Llms.txt checker: does this site publish an llms.txt, and does it follow the format?
In short: Paste websites and see, for each, whether /llms.txt exists, whether it's Markdown with the H1, blockquote summary and linked H2 sections the llmstxt.org proposal describes, how many links it lists, and whether /llms-full.txt exists. Limit: llms.txt is a proposal; the checker can't say whether any given assistant reads the file.
An llms.txt checker fetches a site's /llms.txt and reads it against the llmstxt.org proposal. Paste one site or up to 100 (500 after a Google sign-in): each gets Follows the format, Partly follows it, Not llms.txt format, No llms.txt or Unreachable, with its title, summary, sections and link counts, and whether a companion /llms-full.txt exists.
Price: this tool is free. Checking a whole email list is from $9/mo, and the first 100 checks are free with Google, no card. See pricing
Sample result
docs.acme.example has an llms.txt with a title, a summary and 41 links in 3 sections.
- Website
- docs.acme.example
- Title
- Acme API
- Links
- 41 in 3 sections
What this means for you
See which sites publish an llms.txt, and whether it has the parts the format asks for.
- H1, summary and sections read
- Links counted per section
- /llms-full.txt checked too
- 100 sites a run, 500 when signed in
- llms.txt
- AI answers
- AEO
By SimpleVerifier Team · Last updated
Checking llms.txt across a list of sites?
- Over 500 sites? Run them in batches of 500 when signed in and download the CSV after each.
- Check which AI crawlers each site lets in with the robots.txt checker; llms.txt helps only if they can fetch it.
- Emailing the owners of these sites? Check the list at /verify. The first 100 email checks are free with a Google sign-in, no card.
How do I check if a site has an llms.txt file?
- Paste one website or a list, one per line: up to 100 a run, or 500 after a free Google sign-in.
- Press Check llms.txt. Each site's /llms.txt is fetched (HTTPS first), and /llms-full.txt on the same origin.
- Read the verdict, the H1 title, the summary line, each section with its link count, and the notes on what's missing.
- Download the CSV with one row per site.
Example
- You enter
- Three websites:
docs.acme.example,globex.exampleandinitech.example. - You get
docs.acme.exampleFollows the format: H1 "Acme API", a blockquote summary, 3 sections with 41 links including Optional, and /llms-full.txt exists.globex.examplePartly follows it: an H1 and links, but no summary.initech.exampleNot llms.txt format: /llms.txt returns the site's HTML 404 page with status 200. Download the CSV.- Limits
- Up to 100 websites a run without an account and 500 when signed in with Google. Linked pages aren't fetched.
What should an llms.txt file contain?
The llms.txt proposal, published in September 2024, describes a Markdown file at /llms.txt in a fixed order. First an H1 with the name of the site or project, the only required part. Then a blockquote (> ...) with a short summary, then any plain paragraphs, then H2 sections, each a list of links in the form `- Page name: what it covers`.
An H2 called Optional has a special meaning: links an assistant can skip when it needs a shorter context. Many sites also publish /llms-full.txt, the full text of those pages in one file. That is a common convention rather than part of the core format, so the checker reports whether it exists without counting it against the site.
Do ChatGPT, Claude or Google read llms.txt?
It's a proposal, not an IETF or W3C standard, and reading it is up to each operator. The file costs little to publish and is mainly useful to tools that fetch documentation for coding assistants, and to any assistant that looks for it. The checker reports the file's shape, not whether any particular assistant uses it.
Two things matter more for appearing in AI answers: that the crawlers can fetch your pages at all, which is set in robots.txt (OAI-SearchBot for ChatGPT search, Claude-SearchBot, PerplexityBot), and that the pages linked from llms.txt are real and current. A common fault the checker catches is a site that answers /llms.txt with its HTML 404 or home page and a 200 status, which looks like a file but holds nothing to read.
Who uses this tool, and for what?
- Developer tool companies
- Confirm the docs site's llms.txt lists every current guide.
- SEO and AEO teams
- See which sites in a portfolio, or among competitors, publish an llms.txt.
- Agencies
- Catch sites that answer /llms.txt with an HTML page after a redesign.
- Researchers
- Measure llms.txt adoption across a list of domains.
What can’t this tool tell you?
- llms.txt is a proposal; the checker can't say whether any given assistant reads the file.
- Linked pages aren't fetched; only the link form is checked.
- The first 1 MiB of the file is read.
- Up to 100 sites a run without an account and 500 signed in.
Common questions
- Is llms.txt the same as robots.txt?
- No. robots.txt (RFC 9309) says which crawlers may fetch which paths. llms.txt is a reading list: a Markdown summary and links to the pages worth reading. It grants or blocks nothing.
- What does Partly follows it mean?
- The file has the required H1, but no blockquote summary or no H2 section with [name](url) links, so an assistant gets a title and little else.
- Are the linked pages checked?
- No. Links are counted and checked for form (absolute URL or /path), not fetched.
- Should the links point at .md files?
- The proposal suggests offering Markdown versions of pages at the same URL plus .md, but ordinary page URLs are fine; the checker accepts both.
- Can I check many sites at once?
- Yes. 100 sites a run without an account and 500 after a free Google sign-in, with a CSV.
- Is the llms.txt checker free?
- Yes, it's a free tool with no card. Two small requests per site.
Sources
You audited one domain. Cold outreach means thousands.
This tool checks a domain you type in. It will not tell you which addresses at that domain are real.
- Bulk mailbox verification with real SMTP checks
- The email finder — name plus company to a verified address
- Website enrichment for emails, owner names and socials
Plans from $9 a month, cancel anytime, no contract. Sign in with Google and your first 100 email checks are free, no card. The free tools stay free either way.