GStars
    microsoft

    microsoft/agent-governance-toolkit

    #233 this week

    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.

    ai-agents
    security
    agent-framework
    ai-safety
    compliance
    governance
    microsoft
    Python
    MIT
    6.4K stars
    1.1K forks
    6.4K GitHub watchers
    Updated Oct 11, 2026
    View on GitHub

    Build with Backblaze B2

    SDKs, agent skills, IDE extensions, and reference pipelines from Backblaze Labs. All open source.

    Explore Backblaze Labs

    Loading star history...

    Where it stands

    Rank, growth pace and release cadence relative to everything GStars tracks.

    Ranks #233 of 2,845 repositories GStars tracks this week (top 8%).

    No releases in the last 90 days; the most recent was 124 days ago, with 164 contributors on GitHub.

    Peaked at #15 in the weekly ranking the week of Jul 26, its best in the past year.

    Use Cases & Benefits

    • Provides deterministic runtime governance for autonomous AI agents through policy enforcement, zero-trust identity, sandboxing, and reliability engineering.
    • Ensures 100% enforcement of AI agent policies with sub-millisecond latency, covering all 10 OWASP Agentic Top 10 risks for robust security and compliance.
    • Use for enforcing strict action-level policies in multi-agent AI systems to prevent unauthorized or dangerous operations before execution.
    • Use for integrating zero-trust identity and trust scoring in AI agent frameworks to secure inter-agent communication and resource access.
    • Use for auditing and monitoring AI agent fleets with real-time dashboards, error budgets, and chaos engineering to maintain operational reliability.

    Should you depend on it?

    License terms, project hygiene and risks, from GitHub metadata and GStars' snapshots.

    License

    MIT

    Permissive: commercial use, modification and redistribution are allowed with attribution.

    Community files

    • README: present
    • Contributing guide: present
    • Code of conduct: present

    Watch-outs

    No watch-outs from GStars' checks.

    General guidance from repository metadata, not legal advice. How we score

    From the README

    Runtime governance for AI agents -- deterministic policy enforcement, zero-trust identity, execution sandboxing, and SRE for autonomous agents. Covers all 10 OWASP Agentic risks with 13,000+ tests.

    Works with any stack — AWS Bedrock, Google ADK, Azure AI, LangChain, CrewAI, AutoGen, OpenAI Agents, and 20+ more. Python · TypeScript · .NET · Rust · Go.

    What it does: Sits between your agent framework and the actions agents take. Every tool call, resource access, and inter-agent message is evaluated against policy before execution. Deterministic — not probabilistic.

    What it doesn't do: This is not a prompt guardrail or content moderation tool. It governs agent actions, not LLM inputs/outputs. For model-level safety, see Azure AI Content Safety.

    Why it matters: Prompt-based safety ("please follow the rules") has a 26.67% policy violation rate in red-team testing. AGT's deterministic application-layer enforcement: 0.00%.

    Full walkthrough: QUICKSTART.md — zero to governed agents in 10 minutes with YAML policies, OPA/Rego, and Cedar support. 🌍 Also available in: 日本語 | 简体中文

    Excerpt from the microsoft/agent-governance-toolkit README on GitHub (MIT license). © its authors.Read the full README on GitHub

    Daily snapshots

    Stars gained per day, and how forks and open issues moved, from GStars' daily snapshots

    Jul 27: +12Jul 28: +161Jul 29: +353Jul 30: +46Jul 31: +37Aug 1: +22Aug 2: +12Aug 3: +13Aug 9: +16

    +1,526 stars over 81 days across 16 snapshot days; best day +353 on Jul 29.

    Forks

    1.1K+345

    Open issues

    78-37

    Compared with peers in AI Agents

    Fastest-growing repositories GStars tracks in this cohort for the week of Oct 11, by 7-day star growth

    View category →
    microsoft/agent-governance-toolkit compared with AI Agents repositories by stars, 7-day star growth, health score and last release
    RepositoryStars+7dHealthLast release
    morluto/rea366.3K+249.0K604 days ago
    vxcontrol/pentagi32.0K+5.4K7517 days ago
    DietrichGebert/ponytail173.5K+5.3K756 days ago
    lexmount/moli20.1K+4.5K751 day ago
    hugohe3/ppt-master61.7K+3.8K755 days ago
    microsoft/agent-governance-toolkit6.4K+075124 days ago
    Category median61.7K+5.3K75—
    Compare agent-governance-toolkit with rea, pentagi, ponytail →

    Also by microsoft

    Other repositories from this maintainer that GStars tracks

    Discover Repositories

    Search across tracked repositories by name or description