Check 04 / 05
/llms.txt is a plain-text file at your site's root that tells AI crawlers what your site is and which pages matter most — the same job robots.txt does for crawl permissions, but for context instead of access. It isn't an official web standard, and no major AI lab has confirmed it uses one to rank or select sources. It also costs nothing to publish, several crawlers and tools do check for it, and a 404 there is one more small, free signal that a site hasn't been set up with AI visibility in mind.
GET /llms.txt 404 — not found
A one-request, one-response test anyone can run in a browser.
The format borrows from Markdown: a title, a one-line blockquote summary, then sections linking to the pages that matter, with a short description next to each link. rankavex.com/llms.txt is a working example — real content, not a template.
Because adoption is unconfirmed, don't treat this as the fix for a robots.txt block or missing schema — it's a supplement to both, not a substitute for either.
The only real cost is keeping it accurate. A stale llms.txt claiming things about pages that no longer exist is worse than not having one — the same logic applies to any file a client, human or AI, might use as a source of truth.
Send the domain. You'll get the findings back either way.
Ask for a free look at your siteSources
Cite this
/llms.txt is a plain-text file at your site's root that tells AI crawlers what your site is and which pages matter most — the same job robots.txt does for crawl permissions, but for context instead of access.
Igor Almeida, Rankavex. Last updated 2026-08-10https://rankavex.com/checks/what-is-llms-txt/