llms.txt

llms.txt is a proposed standard for a markdown file at /llms.txt on a website that gives AI models a short summary of the site and links to its most useful pages. Jeremy Howard published the proposal in 2024. It argues that web pages are built for people: HTML wraps information in navigation, ads and JavaScript, and converting it back into clean text "is difficult and imprecise," while context windows are still too small for most websites. The file is meant mainly for inference, when an agent needs information while helping a user, rather than for training.

What the file contains

The format is plain markdown in a set order:

• an H1 with the name of the project or site, the only required section;
• a blockquote with a short summary;
• optional paragraphs or lists with more detail;
• sections under H2 headings that list links, each with an optional note;
• an "Optional" section for links an agent can skip when it needs a shorter context.

The proposal also suggests a clean markdown version of each useful page at the same URL with .md added. For a fictional project management tool, the start of the file might look like this:

# Tallyfield

> Project management for creative agencies, with client approvals and time tracking.

## Docs

- [Pricing](https://tallyfield.example/pricing.md): plans and what each includes

What it does for AI visibility

Google's guide to its generative AI features says you don't need new machine-readable files, AI text files or Markdown to appear in Google Search, and that Google Search ignores llms.txt files. The file costs little to publish, but it does not replace the basics: AI crawlers that can reach your pages, key facts in the HTML, and structured data that matches what each page says.