SwipeToLaunch
Add your product

llms.txt validator

Check an llms.txt file's structure against llmstxt.org and test its links.

How to use it

  1. Enter a site. We fetch /llms.txt from its root, or the exact file URL you paste.
  2. Read the checks. Title, summary, sections and link format, each checked against the llmstxt.org proposal.
  3. Fix broken links. We test up to 10 of the file's links, your own pages first, and flag any that fail.

What llms.txt is

llms.txt is a proposed standard (llmstxt.org) for a Markdown file at the root of your site that gives AI assistants a curated map of your most useful pages. A crawler working through your HTML sees navigation, scripts and cookie banners. A model reading llms.txt sees a short summary and a list of the pages worth reading, with a note on each.

The format

# Project name

> One or two sentences on what this is.

Optional paragraphs with more context.

## Docs

- [Quick start](https://example.com/start): install and first run
- [API reference](https://example.com/api): every endpoint

## Optional

- [Changelog](https://example.com/changelog)
  • H1 title. The only required part. It must be the first line.
  • Blockquote summary. A short > line right after the title.
  • H2 sections of link lists, each item - [name](url): note.
  • An Optional section for links a tool can skip when space is short.

Mistakes this catches

  • A catch-all route serving your HTML homepage at /llms.txt with a 200.
  • Prose or bare URLs where list items should be links.
  • Several links squeezed into one list item.
  • Links to pages that have moved or no longer exist.

Does it help?

No major AI company has committed to reading llms.txt, so treat it as cheap insurance rather than a ranking factor. Coding assistants and agent tools are the most common readers today, which makes it most useful for developer products, APIs and documentation sites. It takes an hour, helps the tools that do read it, and doubles as a useful index for people. Many sites also publish llms-full.txt with the full text in one file.

Write yours with the llms.txt generator, and check AI crawlers can reach your pages with the robots.txt tester.

What you get

  • Checks title, summary, sections and link format
  • Counts links per section
  • Tests up to 10 links for errors
  • Detects llms-full.txt
  • Flags HTML served at /llms.txt

Questions

What should an llms.txt file contain?

A `# Title` line, a one-line `> summary`, then `##` sections listing your key pages as `- [name](url): note` items. Put links a model can skip under `## Optional`.

Where does llms.txt go?

At the root of your site, at https://yoursite.com/llms.txt, served as plain text or Markdown. It can also live at the root of a docs subpath.

What is the difference between llms.txt and llms-full.txt?

llms.txt is a short index of links. llms-full.txt, a common companion, puts the full text of those pages in a single file so a tool can load everything at once.

Does Google use llms.txt?

Google has said it does not use llms.txt for Search. Some AI tools and coding assistants read it, so it is worth having, but it does not replace a sitemap or good on-page SEO.