llms.txt Generator

Build a clean llms.txt file — the machine-readable map that helps AI systems like ChatGPT, Claude, and Perplexity understand and cite your site. Free, and it runs entirely in your browser.

How to use your llms.txt file

Save the generated text as llms.txt and upload it to your domain root so it is reachable at yoursite.com/llms.txt — the same way robots.txt is served. Keep it curated (your most important pages, not every URL) and current. It helps non-Google AI engines like ChatGPT, Claude, and Perplexity parse and cite your site accurately.

Learn the full method in our guide to llms.txt and machine-readable files for AI, and pair it with schema markup. Want a complete AI-visibility strategy? Explore our Answer Engine Optimization (AEO) and Perplexity AEO services.

Frequently asked questions

What is an llms.txt file?
llms.txt is a proposed standard: a curated Markdown file at your site root (yoursite.com/llms.txt) that gives AI systems a concise, structured map of your most important pages. It helps non-Google AI engines like ChatGPT, Claude, and Perplexity understand and cite your site accurately.
Where do I put the llms.txt file?
Save the generated text as a file named llms.txt and upload it to the root of your domain so it is reachable at yoursite.com/llms.txt, the same way robots.txt is served. Keep it accurate and update it when your key pages or positioning change.
Is llms.txt an official standard?
No. It is a community proposal, introduced by Jeremy Howard in 2024, and adoption is voluntary. No search engine or AI provider has committed to reading it, so treat it as cheap insurance rather than a ranking tactic.
How is it different from robots.txt or a sitemap?
robots.txt says what crawlers may fetch and a sitemap lists every URL. llms.txt is curated and descriptive: a short, human-written guide to what matters on your site and what each page covers.
How many pages should I include?
Enough to describe the site and no more, typically ten to forty URLs grouped under headings. The value is in the curation, so an exhaustive dump defeats the purpose.