Harness Toolbox/Security & guardrails/microsoft/agent-governance-toolkit

microsoft/agent-governance-toolkit

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.

View on GitHub →
PythonMITagent-frameworkai-agentsai-safetycompliancegovernance
Stars
4.8k
Δ 7d
+92
Δ 30d
+472
Age
4 mo
Last push
3h ago
5.1k4.2k3.3k2.4k1.6kMay 23Jun 19Jul 17
90-day star history

Most-wanted open issues

Ranked by 👍 reactions. 38 open issues total, checked 2026-07-17.

Issue👍CommentsOpened
122 d
RFC: Adopt a dual-stack migration for MCP 2026-07-28

documentation, enhancement, architecture, Priority: HIGH

031 mo
061 mo
feat: command denylist enforcement inside sandbox execution

enhancement, agent-hypervisor, security, Priority: HIGH

051 mo
031 mo

Alternatives in Security & guardrails

Agentic LLM Vulnerability Scanner / AI red teaming kit 🧪

1.9k
+77d
Python
2 yrs

Packmind seamlessly captures your engineering playbook and turns it into AI context, guardrails, and governanc…

301
TypeScript
10 mo

native macOS app that gives you a real-time dashboard for your Claude Code and Cowork sessions, with analytics…

206
+27d
Swift
4 mo

Make Opus 4.8 (or any Claude model) work like Claude Fable 5 — a Claude Code skill + guard hooks (plan gate, m…

115
+527d
Python
1 wk