11,154 sites implement llms.txt
of 14,351 tested · measured 2026-08-23
every listed site fetched, 23 Aug 2026 · 14,351 listed
Checks passed across the 11,154 probed hosts: Markdown negotiation 8,732 · Markdown twin at a predictable URL 5,389 · llms.txt 11,154 · API catalog 3,824 · MCP server card answers 5,836.
What llms.txt is
A file at /llms.txt listing the pages a site considers worth reading, in markdown, as a curated entry point rather than a crawl. Read llmstxt.org — it is the authority on the design and we are not trying to be.
If you are looking for an llms.txt checker or validator: we are not one, and we do not validate the file's structure. What we publish is a dated probe result per site — whether the file was there when we last fetched it, and what else that site does. If that is what you need, the per-site reports below are it.
How we test it
We fetch /llms.txt and require a 200 with a non-empty body. We do not grade its structure.
This is the weakest of the signals we count and we say so on every report: a file that exists is a declaration, not a capability. It appears in tier 1 for that reason.
Sites that implement it
45.2% of these are on mintlify, 2.8% of these are on teachify. The platform supplies the machinery; the domain signals the commitment, and a report says which applies.
The search API has no filter that selects this set, so there is no link here that would return it. The reports above each carry the dated per-site result. What the API can filter on.
llms.txt is one signal among several. The rubric says exactly what we look for and how each tier is reached, and a probe can be requested — the probe decides, never the request.
Method and date
Measured 2026-08-23. every listed site fetched, 23 Aug 2026 · 14,351 listed Every figure on this page carries the population it was measured against; a count without a denominator is not a measurement. How the index is built · All standards.