What is llms.txt, and what it isn't
A plain-language explanation of the llms.txt proposal, what it can do for your website, and the claims to be careful about.
llms.txt is a proposal published at llmstxt.org: a Markdown file at the root of a website that gives large language models a concise, curated overview of the site.
The format
A valid file contains, in order:
- An H1 with the name of the site or project (the only required part)
- A blockquote with a short summary
- Optional paragraphs or lists with important context
- H2 sections with Markdown link lists:
- [Title](url): description - An optional section named Optional for secondary links that can be skipped when context is short
Why it helps
Web pages are built for browsers: navigation, scripts, cookie banners and layout markup surround the actual content. An AI assistant that fetches your page has to dig through all of it. llms.txt points directly at what matters, and companion Markdown files give clean text.
What it isn't
- It is not an official web standard, and no AI company has committed to reading it everywhere.
- It does not control crawling. That's
robots.txt. - It does not guarantee that an assistant will cite, recommend or rank your site.
Think of it as good documentation for machines: low cost, clearly useful when it's read, and harmless when it isn't.