Privacy and advertising choices
Git-Stars uses essential storage for site operation. Optional analytics and ad-measurement scripts stay disabled unless you accept them; partners such as Google may then use cookies or similar identifiers where required. Privacy Policy
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.
This repository page has enough original analysis, source evidence, and comparison context to be treated as an indexable Git-Stars review.
100
review score
Problem solved
AGT solves the fundamental problem that prompt-level safety is insufficient for autonomous agents, as prompt injection attacks achieve near-100% success rates. It replaces probabilistic model-level controls with deterministic, code-enforced policies that make unauthorized actions structurally impossible, providing a verifiable security boundary.
Deployment reality
The available setup signal starts with: pip install agent-governance-toolkit[full]. Treat this as a starting point, then ask Codex or Claude to inspect the README, environment variables, runtime version, and deployment target before production use.
Commercial use
The recorded license is MIT. This is a useful commercial-use signal, but teams should still verify license text, dependencies, model/API terms, and trademark constraints.
Capability ceiling
Developers can build multi-agent systems with fine-grained access control, zero-trust identity, and tamper-evident audit logs. Real-world use cases include enterprise automation where agents interact with databases, email, and APIs, requiring strict policy enforcement. The framework supports any agent framework and enables compliance with regulatory requirements for auditability and incident response.
Git-Stars is independent and not affiliated with GitHub or this project. Analysis may be AI-assisted and based on public repository metadata plus short README-derived summaries. We do not mirror full README files, docs, issues, or social comments.
microsoft/agent-governance-toolkit is tracked as a Python project in the AI Agent area. This evaluation combines public GitHub metadata, category signals, short source summaries, and Git-Stars editorial rules rather than copying project documentation.
Momentum check: the repository has 5.6k total stars, with +0 today, +659 this week, and +0 this month. These growth windows help distinguish durable adoption from short-lived visibility spikes.
Maintenance check: current activity is Active; the latest push was 22 days ago, and the open issue queue is 161, about 2.89% of total stars. Treat this as an adoption signal, not a substitute for engineering due diligence.
Adoption check: 898 forks and 5.6k watchers suggest how often the project is reused or followed. License signal: MIT. Always verify license compatibility before commercial or internal use.
Practical fit: this project is most relevant when you need Python teams evaluating ecosystem-native tooling. Be cautious when you need a legal review, security audit, or production SLA.
Source check: Git-Stars currently has 2 explicit source reference(s) for this report and a recent growth signal of 659. Follow the original GitHub repository for final install, security, and release information.
Analysis
ReadyOriginal problem, capability, and verdict guidance are available.
Sources
ReadyRepository metadata and README/source references are attached.
License
ReadyMIT is recorded for review.
Maintenance
ReadyRecent activity is visible in repository metadata.
Alternatives
ReadyEnough nearby projects exist for comparison.
Momentum
5.6k Stars
Reuse
898 Forks
Attention
5.6k Watchers
Maintenance
active
License
MIT
Open issues
161
Agent Governance Toolkit (AGT) is an open-source framework from Microsoft for enforcing policy, identity, sandboxing, and SRE on autonomous AI agents. It intercepts tool calls in deterministic application code to make policy violations structurally impossible, rather than relying on prompt-level safety.
Key Features
- Intercepts every tool call, message send, and delegation in deterministic application code before the model's intent reaches the wire, making policy violations structurally impossible. - Supports YAML-based policies with conditions, actions (allow/deny/require_approval), and multi-agent identity tracking. - Provides a simple two-line API (`govern(tool, policy)`) and integrates with any framework via `pip install`.
AI Agent
Agent frameworks, autonomous workflows, and tool-use systems
pip install agent-governance-toolkit[full]73
Health Score
Active
Commit Activity
Mar 2, 2026
Created
Aug 1, 2026
Last push
+11
Today's growth
+385
7-day growth
+385
30-day growth
Forks
Open
Watchers
microsoft
GitHub profileobra/superpowers
An agentic skills framework & software development methodology that works.
affaan-m/ECC
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
NousResearch/hermes-agent
The agent that grows with you
mattpocock/skills
Skills for Real Engineers. Straight from my .agents directory.
anomalyco/opencode
The open source coding agent.
✓
License
✓
Forked
✓ Active
Maintained
Problem Solved
AGT solves the fundamental problem that prompt-level safety is insufficient for autonomous agents, as prompt injection attacks achieve near-100% success rates. It replaces probabilistic model-level controls with deterministic, code-enforced policies that make unauthorized actions structurally impossible, providing a verifiable security boundary.
Capabilities
Developers can build multi-agent systems with fine-grained access control, zero-trust identity, and tamper-evident audit logs. Real-world use cases include enterprise automation where agents interact with databases, email, and APIs, requiring strict policy enforcement. The framework supports any agent framework and enables compliance with regulatory requirements for auditability and incident response.
Bottom Line
This toolkit is essential for teams deploying autonomous AI agents in production, especially in regulated industries. It is not for simple chatbots or projects where prompt-level safety is sufficient. The key trade-off is increased operational complexity for deterministic security guarantees.