AANA is a pre-action control layer for AI agents: agents propose actions, AANA checks evidence/auth/risk, and tools execute only when the route is accept.

Regex backstop for German HWG & EU 1924/2006 compliance. Flags health claims in LLM-generated marketing copy. 14 patterns, MIT licensed, zero deps.

LLM Guard - A pure Rust implementation guardrails for LLM input/output.

A practical hybrid safety middleware for Large Language Models. It runs both a FastAPI production endpoint and the original interactive CLI with heartbeat. For AI labs, red/blue teaming, prompt engineering

Real-time LLM hallucination guardrail — NLI + RAG fact-checking with token-level streaming halt. Drop-in for any LLM backend.