A markdown file at the root of your domain — /llms.txt — that gives AI assistants a curated map of your site: what it is, and which pages matter. It is a proposal published at llmstxt.org, not a standard any company is obliged to honour, but it costs nothing to publish and is easy to keep correct.

Is llms.txt required, and does Google use it?

It is required by nobody. Google has not said it uses llms.txt. It is worth publishing because it is cheap and because several assistants and crawlers do read it — not because any search engine has promised to.

What is the difference between llms.txt and robots.txt?

robots.txt controls access: which crawlers may fetch which paths. llms.txt is the opposite — it grants nothing and blocks nothing, it just describes your site and recommends pages. Use robots.txt to decide who gets in, llms.txt to tell them what is worth reading. If you want to check crawler access, use our AI Crawler Checker.

Which parts of the file are actually required?

The H1 is the only element the spec makes mandatory. Everything else is optional, which is why this tool reports a missing summary or missing sections as a warning rather than an error — the file is still valid, it is just not saying much.

Why are relative URLs an error?

Because the file is read away from your site. A crawler that has your llms.txt in a context window has no base URL to resolve "/docs" against, so a relative link points at nothing. Always use the full https:// address.

What does the "Optional" section mean?

In the llms.txt format, a section titled Optional marks links a reader can skip when it needs a shorter context. Put secondary material there — changelogs, archives — and keep the pages you most want quoted in the main sections.

SEO

llms.txt Validator

Check an llms.txt against the spec at llmstxt.org — structure, link format, and the mistakes that make a file useless to an AI crawler.

100% free
No sign-up

Your llms.txt

What this tool does

Validates against the published llms.txt format
Every finding comes with the fix
Checks your live file or a pasted draft
Separates real errors from suggestions
Free, no account, no daily limit

Want the whole picture? Run a free website audit for a score and prioritised issues. No signup needed to start.Run a free audit

The short version

What is llms.txt Validator?

llms.txt is a markdown file at the root of a domain that tells AI assistants, in one place, what a site is and which pages are worth reading.

The format is published at llmstxt.org and it is strict about order, because a crawler reads it positionally: an H1 with the project name, a blockquote summarising the site, optional prose containing no headings, then H2 sections whose list items are markdown links with optional notes after a colon. This validator parses a file the way that spec describes and reports what is wrong, where, and what to change. It separates errors — a missing H1, a relative URL, a heading where prose should be, a list item that is not a link — from warnings and suggestions, because a file can be perfectly valid and still be doing a poor job of describing your site.

Step by step

How to use llms.txt Validator

1
Fetch or paste
Enter your domain to read the live /llms.txt, or paste a draft you have not published yet.
2
Fix the errors first
Errors mean a crawler will read the file differently from how you intended. Each one names the line and the change.
3
Then read the warnings
Warnings are valid-but-weak: a missing summary, a section with no links, a duplicate URL wasting the budget a model gives the file.
4
Check the read-back panel
The last panel shows the title, summary and sections a crawler extracts. If that does not describe your site, the file is not doing its job however valid it is.

What's inside

Everything this tool
does for you

Parses the published llms.txt format, not a guess at it
Line numbers on every finding
A concrete fix attached to every finding
Errors, warnings and suggestions kept apart
Catches relative URLs, duplicate links and prose headings
Shows what a crawler actually extracts from your file

Understand the result

Related free tools

All SEO tools

Meta Tag Generator

Import metadata from a URL or edit SEO and social tags, preview them, and copy the generated HTML.

SEO

Meta Tag Analyzer

Inspect page metadata, social tags, response directives and actionable fixes from a URL.

SEO

Open Graph Tag Generator

Generate Open Graph meta tags with live Facebook and LinkedIn preview.

SEO

Open Graph Checker

Check any URL's Open Graph tags and preview how links appear on social media.

SEO

Twitter Card Generator

Generate Twitter Card meta tags with live preview for summary and large image cards.

SEO

Robots.txt Generator

Build a robots.txt file with a visual editor. Add rules for any user agent.

SEO

Questions

Frequently asked questions

Beyond this tool

See the full picture for your website.

Enter your URL for a free audit across eight scored areas. See prioritised issues and clear next steps in one report.

Run a free website audit

Free to start · No signup required