llms.txt Generator and Validator
Create or validate an llms.txt file for your website in the llmstxt.org format: summary, sections and links for AI agents. Free, in your browser.
Paragraphs and lists are fine here, but no headings: the format reserves headings for the H1 and the link sections.
Links in a section named exactly “Optional” are secondary: agents may skip them when they need a shorter context. Keep the English name; it is part of the format.
Enter a site name to see the llms.txt preview.
✓ This llms.txt follows the format.
⚠ Valid, with a few things worth fixing.
✗ This file doesn’t follow the llms.txt format.
- —
Your input stays in your browser — nothing is uploaded to our servers.
An llms.txt file gives AI assistants and agents a short, curated map of your site: what it is, and which pages to read for which purpose. This tool builds one in the format described at llmstxt.org, lets you download it, and checks an existing file for the mistakes that make it hard for tools to parse.
How to create an llms.txt file
- Enter your site or project name (the only required part) and a one- or two-sentence summary.
- Optionally add details: key facts an agent should know, as paragraphs or lists, without headings.
- Add sections such as “Docs”, “Guides” or “API”, each with links in the form title, URL and a short note. Put secondary links in a section named Optional.
- Click Download llms.txt and upload the file to the root of your site, so it is served at
https://your-site.com/llms.txt. - To check a file you already have, switch to Validate existing file, paste it in, and fix the issues listed by line number. Edit in builder loads it into the form.
What is llms.txt?
llms.txt is a proposal, published at llmstxt.org, for a Markdown file at the root of a website that helps language models use the site. Web pages are full of navigation, scripts and ads; an llms.txt file points a model straight at the most useful content, ideally clean Markdown versions of key pages.
The format is small and strict. It starts with an H1 with the site name, followed by a blockquote summary. Free text may follow, but no headings. Then come H2 sections, each a list of links written as - [Title](URL): notes. A section called Optional holds links an agent can skip when it needs a shorter context.
llms.txt complements rather than replaces the files you already have. robots.txt tells crawlers what they may access, and sitemap.xml lists every page for search engines. llms.txt is a hand-picked reading list for AI tools. It isn’t a search ranking signal, and support differs between AI products, but it is cheap to add and easy to keep up to date.
Frequently asked questions
Where should I put the llms.txt file?
At the root of your domain, so it is available at https://your-site.com/llms.txt, the same place as robots.txt. If your documentation lives on a subpath or subdomain, you can also publish one there.
Is llms.txt an official standard?
It is a community proposal documented at llmstxt.org, not a formal web standard. Some AI tools and documentation platforms read it, others don’t. Following the format exactly gives the files the best chance of being understood.
Does llms.txt replace robots.txt or a sitemap?
No. robots.txt controls crawler access and a sitemap lists all your URLs for search engines. llms.txt is a short, curated guide for language models. Most sites benefit from having all three.
What goes in the “Optional” section?
Links that are useful but not essential, such as full API references, changelogs or long background pages. By convention, an agent with limited context can skip that section. Keep the English name “Optional”, since it is part of the format.
Can I write the summary and sections in my own language?
Yes. Only the structure (the # and ## headings, the > summary and the link syntax) is fixed. Write the content in the language of your site, and keep the section named “Optional” in English.