Free tool · GEO
llms.txt generator
llms.txt is a Markdown file that introduces your site to language models: who you are, what you offer and which pages are worth reading. Create it in a minute from your own website.
It is an open proposal (llmstxt.org), not a standard: Google has said it does not use it and there is no evidence assistants read it systematically. Having one does no harm and costs little.
Would you rather we did it for you?
We run your site’s SEO every month: content, structured data, links and the technical side.
More free tools
AI visibility checker →
Whether ChatGPT, Perplexity, Gemini and Google can get into your site and whether your content is easy for AI to read and quote. Score from 0 to 100.
robots.txt generator and tester →
Create your robots.txt for WordPress, WooCommerce or Shopify with a clear policy for AI crawlers, and test which URLs each crawler can fetch.
Schema (JSON-LD) generator →
Create structured data of 15 types (local business, article, product, event, recipe, job…) or analyze a page and get its corrected schema.
How to use it
- Enter your website URL and press "Prefill": we take the name, the description and the menu links.
- Review the summary, add useful details and keep only the pages that best explain what you do, with a short description.
- Download the file and upload it to the domain root. In WordPress you can do it over FTP or with a file manager plugin.
FAQ
What is llms.txt?
A Markdown text file, proposed at llmstxt.org, that summarises a website for language models: a title, a summary and lists of links to the most useful pages.
Does it improve my ranking on Google or ChatGPT?
There is no evidence of that. Google has said it does not use it. What does matter is that AI crawlers can get into your site and that the content is clear.
How is it different from robots.txt?
robots.txt tells crawlers what they may crawl; llms.txt allows or blocks nothing, it only introduces your content.
What about llms-full.txt?
A variant with the full text of the pages in one file. It mostly makes sense for technical documentation.