llmtxt.info
English
Français Deutsch Español Italiano Русский العربية 简体中文 日本語
Validate a file

llms.txt Observatory

A public, dated measurement layer for llms.txt. The figures describe a fixed panel and observable HTTP behavior, not all websites or AI usage.

Last updated:

Study with Firecrawl

Detecting llms.txt files: what an analysis of 2,000 domains shows

192 files recognized across 2,000 domains. Study with Firecrawl: charts, method, limits and practical checks for your site.

Read the study

Latest fixed-panel snapshot

57.6%

125 of 217 testable hosts served a qualifying file

14.0 KB

median file size across parsed directory files

85.6%

parsed directory files with a blockquote summary

The current observation was generated on . The panel is fixed and curated. It should be compared with future releases, not extrapolated to the web.

The observatory is designed for reproducibility. It records the public HTTP response, parse outcome and link checks available at release time, so a reader can distinguish adoption, syntax quality and discovery signals instead of treating a served file as proof of AI usage.

By sector

SectorTestedServingRate
AI & ML 36 21 58.3%
Developer tools 61 44 72.1%
Docs platforms 7 5 71.4%
E-commerce 13 8 61.5%
Fintech 16 8 50%
Media 14 2 14.3%
Other 23 5 21.7%
SaaS 47 32 68.1%

V2 implementation signals

The v2 observation is narrower than a client-support matrix. It recorded 320 reachable links out of 330 checked, 40 Markdown alternates, 9 describedby relations, and 23 hosts with a qualifying subpath file.

Downloads and scope

Use the JSON release manifest for source hashes and limitations, the CSV for sector values, and the status endpoint for the current snapshot identifier. Read the full methodology before quoting a number.

Dated file analyses

Directory measurement: .

These analyses describe the measured files, including their limits. Inclusion does not mean that a file has no structural errors or is used by an AI system.

Sources