Show HN: Enforra – open-source action governance for AI agent tool calls

Category: security

Tags: ai-governance, tool-call-policy, agent-security

Score: 7.5/10 (Innovation: 7, Technical: 7, Documentation: 8, Utility: 8)

Enforra provides an open-source SDK for enforcing policies on AI agent tool calls before they execute, offering decisions like allow, block, require_approval, or log_only. It addresses a critical gap in AI agent safety by treating system prompts as insecure and providing a typed, local enforcement layer. Its innovative combination of policy-as-code with agent governance makes it highly relevant for production AI systems.

Target audience: backend devs, devops, AI engineers

Repository: https://github.com/enforra/enforra · TypeScript · Apache-2.0 · 4 stars

View on Hacker News