Glossary

llms.txt

A site's own reading list for AI models, in one Markdown file.

By Roger Campos · Last updated: September 2026

TL;DR

llms.txt is a proposed convention for a Markdown file at the root of a website, at /llms.txt, that describes the site for language models: a title, a one-paragraph summary, and lists of links to the pages worth reading, ideally in Markdown. It was proposed in 2024 and is not an official standard.

Start free See the API

Free plan, no credit card. 1,000 credits a month.

How it works

The format

Jeremy Howard of Answer.AI proposed llms.txt in September 2024. The file is Markdown with a fixed outline: an H1 with the site's name, a blockquote summary, optional free text, then H2 sections that list links with a short note each. A section titled Optional marks links a model can skip when context is short. The proposal also suggests serving a Markdown version of each page at the same URL with .md appended.

https://example.com/llms.txt

# Example Docs

> Example is a payments API. These docs cover setup, the REST API and webhooks.

## Docs

- [Quickstart](https://example.com/docs/quickstart.md): first API call in five minutes
- [Webhooks](https://example.com/docs/webhooks.md): events, retries and signatures

## Optional

- [Changelog](https://example.com/changelog.md)

In practice

Who reads it

Honestly: it is unclear. Many documentation sites and developer tools publish one, and some AI coding tools and agents fetch it when pointed at a site. No major search or AI company has committed to using it for crawling or ranking. It costs little to publish and is useful when a person or an agent is deliberately told to read it; don't expect it to change how a model discovers you. Unlike robots.txt, it grants or denies nothing.

URLpipe

llms.txt and URLpipe

URLpipe publishes its own at /llms.txt, with every page's full text at /llms-full.txt, both generated from the same registries as the site so they cannot drift from it.

For your own site, /markdown produces the Markdown versions the proposal asks for: run it over the pages your llms.txt lists and serve the results as .md files. And when a site you want to read has no llms.txt, /markdown on its pages gives an agent the same thing.

Try it

llms.txt, on a page you choose

Turn any URL into clean Markdown

Paste a link and get the page's main content as tidy Markdown — headings, lists, links and code kept, navigation and cookie banners stripped. The format LLMs and RAG pipelines work best with.

Try it free

FAQ

Frequently asked questions

Is llms.txt an official standard?

No. It is a proposal from 2024, published at llmstxt.org, with no standards body behind it.

Does llms.txt affect SEO?

There is no evidence that search engines use it for ranking. Treat it as documentation for agents and tools that are pointed at your site.

What is the difference between llms.txt and robots.txt?

robots.txt tells automated clients what they may fetch. llms.txt tells language models what is worth reading. One is about access, the other about content.

Keep reading

HTML to Markdown for LLMs Markdown Embeddings Monitoring pages for changes Best HTML-to-Markdown APIs Context window All of glossary

See it on your own pages.

Free plan, no card. Confirm your email and your API key is live — you'll be making real requests in minutes.

Start free Email the team