What is llms.txt and how do you create one?

llms.txt is a plain Markdown file published at the root of a website, at /llms.txt, that gives AI tools a short summary of the site and a curated list of its most useful pages. It was proposed in September 2024 by Jeremy Howard of Answer.AI, and the specification lives at llmstxt.org.

Why does llms.txt exist?

Web pages are full of navigation, scripts and layout that make them slow and noisy for a language model to read. An llms.txt file is the opposite: a few hundred words of clean Markdown that say what the site is and where the important content is. It is a young convention and no major AI company has promised to use it, but it costs minutes to create and some AI tools and coding assistants already read it.

What goes in an llms.txt file?

The format is simple and in this order:

1. An H1 with the name of the site or project. This is the only required part.
2. A blockquote with a one or two sentence summary.
3. Optional paragraphs or lists with more detail.
4. H2 sections, each with a list of Markdown links and a short note on what each page contains.
5. Optionally, a section called ## Optional for pages a tool can skip when it is short of space.

An example llms.txt

# Example Dental Clinic

> Family dental clinic in Pune offering check-ups, implants and braces. Open Monday to Saturday.

## Services

- [Dental implants](https://example.com/implants): what the treatment involves, cost and recovery time
- [Braces and aligners](https://example.com/braces): options for children and adults

## About

- [Our dentists](https://example.com/team): qualifications and experience
- [Contact and directions](https://example.com/contact): phone, address and opening hours

## Optional

- [Blog](https://example.com/blog): oral health articles

How do you publish it?

Save the file as llms.txt and upload it to the root of your site so it loads at https://yoursite.com/llms.txt. Serve it as plain text or Markdown, not as an HTML page. Make sure robots.txt does not block it, and update it when you add or remove important pages.

Does llms.txt replace robots.txt or a sitemap?

No. robots.txt controls which crawlers may visit which URLs, and an XML sitemap lists every page you want indexed. llms.txt is a short, human-readable guide to the best content. Keep all three.

Common mistakes

• Listing every page. Keep it to the pages that answer real questions.
• Marketing copy instead of facts. Describe what each page contains.
• A file that returns your HTML 404 page with status 200. Check it loads as text.