llms.txt Validator
Validate a site's llms.txt against the llmstxt.org structure.
How it works
Enter any URL on the site and the validator fetches /llms.txt from that origin and checks the llmstxt.org structure: a single H1 title, a blockquote summary, and '## Section' headings whose list items are markdown links with descriptions.
It then samples the linked URLs live — an llms.txt that sends AI agents to 404s is worse than none — and compares the same-origin links against your XML sitemap to warn when the file has drifted stale.
Findings and section stats download as CSV or JSON, free and instant.
Frequently asked questions
What is llms.txt?
A proposed standard (llmstxt.org) for a markdown index at your site root that tells AI agents what your site contains and where the machine-readable versions live — the AI-era counterpart to sitemap.xml.
What structure does the validator require?
An H1 title on the first line, an optional but recommended '>' blockquote summary, and sections introduced by '## Heading' containing '- [Name](url): description' list items. Malformed list lines are flagged because agents parse that form strictly.
How does the staleness check work?
Same-origin links in llms.txt are compared against the URLs in your sitemap. When only a small fraction overlap, the file likely predates your current page set — regenerate it alongside the sitemap.
Agents can read you. Now get recommended.
BuildSEO AI builds the authority signals that put your site in AI answers.
Try BuildSEO AI