llms.txt generator

Fill in your site name, a one-line description and the pages that matter, and this tool builds a valid llms.txt file you can copy straight to the root of your domain. It runs in your browser, needs no account, and sends nothing anywhere.

Key pages

Your file

# Your site

What llms.txt is

llms.txt is a plain Markdown file at the root of your domain — yoursite.com/llms.txt — that tells an AI reader, in your own words, what the site is and which pages are worth reading first. It is a proposal, not a ratified standard: no model provider has committed to reading it, and it will not, by itself, bring you traffic.

It is still worth ten minutes. The file is tiny, it costs nothing to serve, and it is the only place where you get to state plainly what your product is instead of leaving a crawler to infer it from navigation and marketing copy. It does not block anything, either: keeping a crawler out is the job of robots.txt.

How to use the file you get

Save the output as a file named exactly llms.txt and deploy it at the root of your domain, next to robots.txt. Tools look for that exact path; a copy in a subfolder will never be found. On Next.js you can serve it from a route; on a static host it is an upload; on WordPress it goes in the web root via the file manager or SFTP.

Then check it the boring way: open the URL in a browser and confirm you get plain text and a 200, not a redirect or your 404 page. Regenerate it when the facts change — a file that lists pages you deleted is worse than no file.

What this generator is not

  • It is not a guarantee that any assistant will read the file. Support for llms.txt is voluntary and, today, largely aspirational.
  • It does not crawl your site or discover pages for you. You choose which pages matter — that judgement is the valuable part.
  • It does not deploy anything. You copy the text and put it live yourself.

Questions about llms.txt

Where exactly does the file go?
At the root of your domain, as https://yoursite.com/llms.txt, served as plain text with a 200 status. The same place robots.txt lives. A file at /docs/llms.txt or /public/llms.txt is not found by anything looking for the standard path.
How many links should I list?
Few enough that every one earns its place — usually between five and twenty. The point of the file is curation: a list that mirrors your entire sitemap tells a reader nothing about what matters, which is exactly what the file exists to communicate.
Does llms.txt block AI crawlers from my content?
No, and this is the most common misunderstanding about it. The file is an invitation, not a fence. It cannot forbid crawling or training. If you want to keep a specific crawler out, that belongs in robots.txt with its user-agent rules.
Do I still need a sitemap and Schema markup?
Yes. They do different jobs: robots.txt controls access, sitemap.xml lists everything for search engines, Schema describes entities inside a page, and llms.txt curates the best of the site for AI readers. Three of the four are settled infrastructure; llms.txt is the bet.

Related