# Guardrails AI

An open-source Python framework that runs input and output guards around LLM calls.

Guardrails is an open-source Python framework from Guardrails AI. It runs input and output guards in your application that detect, quantify and mitigate specific risks in LLM traffic. It also helps you get structured data from LLMs. Guardrails Hub is a collection of pre-built validators. The repository is under the Apache 2.0 licence. A July 2026 notice in the repository says validators are moving to standard PyPI packages and that hosted remote inferencing is discontinued, so read the migration notes before you plan a rollout.

Price: Free, open source (Apache 2.0). Site: https://github.com/guardrails-ai/guardrails.

Also on the [web page](https://aigovernancetools.fyi/apps/guardrails-ai).