# NeMo Guardrails — Programmable LLM Safety Rails

> Define what your LLM can and can't do using a simple dialogue DSL.

- Org: NVIDIA
- Date: 2024-06-15
- Category: security, tool, repo
- Source: https://github.com/NVIDIA/NeMo-Guardrails
- Canonical page: https://ai-tldr.dev/releases/nvidia-nemo-guardrails/

## In short

NVIDIA's toolkit for adding programmable safety rails to LLM apps. Define conversation flows, topic boundaries, and safety checks using Colang DSL.

## What it is

NeMo Guardrails lets you define safety rails for LLM conversations using Colang, a simple DSL. You specify allowed topics, forbidden responses, and conversation flows — the system enforces them.

## How it works

Write Colang files defining rails: 'if user asks about X, respond with Y' or 'never discuss Z'. The runtime intercepts LLM calls, checks against rails, and blocks/redirects as needed.

## Why it matters

Instead of hoping your system prompt holds, you get deterministic guardrails. The LLM literally cannot respond outside defined boundaries.

## Who it's for

Teams building customer-facing LLM apps that need strict topic/safety control.

## Try it

pip install nemoguardrails

## Links

- [GitHub](https://github.com/NVIDIA/NeMo-Guardrails)
- [Docs](https://docs.nvidia.com/nemo/guardrails)