microsoft/agent-governance-toolkit - Open Source PR Review Scorecard

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.

C-Rank Grade: S (Elite) - 69/100

External PR Merge Rate: 76%

Response Time: -

First Timer Success: 61%

Frequently Asked Questions

Is microsoft/agent-governance-toolkit welcoming to first-time open-source contributors?

microsoft/agent-governance-toolkit has a recorded first-timer success rate of 61.3%. Repositories ranked S typically provide actionable feedback during code reviews and actively nurture new community contributors.

How fast can I expect code review feedback on my pull request?

Maintainers in microsoft/agent-governance-toolkit respond to incoming external pull requests in approximately 0.0 hours on average. Keeping PRs focused on single tasks and ensuring tests pass helps maintainers review faster.

What does the 69.5 C-Rank™ score (S Tier) represent?

The C-Rank™ system evaluates GitHub projects on a 0–100 scale using real data: PR merge rates, review turnaround time, active maintainer presence, and first-time contributor success. A score of 69.5 places microsoft/agent-governance-toolkit in the S tier.

What is the external contributor pull request merge rate for microsoft/agent-governance-toolkit?

The external contributor pull request merge rate for microsoft/agent-governance-toolkit is 76.2%, based on public PR activity from non-core contributors.

Are there Good First Issues available in microsoft/agent-governance-toolkit?

microsoft/agent-governance-toolkit currently has 3 active issue(s) tagged with beginner-friendly labels like "good first issue", "beginner", or "up-for-grabs".

microsoft
microsoft/agent-governance-toolkitS•Elite6.4k
GitHub
Back to Explorer
microsoft

microsoft/agent-governance-toolkit

6,415
Active (30d)S•Elite(69/100)Python

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.

GitHub
Compare••
Jump to:

AI Maintainer Review Guidelines

Review Persona

Empathetic Technical Mentor

Warmth Score
8.1/10
Patience Score
8.4/10
Nitpick Rate
30%

Highly welcoming maintainers in microsoft/agent-governance-toolkit. Prompt code reviews with positive guidance for new contributors.

Top PR Submission Do's

  • •Ensure code complies with the project coding style
  • •Keep PRs scoped to a single concern
  • •Include context and link to the related issue

Top PR Friction Pitfalls (Don'ts)

  • •Do not submit PRs without linking an issue
  • •Do not break existing tests without fixing them
  • •Do not mix unrelated refactors in a single PR
Response Velocity
-
No reviewer activity recorded

Average Response Latency

Tracks hours until a maintainer leaves a review, comment, or PR response.

Merge Efficiency
76.2%
High acceptance rate for external PRs

External Acceptance Rate

Percentage of community pull requests successfully merged into main.

First-Timer Success
61.3%
Strong first-timer PR acceptance rate

First PR Conversion

Rate at which developers submitting their first repository PR succeed.

Active Maintainers
42 core
Highly collaborative maintainer core
Diagnostic Health HUD
76.2%
Merge Gauge
61.3%
1st-Timer
Community Vibe49/100

Embed C-Rank Badge

Show contributors that your repository actively reviews and merges external pull requests.

GetMerged C-Rank badge for microsoft/agent-governance-toolkit
[![GetMerged C-Rank](https://getmerged.abhishekco.de/api/badge/microsoft/agent-governance-toolkit)](https://getmerged.abhishekco.de/microsoft/agent-governance-toolkit?utm_source=github&utm_medium=badge)

Active Good First Issues (5)

View on GitHub

Package agent-governance Description The base wheel ships only agent_compliance. Both README quick-start imports work only after: pip install "agent-governance-toolkit[full]" Separately, once [full] is installed, importing agent_os emits: DeprecationWarning: agent-os-kernel is deprecated. Use agent-governance-toolkit-core instead. (docs/package-consolidation/MIGRATION.md) — but the README quick start (and several discussion examples) still reference the deprecated path. Suggested fixes Quick Start: pip install "agent-governance-toolkit[full]", or include the governance modules in the base wheel. Update quick-start imports to the canonical agent-governance-toolkit-core paths per MIGRATION.md. Happy to PR the README change if useful. Steps to Reproduce Repro (Python 3.12, pip 24): pip install agent-governance-toolkit # v4.1.0 python -c "from agentmesh.governance import govern" # ModuleNotFoundError: No module named 'agentmesh' python -c "from agent_os.policies import PolicyD

📅 Opened Jul 4, 2026💬 6 comments
Quality: 50/100Contribute

Found during a code-quality / docs pass. In agent_os/credential_redactor.py (around lines 101-199), redact() / redact_data_structure() iterate only PATTERNS (secret-like material), not PII_PATTERNS (email / phone / SSN / credit-card / IP). So PII is detected by find_pii_matches() but not removed by redact(). The class docstring's 'redact sensitive material' phrasing can lead a caller to assume PII is scrubbed when persisting/returning data. Suggestion: either add an opt-in redact_pii=True path, or clarify in the docstring that redact() is secrets-only. Separately, the SSN pattern here (\d{3}-\d{2}-\d{4}) is narrower than the one in integrations/base.py (which also accepts space/dot/no-separator) — reconciling to one shared pattern would avoid divergent detection.

📅 Opened Jun 30, 2026💬 2 comments
Quality: 90/100Contribute

Summary The examples/flowise-governance/flowise-flow.json shipped in #3105 fails to import on Flowise 2.x and 3.x. Reported by an external adopter (jinweida) via email after trying to import the file on both major versions. Root cause The JSON was authored by hand against Flowise's documented chatflow schema rather than exported from a running Flowise instance: Contains a non-standard top-level _comment key (real Flowise exports never include this). Node data (inputParams / baseClasses / anchors) does not match Flowise's live node registry, and every node is version: 1 regardless of the installed node versions. The _comment and README claim "Flowise 2.x / 3.x" but the file was never validated against a live import. For accuracy: it is a 5-node flow (chatInput, customFunction, httpRequest, customFunction, chatOutput), not the 9-node flow the merge note described. What works (no change needed) flowise-agentmesh package: GovernanceNode, AuditNode, RateLimiterNode, TrustGateNode all exi

📅 Opened Jun 26, 2026💬 8 comments
Quality: 80/100Contribute

Summary Hypervisor (and SagaOrchestrator) expose a mixed sync/async surface. Several methods are declared async def but never await anything, while sibling methods that operate on the same objects are plain def. This is a footgun: an un-awaited coroutine is silently truthy and the failure surfaces later, far from the call site. Important correction to the original framing The original report described this as an "annotation bug" (e.g. async def create_session(...) -> ManagedSession claiming a non-coroutine return). That part is not a bug: annotating an async def with the awaited type is correct Python, and type checkers (mypy/pyright) already understand the call returns a coroutine and would flag .session_id on an un-awaited result. Annotating these as Coroutine[...] / Awaitable[...] would actively mislead type checkers and should not be done. The genuine issues are: Async-without-await. In agent-governance-python/agent-hypervisor/src/hypervisor/core.py, create_session, join_session,

📅 Opened Jun 25, 2026💬 3 comments
Quality: 80/100Contribute

Summary Update MCP docs for issue #2597 after implementation lands so AGT documents stateless 2026-07-28 as the preferred behavior and 2025-11-25 as compatibility. Scope Update docs\tutorials\27-mcp-scan-cli.md. Update related MCP trust/security docs found during implementation. Stop describing Mcp-Session-Id as the normal scanner lifecycle. Distinguish AGT application-level auth/state helpers from MCP protocol sessions. Update ADR 0027 status only if maintainers want the implementation PR to carry that change. Testing Run relevant docs checks for edited files. Verify commands, links, and lifecycle descriptions match shipped behavior. Parent: #2597

📅 Opened Jun 22, 2026💬 0 comments
Quality: 90/100Contribute
Looking for more Python beginner tasks?Explore Python GFI

Contributor Community Vibe Feedback

Rate what actually matters after opening a pull request here.

Have you contributed to this repo?

Rate your first-hand PR experience (review speed, maintainer responsiveness, and onboarding ease) to help other contributors.

3 ratings required
Maintainer helpfulness
Review speed
Beginner friendliness

Contributor Compatibility & Review Speed Analysis for microsoft/agent-governance-toolkit

When evaluating whether to contribute to microsoft/agent-governance-toolkit, response velocity and maintainer engagement are crucial. GetMerged continuously tracks pull request trajectories, first-comment latency, and code review rounds to help developers avoid submitting pull requests to backlogged repositories.

Currently, maintainers of microsoft/agent-governance-toolkit acknowledge new external contributions in approximately -. Out of all submitted pull requests from non-core authors in the last 180-day window, 76.2% were successfully merged into the primary branch.

Frequently Asked Questions - Contributing to microsoft/agent-governance-toolkit

01

Is microsoft/agent-governance-toolkit welcoming to first-time open-source contributors?

microsoft/agent-governance-toolkit has a recorded first-timer success rate of 61.3%. Repositories ranked Elite typically provide actionable feedback during code reviews and actively nurture new community contributors.

02

How fast can I expect code review feedback on my pull request?

The initial maintainer response time averages ~-. Keeping PRs scoped to single concerns and ensuring CI checks succeed will optimize review turnaround.

03

What does the 69.5 C-Rank™ score represent?

The C-Rank™ index scores repositories on a 0 to 100 scale using an objective formula: external PR merge rates, initial response speed, active maintainer count, and first-time contributor retention. A score of 69.5 places microsoft/agent-governance-toolkit in the Elite tier.

04

What is the external contributor pull request merge rate for microsoft/agent-governance-toolkit?

The external pull request merge rate is 76.2%. GetMerged isolates non-core community contributions so external developers get an accurate benchmark of PR acceptance probability.

05

Are there beginner Good First Issues open in microsoft/agent-governance-toolkit?

Yes, microsoft/agent-governance-toolkit currently has 3 active issue(s) tagged with beginner-friendly labels. You can inspect these directly from the repository issues tab.

GetMerged C-Rank™ Indexing Standard

All metrics displayed for microsoft/agent-governance-toolkit are automatically retrieved via the public GitHub API and recalculated daily. Insider pull requests submitted by repository owners or organization members are excluded from merge rate calculations to preserve objective external contributor statistics.