> ## Documentation Index
> Fetch the complete documentation index at: https://mintlify.com/NVIDIA-NeMo/Guardrails/llms.txt
> Use this file to discover all available pages before exploring further.

# NeMo Guardrails

> Open-source toolkit for adding programmable guardrails to LLM-based conversational applications

<img className="block" src="https://github.com/NVIDIA-NeMo/Guardrails/raw/develop/docs/_static/images/programmable_guardrails.png" alt="Programmable Guardrails" />

# NeMo Guardrails

**Add safety, security, and control to your LLM applications**

NeMo Guardrails is an open-source toolkit for easily adding programmable guardrails to LLM-based conversational systems. Built by NVIDIA, it provides a flexible framework for defining rules and controls that govern how your LLM interacts with users.

## Get Started

<CardGroup cols={2}>
  <Card title="Installation" icon="download" href="/installation">
    Install NeMo Guardrails and set up your environment
  </Card>

  <Card title="Quickstart" icon="rocket" href="/quickstart">
    Build your first guardrailed application in minutes
  </Card>

  <Card title="Core Concepts" icon="book" href="/concepts/overview">
    Learn about the five types of guardrails
  </Card>

  <Card title="Examples" icon="code" href="/examples/basic-rag">
    Explore real-world implementations
  </Card>
</CardGroup>

## Why NeMo Guardrails?

<CardGroup cols={2}>
  <Card title="Safety & Trust" icon="shield-check">
    Prevent harmful content and keep conversations on-topic
  </Card>

  <Card title="Controllable Dialog" icon="comments">
    Guide conversations along predefined paths
  </Card>

  <Card title="Secure Tool Integration" icon="plug">
    Safely connect LLMs to external services
  </Card>

  <Card title="Multi-Layer Protection" icon="layer-group">
    Apply guardrails at input, dialog, retrieval, execution, and output stages
  </Card>
</CardGroup>

## Key Features

* **Five Types of Guardrails**: Input, dialog, retrieval, execution, and output rails for comprehensive control
* **Colang DSL**: Purpose-built language for defining conversational flows and guardrails
* **Built-in Library**: Pre-built guardrails for jailbreak detection, content safety, fact-checking, and more
* **LLM Integration**: Works with OpenAI, NVIDIA NIM, HuggingFace, and other providers
* **Async-First**: Built on Python async for high-performance applications
* **LangChain Compatible**: Seamlessly integrate with LangChain chains and agents