Plain-AyI
← All projects
AI testing & safety

NeMo Guardrails

NVIDIA's toolkit for adding safety rules that keep AI chatbots on topic and guard against misuse.

Research-backedNew this week

What it does

NeMo Guardrails lets developers put "guardrails" around an AI chatbot. These are rules that control what it says, such as staying off certain topics, following a set conversation flow, or checking facts in answers.

It also helps protect chat apps against common tricks like jailbreaks and prompt injections (messages designed to make the AI ignore its instructions). It can be used from Python code or run as a separate server.

Who it's for

Developers building AI chatbots or assistants that need to be safe and predictable.

Can I use it without coding?

Developers only. It is a Python library and server for developers. New to this? Start here.

Can I run it?

Cost
FreeNothing to pay or sign up for.
Runs on
Server, Mac, Windows, Linux
Computer
An ordinary computer is fine
API key
Not needed

Try it

Using Claude Code, Cursor or another AI coding assistant? Paste the prompt and it will walk you through the setup.New to this?

Before you install

  • Only download from the official GitHub page. Copies with similar names exist for many popular projects.
  • No standard license listed. Check the GitHub page before using it for business.
  • More on staying safe

Where people are talking about it