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.
安装
npx skills add Orchestra-Research/AI-Research-SKILLs --skill nemo-guardrailsnpx skills add Orchestra-Research/AI-Research-SKILLs --skill nemo-guardrails -a claude-code -gnpx skills add Orchestra-Research/AI-Research-SKILLs --skill nemo-guardrails -a codex -ggemini skills install https://github.com/Orchestra-Research/AI-Research-SKILLs.git --path 07-safety-alignment/nemo-guardrailsgh skill install Orchestra-Research/AI-Research-SKILLs nemo-guardrailsgit clone --depth 1 https://github.com/Orchestra-Research/AI-Research-SKILLs /tmp/Orchestra-Research__AI-Research-SKILLs
mkdir -p ~/.claude/skills ~/.agents/skills
cp -R /tmp/Orchestra-Research__AI-Research-SKILLs/07-safety-alignment/nemo-guardrails ~/.claude/skills/nemo-guardrails # Claude Code
cp -R /tmp/Orchestra-Research__AI-Research-SKILLs/07-safety-alignment/nemo-guardrails ~/.agents/skills/nemo-guardrails # Codex, Cursor, Gemini CLI, Copilot, OpenCode