Skill

nemo-guardrails

Published by Orchestra Research

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.

Skill details

Resource Id
aede2495-22e4-4a37-b190-f6a5c018bb41
Skill Md Url
https://github.com/davila7/claude-code-templates/blob/14680ec431ec8cbfd42b12ddcbe58e2f4ee3cccf/cli-tool/components/skills/ai-research/safety-alignment-nemo-guardrails/SKILL.md
Supported Agents
Claude Code
Version
1.0.0
Created At
"2026-10-08T13:50:31.118Z"
Updated At
"2026-10-08T13:50:31.118Z"