 125,488 followers of microsoft |
| Track record | met | 25 / 25 | 8207 public repos, account ~12 yr old |

### Package maintenance — 100/100 (Excellent)

| Criterion | Status | Points | Detail |
|---|---|---|---|
| Published & resolvable | met | 25 / 25 | 6 package(s) on go, npm |
| Publish recency | met | 35 / 35 | latest publish 40 days ago |
| Version history | met | 20 / 20 | 20 published versions |
| Not deprecated | met | 20 / 20 | active, not deprecated or yanked |

## Engineering Quality — 85/100 (Excellent)

Are baseline engineering and documentation practices in place? Weight: 20% of the overall index.

### Engineering practices — 92/100 (Excellent)

| Criterion | Status | Points | Detail |
|---|---|---|---|
| CI workflows | met | 24 / 24 | 41 workflow(s) |
| Tests present | met | 24 / 24 | — |
| Linter config | met | 16 / 16 | .eslintrc.json, eslint.config.js |
| Pre-commit hooks | met | 9.6 / 9.6 | — |
| .editorconfig | not met | 0 / 6.4 | — |
| OpenSSF Scorecard: CI-Tests | excluded | 0 / 20 | OpenSSF Scorecard unavailable |

### Documentation — 75/100 (Good)

| Criterion | Status | Points | Detail |
|---|---|---|---|
| README | met | 30 / 30 | — |
| Documentation directory | met | 25 / 25 | — |
| Documentation / homepage site | not met | 0 / 15 | — |
| Repository description | met | 10 / 10 | — |
| Topics | met | 10 / 10 | 12 topics |
| Wiki | not met | 0 / 10 | — |

## Security — 97/100 (Excellent)

Are visible security and supply-chain practices strong, with no malicious dependency and no unresolved high-risk jurisdiction exposure? Weight: 16% of the overall index.

### Security posture — 100/100 (Excellent)

Excluded from scoring (no data or not applicable): Dependency lockfiles. Remaining weights renormalized.

| Criterion | Status | Points | Detail |
|---|---|---|---|
| Security policy (SECURITY.md) | met | 30 / 30 | — |
| Dependabot config | met | 25 / 25 | — |
| Dependency lockfiles | excluded | 0 / 25 | published library — lockfiles are an application concern, not expected |
| CodeQL workflow | met | 20 / 20 | — |

### Dependency advisories — 85/100 (Excellent)

Matched the npm:@microsoft/agent-governance-antigravity-cli@4.0.0 runtime dependency closure — what installing the published package pulls in — 7 packages. Reachability is not analyzed.

| Criterion | Status | Points | Detail |
|---|---|---|---|
| Direct dependencies free of known advisories | met | 35 / 35 | no direct dependency carries a known advisory |
| Indirect dependencies free of known advisories | partial | 10 / 25 | 1 affected: js-yaml 4.1.1 (high 7.5) |
| No advisories left outstanding | met | 40 / 40 | no advisory has been public longer than 90 days |

### Malicious dependencies — 100/100 (Excellent)

| Criterion | Status | Points | Detail |
|---|---|---|---|
| No dependency reported as a malicious package | met | 100 / 100 | no dependency is reported as a malicious package |

### High-Risk Jurisdiction Exposure — 100/100 (Excellent)

Only high-confidence self-published location evidence affects this multiplier. Ambiguous matches are review-only; country evidence is not proof of nationality, citizenship, legal registration, malicious intent, or sanctions status.

| Criterion | Status | Points | Detail |
|---|---|---|---|
| Policy exposure multiplier | met | 100 / 100 | no confirmed policy-scope location match |

## AI Readiness — 79/100 (Good)

How well is the repo equipped to be developed and maintained with AI coding agents? An independent, experimental badge — weight 0.0, so it is surfaced on its own and does not affect the overall health score.

### Agent context & guidance — 75/100 (Good)

Excluded from scoring (no data or not applicable): Legible commit history. Remaining weights renormalized.

| Criterion | Status | Points | Detail |
|---|---|---|---|
| Agent instructions | met | 45 / 45 | .github/copilot-instructions.md, .github/pipelines/AGENTS.md, AGENTS.md, agent-governance-claude-code/AGENTS.md, agent-governance-dotnet/AGENTS.md, agent-governance-opencode/AGENTS.md, agent-governance-python/AGENTS.md, agent-governance-python/agent-compliance/AGENTS.md, agent-governance-python/agent-mesh/AGENTS.md, agent-governance-python/agent-mesh/sdks/AGENTS.md, agent-governance-python/agent-os/AGENTS.md, agent-governance-python/agent-sre/AGENTS.md, agent-governance-rust/AGENTS.md, docs/AGENTS.md, examples/AGENTS.md, examples/demos/AGENTS.md, policy-engine/AGENTS.md |
| Machine-readable docs (llms.txt) | not met | 0 / 15 | — |
| Legible commit history | excluded | 0 / 40 | no data |

### Verify loop (build / test / typecheck) — 74/100 (Good)

Excluded from scoring (no data or not applicable): Demonstrated agent practice. Remaining weights renormalized.

| Criterion | Status | Points | Detail |
|---|---|---|---|
| One-command bootstrap | not met | 0 / 18 | — |
| Automated tests | met | 22 / 22 | — |
| Lint / format config | met | 11 / 11 | .eslintrc.json, eslint.config.js |
| Static type checking | met | 11 / 11 | agent-governance-python/agent-compliance/src/agent_compliance/py.typed, agent-governance-python/agent-hypervisor/src/hypervisor/py.typed, agent-governance-python/agent-marketplace/src/agent_marketplace/py.typed, agent-governance-python/agent-mesh/packages/mcp-proxy/tsconfig.json, agent-governance-python/agent-mesh/services/api/tsconfig.json, agent-governance-python/agent-mesh/src/agentmesh/py.typed, agent-governance-python/agent-os/extensions/chrome/tsconfig.json, agent-governance-python/agent-os/extensions/copilot/tsconfig.json, agent-governance-python/agent-os/extensions/cursor/tsconfig.json, agent-governance-python/agent-os/extensions/mcp-server/tsconfig.json, agent-governance-python/agent-os/modules/atr/atr/py.typed, agent-governance-python/agent-os/modules/cmvk/src/cmvk/py.typed, agent-governance-python/agent-os/modules/emk/emk/py.typed, agent-governance-python/agent-os/modules/iatp/iatp/py.typed, agent-governance-python/agent-os/src/agent_os/py.typed, agent-governance-python/agent-primitives/agent_primitives/py.typed, agent-governance-python/agent-runtime/src/agent_runtime/py.typed, agent-governance-python/agent-sre/src/agent_sre/py.typed, agent-governance-python/agentmesh-integrations/copilot-governance/tsconfig.json, agent-governance-python/agentmesh-integrations/mastra-agentmesh/tsconfig.json, agent-governance-python/agentmesh-integrations/openshell-skill/openshell_agentmesh/py.typed, agent-governance-typescript/agent-os-vscode/tsconfig.json, agent-governance-typescript/tsconfig.json, policy-engine/sdk/node/tsconfig.json |
| Reproducible environment | met | 10 / 10 | Dockerfile, lockfile |
| Demonstrated agent practice | excluded | 0 / 10 | no data |
| Automated maintenance | partial | 5 / 8 | dependency automation configured, none observed in the sampled commits |
| OpenSSF Scorecard: Pinned-Dependencies | excluded | 0 / 10 | OpenSSF Scorecard unavailable |

### Code legibility for models — 82/100 (Good)

| Criterion | Status | Points | Detail |
|---|---|---|---|
| Type-checkable code | partial | 27 / 45 | Python with type-check config (agent-governance-python/agent-compliance/src/agent_compliance/py.typed, agent-governance-python/agent-hypervisor/src/hypervisor/py.typed, agent-governance-python/agent-marketplace/src/agent_marketplace/py.typed, agent-governance-python/agent-mesh/packages/mcp-proxy/tsconfig.json, agent-governance-python/agent-mesh/services/api/tsconfig.json, agent-governance-python/agent-mesh/src/agentmesh/py.typed, agent-governance-python/agent-os/extensions/chrome/tsconfig.json, agent-governance-python/agent-os/extensions/copilot/tsconfig.json, agent-governance-python/agent-os/extensions/cursor/tsconfig.json, agent-governance-python/agent-os/extensions/mcp-server/tsconfig.json, agent-governance-python/agent-os/modules/atr/atr/py.typed, agent-governance-python/agent-os/modules/cmvk/src/cmvk/py.typed, agent-governance-python/agent-os/modules/emk/emk/py.typed, agent-governance-python/agent-os/modules/iatp/iatp/py.typed, agent-governance-python/agent-os/src/agent_os/py.typed, agent-governance-python/agent-primitives/agent_primitives/py.typed, agent-governance-python/agent-runtime/src/agent_runtime/py.typed, agent-governance-python/agent-sre/src/agent_sre/py.typed, agent-governance-python/agentmesh-integrations/copilot-governance/tsconfig.json, agent-governance-python/agentmesh-integrations/mastra-agentmesh/tsconfig.json, agent-governance-python/agentmesh-integrations/openshell-skill/openshell_agentmesh/py.typed, agent-governance-typescript/agent-os-vscode/tsconfig.json, agent-governance-typescript/tsconfig.json, policy-engine/sdk/node/tsconfig.json) |
| Manageable file sizes | partial | 54.7 / 55 | 15/2742 source files over 60KB |

### Machine-readable interfaces — 100/100 (Excellent)

| Criterion | Status | Points | Detail |
|---|---|---|---|
| API schema (OpenAPI/GraphQL/proto) | met | 40 / 40 | agent-governance-python/agent-mesh/proto/registration.proto, agent-governance-python/agent-os/modules/iatp/proto/iatp.proto, docs/studio/openapi.yaml |
| MCP server | met | 20 / 20 | — |
| Runnable examples | met | 40 / 40 | demos, examples, notebooks |

## Collection warnings

- OpenSSF Scorecard did not return a usable result (exit code -9); skipping Scorecard checks

## What this report is

inspect.software measures public repositories against a single published, versioned methodology and reports the result as a 1–100 health index. Findings are signals derived from what is visible in public repository data — they are not a security audit, a warranty, or an endorsement, and no result depends on payment.

- Methodology, formulas and weights: https://inspect.software/methodology.md
- What a result does and does not claim: https://inspect.software/wiki/signals-not-warranties.md
- Rating bands: https://inspect.software/wiki/scoring-bands.md
- Corrections: https://inspect.software/contact.md
- Index of all documents: https://inspect.software/llms.txt