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
Mis à jour 1/20/2026
Étoiles
17577
Forks
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.
Installation
$ install --globalskills.sh
Utilisation
Après l'installation, vous pouvez utiliser ce skill en exécutant la commande suivante dans votre terminal :
skills use nemo-guardrails