Generate your llms.txt

No model is called anywhere in this tool. It reads a file your site already publishes and reshapes it, which is why it stays free. Your sitemap: We read sitemap.xml, following a sitemap index when there is one. It is the only list of pages your site has already committed to publishing. Grouped by section: Pages are grouped by their first path segment, so guides, tools and comparisons arrive as sections rather than one long list of URLs. Capped at 120 pages: A sitemap can name fifty thousand URLs. A file that long helps nobody, and being the short version is the entire point of this one. Your own summary line: The line describing what you do is the line that matters most, so the draft leaves it for you. Generating it would be guessing at your own positioning.

llms.txt is a proposed convention: a markdown file at your site root that tells an AI assistant what your site is and which pages matter. It plays a similar role to robots.txt, but where robots.txt says what a crawler may fetch, llms.txt says what is worth reading.

At the root of your domain, served as plain text or markdown: https://yourcompany.com/llms.txt. Some sites also publish llms-full.txt containing the full text of their key pages.

There is no public commitment from any major engine to read it, and no independent evidence that publishing one changes how often you are cited. It is a proposal that some sites have adopted early. The honest case for it is that it costs one file, not that it is known to work.

robots.txt grants or denies access, and a sitemap is an exhaustive machine-readable list of every URL. llms.txt is neither: it is a short, curated, human-written summary of what your site is and which handful of pages an assistant should read first.

No. It reads your sitemap and drafts the file for you to copy. You edit the summary line and publish it yourself, because the one line that matters most is the one describing what you do, and that is not something to generate.