llms.txt Generator

Paste a URL and get a ready-to-serve llms.txt file, built from the site's own title, description and sitemap.

What is llms.txt?

llms.txt is a plain-text file at the root of your site that tells AI assistants what your product is and which pages matter. Where robots.txt says what a crawler may fetch, llms.txt says what a language model should read first: a one-line description of the product, then a short list of titled links to the pages that explain it. It exists because assistants answer questions from a handful of retrieved pages, and a marketing site buried in client-rendered markup gives them nothing to retrieve.

Where to put the file

Serve it at yourdomain.com/llms.txt. In a Next.js, Vite or Astro project that means dropping it in public/llms.txt; on a static host it goes in the web root. Nothing needs to import it and no build step has to know about it, which is why this takes a minute rather than a sprint.

What this generator does, and what it cannot do

It fetches your page once, reads the title, meta description and the same-origin links, falls back to your sitemap when the page is client-rendered, and lays the result out in the conventional llms.txt sections. It does not invent features, pricing or claims, so read the output before you publish it and add the three or four lines only you know: what the product replaces, who it is for, and what it costs.

Does llms.txt actually get read?

No assistant has committed to reading it, and anyone telling you otherwise is guessing. What it does reliably is force you to write a retrievable, one-screen description of your product, which is the same text that helps every other discovery surface: search snippets, directory listings and the comparison pages people reach for when they are choosing between you and a rival. That is worth the minute whether or not the file itself is ever fetched.