Show HN: A policy gate that runs before your AI coding agent's tool calls

Category: security

Tags: ai-governance, policy-enforcement, agent-safety, security, microsoft

Score: 8.0/10 (Innovation: 7, Technical: 8, Documentation: 9, Utility: 8)

Agent Governance Toolkit provides deterministic policy enforcement for AI agent tool calls, intercepting actions before they reach production systems. It combines policy engines, identity management, and audit logging into a single framework, addressing a critical gap in AI agent safety where prompt-level controls fail.

Target audience: backend devs, devops, security engineers

Repository: https://sigmashake.com · Python · MIT · 4359 stars

View on Hacker News