Free tool
llms.txt generator and validator
Build an llms.txt from your sitemap with every page's title and description grouped into sections, or paste your domain to validate the file you already publish.
Free, no sign-up. Results for the same URL are cached for an hour.
What the generator does
It finds your sitemap (from robots.txt or /sitemap.xml), reads up to 40 page URLs, fetches each page for its title and meta description, and writes a file in the llms.txt format:
- An H1 with the site name, taken from your home page title.
- A blockquote summary, taken from your home page description. Edit this; it is the line models read first.
- One H2 section per top-level path (Blog, Docs, Features...), each a list of "- [Title](URL): description" lines.
The file is yours to edit. Nothing is published automatically.
What the validator checks
- The file exists at /llms.txt and is not an HTML error page.
- The first non-empty line is a single H1.
- A blockquote summary follows the H1.
- Links are grouped under H2 sections, use absolute URLs, have titles, and mostly carry a note after the colon.
- The file is reasonably short; long content belongs in llms-full.txt.
How to write a good summary line
One paragraph, in the third person, that names the product, the category it belongs to, who it is for and what makes it different. Models reuse this sentence when they describe you, so write it the way you would want to be quoted, and keep facts such as prices out of it unless you will keep them current.
FAQ
What is llms.txt?
A plain-text markdown file at /llms.txt that tells language models what a site is and where its important pages are: an H1 with the site name, a one-paragraph summary in a blockquote, then sections of links with a short note each. It was proposed by Jeremy Howard in 2024 and is published by a growing number of documentation and product sites.
Do AI engines actually read llms.txt?
Adoption by the engines is uneven and none of the major vendors has committed to it publicly. It costs nothing to publish, it is useful to any agent that fetches it, and several AI readiness audits (including ours) check for it. Treat it as cheap insurance, not a ranking lever.
What is the difference between llms.txt and llms-full.txt?
llms.txt is the short index: summary and links. llms-full.txt is an optional companion that contains the full text of the linked pages in one file, for agents that want everything in a single fetch. Start with llms.txt.
How is this different from robots.txt and sitemap.xml?
robots.txt says what crawlers may fetch, sitemap.xml lists URLs for search engines, and llms.txt explains the site in prose for models. All three are complementary. Our generator builds llms.txt from your sitemap.
Why are only 40 pages included?
The free tool reads the first 40 URLs of your sitemap so a run stays fast and within our limits. llms.txt should be curated anyway: list the pages a model should start from, not every URL you own.
What should I edit before publishing?
The summary line: make it a precise one-paragraph description of what the site offers and for whom. Then prune links that do not help a model, and add a short note to any link that lacks one.
Where do I put the file?
At the root of your domain, served as text/plain or text/markdown: https://yourdomain.com/llms.txt. Link to it from your footer so crawlers find it, and mention it in your AI instructions page if you have one.
More free tools
Publishing llms.txt is the easy part
LeapScope shows whether the engines then cite your pages for the prompts your buyers ask, and which pages they cite instead.