NVIDIA NeMo Guardrails Library
The NeMo Guardrails library is an open-source Python package for adding programmable guardrails to LLM-based applications. It intercepts inputs and outputs, applies configurable safety checks, and blocks or modifies content based on defined policies.
Get Started
Copy the starter prompt and paste it into your AI coding agent to help it install the NVIDIA NeMo Guardrails library, choose the right docs, or follow contributor guidance.
Browse the following introductory guides to learn more about the NVIDIA NeMo Guardrails library.
Overview of the NVIDIA NeMo Guardrails library, including its capabilities, architecture, and supported LLMs.
ConceptInstall NeMo Guardrails with pip, configure your environment, and verify the installation.
Get StartedConnect Cursor, Claude Code, Codex, or another AI agent to the documentation MCP server or starter prompt.
Get StartedFollow hands-on tutorials to deploy Nemotron Content Safety, Nemotron Topic Control, and Nemotron Jailbreak Detect
TutorialReference for pre-built guardrails including content safety, jailbreak detection, topic control, PII handling, agentic security, and third party APIs.
ReferenceNext Steps
Once you’ve completed the get-started tutorials, explore the following areas to deepen your understanding.
Configure YAML files, Colang flows, custom actions, and other components to control LLM behavior.
ConceptRun guardrailed inference using the Python API or Guardrails API server.
Get StartedMeasure accuracy and performance of dialog, fact-checking, moderation, and hallucination rails.
How ToDebug guardrails with verbose mode, explain method, and generation log options.
How ToUse OpenTelemetry to trace requests, forward Python logs, and emit metrics for end-to-end visibility into guardrails.
How ToDeploy guardrails using the local API server, Docker containers, or production microservices.
How ToIntegrate NeMo Guardrails with LangChain chains, runnables, and LangGraph workflows.
How To