Start free trial Dashboard →
Free tool

llms.txt generator and checker

Enter your site and get an llms.txt built from your own pages: grouped into sections, with titles and descriptions, and checked against the llmstxt.org format. Or check the file you already have.

Try:

Free. No signup, no email, nothing added to the file. Reads your sitemap and up to 40 pages, in 10 to 30 seconds.

Example result · acme.com, illustrative

Your llms.txt, with 4 pages.

4pages listed, of 214 in the sitemap
3sections
7 of 7format checks passed
# Acme

> Acme makes scheduling software for clinics: online booking, reminders and a shared calendar for front desks.

## Product

- [Online booking](https://acme.com/booking): Patients book and reschedule without a phone call
- [Reminders](https://acme.com/reminders): Text and email reminders that cut no-shows

## Docs

- [Getting started](https://acme.com/docs/start): Set up your clinic in fifteen minutes

## Optional

- [Blog](https://acme.com/blog): Guides for running a clinic front desk

Built from your own pages

It reads your sitemap, keeps the pages that matter across every section, and takes each title and description from the page itself.

Checked against the format

Every file is tested against the llmstxt.org format before you see it, and an existing file gets the same checks.

Links that still open

The checker opens a sample of the links in your file and lists any that are broken, so the map never points at a dead page.

The format

What goes in an llms.txt

The format is small on purpose. One heading with the name of the site, one line that says what it is, then sections of links with a short note on each. Secondary pages, like the blog archive or legal pages, go under a section called Optional, which a model can skip when it is short of space.

FileWritten forWhat it says
robots.txtAll crawlersWhat they may and may not fetch
sitemap.xmlSearch enginesEvery page, for discovery
llms.txtAI models and agentsWhat the site is and which pages to read first
How it works

How the generator builds your file

It starts from your sitemaps, following sitemap index files, or from your homepage links when there is no sitemap. It leaves out pages that carry nothing for a model: login and account pages, carts and checkout, tag archives, pagination, feeds, and anything marked noindex. From what is left it keeps your homepage and your most important pages, spread across the sections of the site so one large blog cannot crowd out everything else.

Each page's title and description come from the page itself, with the site name trimmed from titles, since it is already the file's heading. Pages that share a section of your site, like /docs or /products, are grouped under that heading. The file is then checked against the format before you see it.

Publishing

Publishing it

Save the file as llms.txt and serve it from the root of your domain as plain text, so it opens at yourdomain.com/llms.txt. Then run the checker on the live address to confirm it is found and its links open. Keep it short and edit it by hand: you know better than any generator which pages should be first.

Limits

What llms.txt will not do

It will not make an AI engine cite you, and it will not unblock a crawler that robots.txt or your firewall keeps out. For that, run the AI crawler checker. To see which AI answers cite your site today, run the free AI visibility audit.

FAQ

Questions

Is this llms.txt generator free?

Yes. No signup, no email, and nothing added to the file. Generate as many as you like, within a fair-use limit per minute.

What is llms.txt?

A markdown file at the root of your site, /llms.txt, that tells AI models what the site is and which pages matter. It follows a proposal published at llmstxt.org: a # title, a one-line > summary, then ## sections of links.

Do ChatGPT, Claude or Google actually read llms.txt?

None of the big AI companies has said its crawler relies on it, so treat it as a cheap, low-risk addition rather than a ranking switch. It is read by AI coding tools and agents that look for it, and it costs a few minutes to add.

How does the generator pick pages?

It reads your sitemaps, or your homepage links if you have none. It drops pages a model gains nothing from, such as login, cart, tags, pagination and feeds, keeps the most important pages spread across your site's sections, and reads each page's own title and description. Pages marked noindex are left out.

Why does it stop at 40 pages?

A file listing thousands of URLs is less useful to a model, not more. The point is a short map of what matters. Edit the file to add anything the generator left out.

Where do I put the file?

At the root of your domain, so it answers at yourdomain.com/llms.txt as plain text. On WordPress, upload it to the site root or use an SEO plugin that serves it; on Webflow, Shopify and similar hosts, use their custom file or redirect settings.

What does the checker test?

That the file is plain text rather than a web page, opens with one # heading, has a > summary, groups links under ## sections, writes links as - [Title](URL), uses full URLs, and that a sample of those links still open.

What is the difference between llms.txt, robots.txt and a sitemap?

robots.txt says what crawlers may fetch. A sitemap lists every page for search engines. llms.txt is a short, curated summary of what the site is and which pages to read first, written for AI models.

Free tools

More free tools

  • AI Crawler Checker See which AI crawlers can read your page, and what blocks the ones that can't.

See what the agent
would fix.

Try it on your own sites for 14 days. No card needed.

Start free trial → Book a demo