llms.txt Checker
Validate your llms.txt in seconds. We fetch your domain's /llms.txt and check it against the convention AI agents expect - H1 name, summary blockquote, link lists, markdown variants - and show you the raw file. No login.
Enter your domain to fetch and validate its /llms.txt. We read only this public file - nothing is stored.
About the llms.txt Checker
llms.txt (llmstxt.org) is an emerging convention: a markdown file at /llms.txt that gives AI agents a curated map of your site - who you are, what matters, and where to find it - without making them wade through HTML, navigation and scripts. Think of it as a sitemap written for LLMs instead of search crawlers.
This free tool fetches your /llms.txt server-side and runs seven checks against the convention: the file exists and is reachable, is served as text/plain or text/markdown, starts with a # Name heading (the one hard requirement), carries a > summary blockquote, lists pages as markdown link lists, links .md variants (clean markdown copies of key pages, or an llms-full.txt), and includes an ## Optional section. You also get every link we parsed and the raw file content - exactly what an AI agent sees.
llms.txt is one signal among several. Whether AI answer engines can find and cite you at all is decided by your robots.txt AI-crawler policy and sitemap - audit those with our AI Discoverability Checker.
Frequently asked questions
What is llms.txt?
A proposed convention (llmstxt.org): a markdown file at /llms.txt giving AI agents a curated map of your site - a # Name heading, a > summary blockquote, and bulleted lists of your important pages with descriptions.
What does this checker validate?
Seven checks: file exists and reachable over HTTPS, Content-Type is text/plain or text/markdown, H1 name present, summary blockquote present, markdown link lists present, .md variants linked, and an ## Optional section. We also list every parsed link and show the raw file. Link reachability is not checked - this is content validation.
Is llms.txt required for AI visibility?
No. It is optional and engine adoption is still limited - but it is low-cost future-proofing. The stronger signals today are your robots.txt AI-crawler policy and sitemap; audit those with the AI Discoverability Checker.
What are .md variants?
Clean markdown copies of your key pages (page.md, or one combined llms-full.txt) linked from llms.txt, so agents read pure text instead of HTML. Most sites skip this half of the convention - it is the most common warning this tool raises.
Do you store the sites I check?
No. We fetch only the public /llms.txt server-side and return the result. Nothing is stored.
Want help getting found by AI?
We help businesses become discoverable and citable by AI answer engines - the technical setup plus the content and authority that gets you cited. If this check surfaced gaps, we can fix them.
Talk to Postbox Services