llms.txt generator
Build your site's llms.txt from your sitemap and your metadata, without inventing descriptions.
Why we do not fill in the descriptions
A generator that invents a believable sentence for each link produces a file that describes your site badly, with total confidence, in the one format designed to be read by a machine.
Here we only write what we actually read: your home page title and its meta description. The rest is left blank for you to complete, which is exactly the work that gives the file its value.
What we read from your site
Three files: the home page, for the title and description; sitemap.xml, to find out what pages you have; and any llms.txt you already had, so we can warn you it exists before you overwrite it.
We do not download every one of your pages to read its title. That would be dozens of requests to your server every time somebody presses the button, and that is what a crawler does, not a tool.
What to expect from this file
Not much, as of today, and it is worth saying so. None of the big engines has committed to reading it. OpenAI, Anthropic and Perplexity crawl the web with their own bots and do not document llms.txt changing anything.
Publishing it costs five minutes and does no harm. Mistaking it for a visibility lever does do harm, because it takes time away from what actually works: your pages answering specific questions, and your entity being identified.
This tells you whether they can read you. Not whether they name you.
The three checks here rule things out: they tell you whether something is stopping you from appearing in an answer. Whether you actually appear, and who appears instead of you, has to be measured by asking the models. The scanner does that free in about a minute.