nemo-guardrails

NVIDIA's runtime safety framework for LLM applications. Features jailbreak detection, input/output validation, fact-checking, hallucination detection, PII filtering, toxicity detection. Uses Colang 2.0 DSL for programmable rails. Production-ready, runs on T4 GPU.

$ インストール

git clone https://github.com/zechenzhangAGI/AI-research-SKILLs /tmp/AI-research-SKILLs && cp -r /tmp/AI-research-SKILLs/07-safety-alignment/nemo-guardrails ~/.claude/skills/AI-research-SKILLs

// tip: Run this command in your terminal to install the skill