Skip to content
Get started

llms.txt generator

Do4U reads your website and writes a ready llms.txt, the file that tells AI assistants what your website is about. You enter the address. Do4U reads the start page and your most important pages (the links in your menu first, then the sitemap), notes the title, description and beginning of each page, and the AI writes the name of your website, a short summary and one sentence per page, sorted into a few groups. The code builds the file in the llmstxt.org format and checks it: only pages that were really read are linked, web addresses and numbers that are not on the page are removed, and special characters are escaped. If your website already has an llms.txt, you see it next to the new one. You download the file or copy it; both happen in your browser.

Try it now Pricing

Who it is for

For website owners, agencies and shop operators who want AI assistants to find and describe their website correctly, without writing the file by hand.

Typical uses

  • Create a first llms.txt for a new website
  • Update an old llms.txt after a relaunch
  • See which pages of a website an AI assistant would read first
  • Prepare llms.txt files for the websites of several customers

Example

Input

Website address: https://www.example-bakery.com/ Pages read (start page and the links in the menu): / · /bread · /cakes · /about-us · /contact

Result

# Example Bakery > Family bakery in Berlin that bakes fresh bread, rolls and cakes by hand every morning. ## Products - [Bread](https://www.example-bakery.com/bread): Rye, spelt and wheat bread baked with sourdough. - [Cakes](https://www.example-bakery.com/cakes): Cheesecake, apple cake and seasonal tarts, made to order. ## About - [About us](https://www.example-bakery.com/about-us): The history of the family business since 1952. - [Contact](https://www.example-bakery.com/contact): Address, opening hours and phone number of the shops. The file is ready to download as llms.txt.

A fixed example, shortened. Real results are AI-generated: please check them.

Price and limits

Price
usually 1–3 credits
Available with
Free, With package
Input limit
One page with up to 300,000 characters of HTML

Privacy

Processed on our own servers in the EU (Poland). Inputs and results are deleted after 7 days (Free) or 30 days (packages), or right after you see the result if you choose not to store them. Images are deleted right after processing.

In the API

Tool name: llms_txt. Create a job with POST /api/v1/jobs and fetch the result with GET /api/v1/jobs/{id}. You find your API key in your account.

curl -X POST https://do4u.eu/api/v1/jobs \
  -H "Authorization: Bearer d4u_…" -H "Content-Type: application/json" \
  -d '{"tool": "llms_txt", "url": "https://example.com/"}'

Full API documentation →

Questions and answers

Which pages does Do4U read?

The address you enter, and in total only a few more pages of the same website: first the links in your menu, then the sitemap if there is one. Do4U reads about one page per second, as Do4U-Check, and follows your robots.txt. Login, cart, search and archive pages are skipped.

Can the AI invent pages or addresses?

No. The AI only sees the pages that were read and refers to them by number. The code writes the addresses, drops everything that was not read, removes web addresses and numbers that are not on the page, and checks the finished file against the llmstxt.org format.

Where do I put the file, and what if I already have one?

Save it as llms.txt in the main folder of your website, so that it opens at your-domain/llms.txt. If your website already has an llms.txt, Do4U shows it next to the new one and lists which pages are only in one of the two files.

Is my text stored?

Only as long as needed: 7 days on Free, 30 days with a package – or not at all if you choose not to store it. Processing happens on our own servers in the EU (Poland).

Can I use the result right away?

Results are AI-generated. Please read them before you publish or send them.

Related tools

  • FAQ and schema markup

    Writes FAQ entries from a page or support texts and builds valid JSON-LD for FAQPage, Organization, LocalBusiness and Product. The code checks the required fields and compares every detail with your source.

  • SEO title & description

    Three variants of page title and meta description, with the length checked.

All tools →