llms.txt generator: create the file from your own pages

Paste your site and get a draft llms.txt built from your home page and up to ten other pages, ready to copy or download, with every gap marked instead of guessed.

Reads up to eleven public pages. Takes up to ten seconds. Nothing is stored.

How to create an llms.txt file in five steps

  1. Get a draft. Paste your address above. You get a file in the right shape with real titles and descriptions from your pages.
  2. Fill the gaps. Search the draft for [fill in and write each missing fact, or delete that line.
  3. Choose what goes in. Keep the pages a buyer needs to decide: services, prices, areas you serve, how to get in touch. Leave out tag archives, login pages and legal boilerplate.
  4. Put it at the root. Save it as plain UTF-8 text named llms.txt so it opens at yoursite.com/llms.txt. Some hosted website builders do not let you place a file at the root; check your platform's help first, because a file at any other address is not read as llms.txt.
  5. Regenerate when pages change. Rename a page or retire a service and the old line now points at nothing. Run the generator again, or build the file from your content on every deploy.

What goes in each section

The draft groups your pages by the part of the site they live in, and puts pages that stand alone under Pages. When you tidy it, a small business usually aims for sections like these:

SectionWhat belongs thereOne line, for example
Start hereThe home page and the one page that explains the business bestwhat we do, for whom, in which city
ServicesOne line per service, each with its own pagewhat an implant costs and how many visits it takes
PricesThe page with prices or how you quotefixed prices for check-ups, a range for implants
GuidesAnswers to the questions buyers ask before they callhow to choose between a crown and a veneer
ContactPhone, email, address, the area you servefilled from your page markup and links

Write each line for a reader deciding which two of your pages to open. "Our services" says nothing; "what an implant costs and how many visits it takes" says why to click.

How this draft is different

Many llms.txt generators ask an AI model to write the descriptions. That reads well and is often wrong: a model that does not know your business fills the gaps with plausible guesses, and those guesses then sit in the one file meant to be a reliable summary of your site.

This one copies. Each line comes from the page it links to: its title or main heading, its meta description or first paragraph. Your name comes from your markup or your og:site_name. Your phone and email come from the tel: and mailto: links on your home page. What is not there stays visibly empty.

What a finished llms.txt looks like

# Harbor Dental Studio

> Family and cosmetic dentistry in Portland, Oregon: check-ups, implants and same-day crowns.

## Services

- [Dental implants](https://example.com/implants/): what an implant costs, how many visits it takes, who is a candidate
- [Same-day crowns](https://example.com/crowns/): one-visit crowns made in the clinic

## Contact

- Phone: +1 503 555 0100
- Address: 12 Harbor St, Portland, OR

An invented example. One heading with the name, one line saying what you do and where, then sections of links with a line each.

llms.txt, robots.txt and sitemap.xml: three different files

FileWho reads itWhat it says
robots.txtEvery well-behaved crawler, before it fetches anythingWhich robots may read which parts of the site
sitemap.xmlSearch enginesEvery address you want indexed, with dates
llms.txtPrograms that choose to look for itThe few pages worth reading, each with a line on what is there

You need all three for different reasons, and none replaces another. A page closed in robots.txt stays closed whatever llms.txt says about it: the AI crawler checker shows which robots are let in.

llms.txt or llms-full.txt?

This tool writes llms.txt: the short map, a line per page. Some sites also publish llms-full.txt, the whole text of those pages in one file, for a reader that wants everything in a single request. Start with the map. A full-text file only makes sense when it is rebuilt automatically from your pages, because a copied one goes stale even faster.

Is it worth making one?

It is cheap, so yes, but keep expectations low. In our study of 731 websites, 84 of 172 English-language sites (49%) already had the file.

ChatGPT named sites that had one in 32% of cases and sites without one in 36%. The file makes the right pages easy to find for a program that reads it; whether you are recommended is decided mostly elsewhere.

A file is the easy part. Does ChatGPT name you?

llms.txt tidies your site for machines; it does not make an assistant recommend you. The free OperStack check scores how readable your site is and asks ChatGPT your buyers' questions to see whom it names.

Run the free AI visibility check →

Related free tools

All free tools · Our study of 731 websites

Questions

How do I create an llms.txt file?

Paste your address above to get a draft, replace every [fill in: ...] with the real fact, add the pages a buyer most needs, save it as plain UTF-8 text named llms.txt and upload it to the root of your site. The format itself is described at llmstxt.org.

Will llms.txt get me into ChatGPT answers?

Do not count on it. In our study of 731 websites, ChatGPT named sites with an llms.txt in 32% of cases and sites without one in 36%: no noticeable difference. The file keeps a site tidy for machines that choose to read it. It does not decide who gets named.

Does Google use llms.txt?

Not for Search. Google says you do not need new machine-readable files or AI text files to appear in AI Overviews and AI Mode (Google: AI features and your website). Rankings are not affected either way.

Where does the text in the draft come from?

Only from your pages: the title or main heading of each page, its meta description or first paragraph, and contact details from your markup, phone and email links. Nothing is written by an AI model and nothing is guessed. Where a fact was not on the pages, the draft says [fill in: ...] so you can see what is missing.

How many pages does it read?

Your home page and up to ten more, taken from your sitemap or, if there is none, from the links on your home page, with no more than three from one section so the draft shows the whole site. Twelve requests at most, all within about eight seconds. A big site needs a fuller file: the free OperStack Astro starter builds one from the whole site on every deploy.

Do you keep the file or the address?

No. The draft is built while the page loads and shown only to you. The download button makes the file in your browser. Nothing is written down on our side, and there is no account or cookie.

Built by Maksim Shchegolev, founder of OperStack. Free, no account, no cookie. The address you check is not stored.