Free tool
llms.txt is a small Markdown file at your site root that tells AI systems what
your site is and which pages matter. Fill this in, copy or download the file, and put it where
crawlers can read it.
Enter your site address above — the file appears here as you type.
Upload the file to your site root so it answers at https://your-site.com/llms.txt.
Nothing else to configure — no DNS, no build step, no registration anywhere. That is the whole
installation, and it is also why the file is cheap enough to be worth trying: the cost is one
upload, and the downside if nobody reads it is zero.
You will see advice to "declare it in robots.txt". There is no such directive —
robots.txt only says who may crawl what. A comment there changes nothing.
Only pages that genuinely matter, one line each, written as facts rather than marketing. It is a map, not a sales page: a file that lists fifty pages tells a machine nothing about which five matter.
To be blunt about it: llms.txt is an emerging convention and no model is obligated
to read it. It costs almost nothing and it may be ignored — which is why we generate it in the
fix pack alongside things that are not optional.
Generating the file is half the job. The other half is whether AI crawlers can actually reach
it — a Disallow in robots.txt, a blocking rule on Cloudflare, or a
client-rendered page all defeat the file you just published.
Run the AI crawler checker on the same address to see what
crawlers really get, with the evidence attached.