---
# SPDX-FileCopyrightText: Copyright (c) 2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
# SPDX-License-Identifier: Apache-2.0
title: "NVIDIA NeMo Guardrails Library"
sidebar-title: "Home"
description: "Add programmable guardrails to LLM applications with an open-source Python library."
keywords:
    ["nemo guardrails", "llm safety", "content moderation", "guardrails python"]
layout: overview
---

import { StarterPromptButton } from "./_components/StarterPromptButton";

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.

<StarterPromptButton />

Browse the following introductory guides to learn more about the NVIDIA NeMo Guardrails library.

<Cards>

<Card title="Overview" href="/overview">

Overview of the NVIDIA NeMo Guardrails library, including its capabilities, architecture, and supported LLMs.

<Badge intent="tip" minimal outlined>Concept</Badge>
</Card>

<Card title="Installation" href="/get-started/installation-guide">

Install NeMo Guardrails with pip, configure your environment, and verify the installation.

<Badge intent="tip" minimal outlined>Get Started</Badge>
</Card>

<Card title="Use with AI Agents" href="/get-started/use-with-ai-agent">

Connect Cursor, Claude Code, Codex, or another AI agent to the documentation MCP server or starter prompt.

<Badge intent="tip" minimal outlined>Get Started</Badge>
</Card>

<Card title="Tutorials" href="/get-started/tutorials">

Follow hands-on tutorials to deploy Nemotron Content Safety, Nemotron Topic Control, and Nemotron Jailbreak Detect

<Badge intent="tip" minimal outlined>Tutorial</Badge>
</Card>

<Card title="Guardrail Catalog" href="/configure-guardrails/guardrail-catalog">

Reference for pre-built guardrails including content safety, jailbreak detection, topic control, PII handling, agentic security, and third party APIs.

<Badge intent="tip" minimal outlined>Reference</Badge>
</Card>

</Cards>

## Next Steps

Once you've completed the get-started tutorials, explore the following areas to deepen your understanding.

<Cards>

<Card title="Configuring Guardrails" href="/configure-guardrails/configure-rails">

Configure YAML files, Colang flows, custom actions, and other components to control LLM behavior.

<Badge intent="tip" minimal outlined>Concept</Badge>
</Card>

<Card title="Running Guardrailed Inference" href="/run-guardrailed-inference/run-rails">

Run guardrailed inference using the Python API or Guardrails API server.

<Badge intent="tip" minimal outlined>Get Started</Badge>
</Card>

<Card title="Evaluating Guardrails" href="/evaluation/evaluate-guardrails">

Measure accuracy and performance of dialog, fact-checking, moderation, and hallucination rails.

<Badge intent="tip" minimal outlined>How To</Badge>
</Card>

<Card title="Logging" href="/observability/logging">

Debug guardrails with verbose mode, explain method, and generation log options.

<Badge intent="tip" minimal outlined>How To</Badge>
</Card>

<Card title="Observability" href="/observability/observability">

Use OpenTelemetry to trace requests, forward Python logs, and emit metrics for end-to-end visibility into guardrails.

<Badge intent="tip" minimal outlined>How To</Badge>
</Card>

<Card title="Deployment Options" href="/more-deployment-options/deployment">

Deploy guardrails using the local API server, Docker containers, or production microservices.

<Badge intent="tip" minimal outlined>How To</Badge>
</Card>

<Card title="LangChain Frameworks" href="/integration-with-third-party-libraries/langchain">

Integrate NeMo Guardrails with LangChain chains, runnables, and LangGraph workflows.

<Badge intent="tip" minimal outlined>How To</Badge>
</Card>

</Cards>