Free tools

llms.txt generator

The file that tells assistants what your site is and which pages matter. Free and no account. Nothing leaves your browser.

llms.txt

# Your site name

Save as llms.txt at the root of your domain, served as plain text.

What it tells you

  • Follows the llmstxt.org shape

    An H1 name, a blockquote summary, optional context, then H2 sections of annotated links.

  • Sections, not a flat list

    The section names are the useful part: they tell a reader which links are documentation and which are marketing.

  • Notes per link

    One line saying what each page covers, which is what makes the file worth reading over a sitemap.

  • Copy and paste

    Plain markdown, ready for the root of your domain.

How to use it

  1. 1Name and summarise the siteOne line that would let a stranger tell whether your site answers their question.
  2. 2Group your key pagesDocs, guides, pricing, about. Four to six links per section is plenty; this is a curated entry point, not an index.
  3. 3Save it at your domain rootyourdomain.com/llms.txt, served as plain text.

Questions people ask

Is llms.txt an actual standard?

No, and anyone telling you otherwise is overselling it. It is a proposed convention from llmstxt.org. No major assistant has publicly committed to reading it, and there is no evidence yet that it affects whether you get cited. The honest case is that it costs ten minutes, cannot hurt, and is already in place if adoption comes.

How is it different from a sitemap?

A sitemap is a machine-readable list of every URL, for crawlers deciding what to fetch. llms.txt is a short curated document in plain markdown, saying what the site is and which handful of pages matter. One is exhaustive, the other is opinionated.

Should I block AI crawlers and also write this?

Those are opposite decisions and worth separating. Blocking training crawlers keeps your content out of models. llms.txt helps an assistant that is already allowed to read you understand what it is reading. If you block retrieval crawlers in robots.txt, this file will never be fetched.

What should go in it?

Documentation, key guides, pricing, and anything that explains what you do not do. Leave out marketing pages that repeat each other; a curated file that is mostly noise is no better than no file.

Other free tools

Want a tool like this on your own domain?

This page is the argument for the offer. A small useful utility gets embedded and linked, and every embed is a link back. kiterank builds one for your audience and hosts it on your domain, so the links accrue to you rather than to us.