llms.txt checker
Fetch any site's llms.txt, validate it against the llms.txt spec, see the outline AI agents will read, and test every link it lists. Free, no account.
Enter your llms.txt URL or just the domain. It is read from the site root.
No llms.txt yet? Build one with the llms.txt generator.
How to check an llms.txt file
- 1
Enter your domain
The checker fetches /llms.txt from the site root, and looks for the optional /llms-full.txt companion file.
- 2
Check the structure
It parses the file the way the spec describes: an H1 title first, a blockquote summary, then ## sections listing links as - [Name](url): notes.
- 3
Test the links
The links the file points AI agents at are requested, so you can fix anything broken or redirected.
- 4
Fix and recheck
Update the file, or rebuild it with the llms.txt generator, then run the check again.
Check the rest of the site too
The free audit checks llms.txt alongside robots.txt, AI crawler access, structured data and the rest of AI-search readiness.
Frequently asked questions
What is llms.txt?
A Markdown file at the root of a site, /llms.txt, that gives AI assistants and agents a short description of the site and a curated list of its most useful pages. It is a proposed convention from llmstxt.org, not an official standard.
What must an llms.txt file contain?
Only an H1 title is required, on the first line. The spec then recommends a one-line blockquote summary, optional notes, and ## sections that list links as - [Name](url): optional notes. A section named Optional marks links that can be skipped when context is short.
Does llms.txt affect Google rankings?
No. Google doesn't use it for ranking. It helps AI tools and coding agents find your key pages and docs quickly, which matters most for documentation-heavy and developer-facing sites.
What is llms-full.txt?
An optional companion that contains the full text of your key pages in one Markdown file, so an agent can load everything in one request instead of following links.
Why does my llms.txt show as a web page?
Many sites route every unknown path to their homepage. If /llms.txt isn't a real file, that catch-all answers with HTML and a 200 status. Serve the file as plain text from the site root.