Free llms.txt generator. Built from the pages that matter.

Enter your domain. We read your robots.txt and sitemap, sort every page by type, keep the ones a model should know about and write a file that passes the llmstxt.org spec. Then we check that AI crawlers are allowed to read it.

Checked against GPTBot, ClaudeBot, PerplexityBot and Google-Extended

Free, no card, no email. Up to 150 pages per file, 3 files a day.

Agency? Make one for every client site

acme.com/llms.txt · 42 of 1,180 pages kept

# Acme
 
> Acme makes electric toothbrushes and replacement heads for sensitive teeth and gums, sold online across the EU.
 
## Products
- [Sonic Pro 5](https://acme.com/sonic-pro-5): Pressure sensor, 5 modes, our best seller for sensitive gums
- [Brush heads](https://acme.com/brush-heads): Soft, deep clean and whitening heads in packs of 4
 
## Help
- [Shipping and returns](https://acme.com/shipping): EU delivery in 2 to 4 days, 30-day returns
- [Which brush is for me?](https://acme.com/guide): Compares every model by gum sensitivity
 
## Optional
- [Blog](https://acme.com/blog): Dentist-reviewed guides on brushing and gum care

Passes the llmstxt.org spec

96/100
Example file. You get all of it: nothing cut, no link back to us.

What you get

The file, a score, and what would stop AI reading it.

Every file is checked against the llmstxt.org spec and scored out of 100. Then we read your robots.txt for the bots that would fetch it, because a perfect llms.txt behind a Disallow line is never read.

Spec checks

96 / 100

  • One H1 with the site name
  • A one-line summary in a blockquote
  • Pages grouped under named sections
  • Absolute URLs, no duplicates
  • A description on every link
  • No login, cart or account pages

1 to fix: 3 descriptions are under 20 characters.

AI crawler access

robots.txt

  • GPTBot OpenAI · training
    Allowed
  • OAI-SearchBot ChatGPT search
    Allowed
  • ClaudeBot Anthropic
    Allowed
  • PerplexityBot Perplexity search
    Blocked
  • Google-Extended Gemini
    Allowed

Blocked by line 11 of robots.txt: Disallow: / for PerplexityBot. Remove it and Perplexity can read your site again.

Three files, three jobs

llms.txt does not replace robots.txt or your sitemap.

Most sites should have all three. Only one of them tells a model what your pages are about.

How robots.txt, sitemap.xml and llms.txt differ
Property robots.txtsitemap.xmlllms.txt
Written for CrawlersSearch enginesLanguage models
Says What may be fetchedEvery URL you haveWhat your key pages are about
Format DirectivesXMLMarkdown
Describes pages NoNoYes
Read today by Every major crawlerGoogle and BingNo engine has confirmed it yet

Ten seconds, three steps.

Nothing to install, nothing to sign. The same crawler and page types our site audit uses.

  1. 0 s

    Drop in your domain

    We read robots.txt and your sitemap, nested sitemap indexes too. No sitemap? We follow the links from your home page.

  2. about 5 s

    We type every page

    Product, category, pricing, docs, guide, legal. Login, cart, tag and paged URLs are dropped before anything is written.

  3. about 10 s

    We write and check it

    Titles without the brand suffix, a description on every link, sections named after what is in them. Then the spec and crawler checks.

Output quality

Most generators paste your sitemap and call it done.

That is how a login page ends up under a heading called “Kb”. Ours is written to be read.

Sections named after what is in them

Products, Help, Pricing, Guides. Never “Pages 1”.

Typed, not guessed

Each page gets one type from its HTML, so a product sits with products and a policy with policies.

Descriptions that say something

Empty or boilerplate meta descriptions are rewritten from the page itself.

No login, cart or checkout

Account, cart, checkout, tag and paged URLs never make the file.

Crawler access checked

We read robots.txt for GPTBot, ClaudeBot, PerplexityBot and Google-Extended and name the line that blocks them.

No watermark, no wall

The whole file, free, with no link back to us inside it.

Publishing

Put it at yourdomain.com/llms.txt.

Same place as robots.txt. Open the URL after you upload it: you should see plain text, not a web page.

  1. 01

    WordPress

    Upload it to the site root, next to wp-config.php. Not into wp-content.

  2. 02

    Shopify

    Upload it under Content › Files, then redirect /llms.txt to the file.

  3. 03

    Webflow

    Upload the file, then add a redirect from /llms.txt.

  4. 04

    Next.js, Nuxt, Astro

    Put it in public/llms.txt and deploy.

  5. 05

    cPanel or shared hosting

    public_html/llms.txt

  6. 06

    Any static host

    Commit it to the folder your site is served from.

A file today. Proof it works next month.

The generator writes the file once. RankRush checks every week whether AI reads your pages, cites them, or names someone else.

Free generator

€0

one file


  • Up to 150 pages, typed and described
  • Spec check, scored out of 100
  • AI crawler check on your robots.txt
  • Copy or download. No login, no email
Generate my llms.txt

RankRush

3-day free trial

from €59

per month


  • llms.txt and crawler access re-checked on every site audit
  • Weekly scans on ChatGPT, Gemini and Google AI Overviews
  • Which of your pages AI cites, and who it names instead
  • Site audit and a weekly list of fixes in Actions
  • Articles written and published from Publish
Start your free trial

Rather have it fixed for you?

Our GEO team runs the audit, ships the fixes and the content, and reports what changed in AI answers every month. You approve, we do the work.

3,042%

organic traffic growth on a campaign run by our founding team, before RankRush productized it

Same team, same playbook, now pointed at AI answers.

Questions about llms.txt.

Want it kept up to date? See RankRush

Is llms.txt an official standard?

No. It is a proposal from llmstxt.org, published in 2024. No standards body has adopted it and no AI company has said its crawler reads it. It takes minutes to publish, so many sites add it anyway.

Will llms.txt get me cited by ChatGPT?

Not on its own. AI engines cite pages that answer the question and that their crawlers can reach. The crawler check matters more than the file: a blocked GPTBot reads nothing.

Does Google use llms.txt?

Google has said it does not use llms.txt for Search or AI Overviews. Google-Extended in robots.txt is what controls Gemini’s use of your pages.

How many pages go into the free file?

Up to 150. We show how many pages we found and how many made the file, so you can see what was left out.

What if my site has thousands of pages?

We keep the pages a model should know first: products, categories, pricing, guides and help. A large shop can split its catalogue into its own file.

What is llms-full.txt?

A second file with the full text of the listed pages in one place. It is optional, much larger, and we do not generate it yet.

Do you store my site?

We fetch public pages only, to write your file. No account, and nothing is shared.

Your llms.txt in ten seconds.

Enter your domain. Copy the file, upload it, and see which AI crawlers your robots.txt lets in.

Agency? Make one for every client site

What blocks AI

acme.com/robots.txt · read for AI crawlers

# robots.txt
 
User-agent: *
Disallow: /cart
Disallow: /account
 
User-agent: GPTBot
Allow: /
 
User-agent: PerplexityBot
Disallow: /
 
Sitemap: https://acme.com/sitemap.xml

Line 11 blocks PerplexityBot from your whole site

Blocked