Free tool

llms.txt generator

Give it a domain. It reads the site's sitemap, opens up to 50 pages, and writes the llms.txt from the headings and meta descriptions those pages already publish — grouped into sections by URL path. No model is involved, so nothing is invented.

Reads /sitemap.xml to find pages, then opens each one. Up to 50 pages.

The crawl is twenty-eight lines of backend

One endpoint reads the sitemap as XML and, for each of the first fifty URLs, opens the page and lifts its H1, title and meta description straight out of the parsed document tree. The grouping and the llms.txt formatting then happen in this page, from those four fields:

.arguments
   url:string
validators.mandatory:x:@.arguments/*/url
strings.concat
   get-value:x:@.arguments/*/url
   .:/sitemap.xml
http.get:x:@strings.concat
xml2lambda:x:@http.get/*/content
.result
for-each:x:@xml2lambda/*/urlset/*/url/*/loc/*/#text
   if
      lt
         get-count:x:@.result/*
         .:int:50
      .lambda
         http.get:x:@.dp/#
         html2lambda:x:@http.get/*/content
         .h1
         strings.join:x:@html2lambda/*/html/*/body/**/h1/[0,1]/**/#text
            .:" "
         set-value:x:@.h1
            strings.trim:x:@strings.join
         unwrap:x:+/*/*/*
         add:x:@.result
            .
               .
                  loc:x:@.dp/#
                  h1:x:@.h1
                  title:x:@html2lambda/*/html/*/head/*/title/*/#text
                  description:x:"@html2lambda/*/html/*/head/*/meta/*/\\@name/=description/./*/\\@content"
return-nodes:x:@.result/*

Describe an endpoint in a sentence, and the Hyperlambda Generator writes and deploys it — then it is a tool your own AI agents can call over MCP. Want the pages' full text as well? Website to JSON returns that. Run the platform yourself:

curl -fsSL https://hyperlambda.dev/docker-compose.yaml | docker compose -f - up

More free tools

Writing an llms.txt is one of nine free tools here, each with the handful of backend lines that powers it printed on the page. See all of them — no signup on any of it.

Questions

What is llms.txt?

A plain Markdown file at the root of a site that tells language models what the site contains and where the important pages are — a title, a one-line summary, then grouped links with short descriptions. It exists because a model reading your rendered HTML wastes most of its context on navigation and markup.

Does this use AI to write it?

No, and that is deliberate. Every line comes from something the site already publishes: the page's H1 or title becomes the link text, its meta description becomes the description, and the sections come from the URL paths. Nothing is generated, so nothing can be invented — but it also means the output is only as good as your existing metadata.

So should I edit the result?

Yes. Treat it as a first draft that took you fifteen seconds instead of an afternoon. The format rewards curation, and a crawler gives you the first fifty URLs in sitemap order rather than the fifty you would have chosen. Pages with no meta description come through without one, which is usually your cue to write one.

Why does it need a sitemap?

Pages are discovered from /sitemap.xml rather than by following links, which keeps the crawl predictable and limited to pages the site itself publishes as worth indexing. A site without one cannot be read by this tool.