home/categories/llm-ai/davila7-claude-code-templates-cli-tool-components-skills-ai-research-safety-alignment-nemo-guardrails-skill-md
llm-aidata-ai
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.
maintainer
davila7
更新于 1/20/2026
星标
17577
分支
1576
quick start
Installation and usage
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
$ install --globalskills.sh
使用
安装后，您可以通过在终端运行以下命令来使用此技能：
skills use nemo-guardrails