Free tool
llms.txt generator
Tell ChatGPT, Claude, Perplexity and other assistants what your product is and which pages to read. Fill this in, copy the file, drop it at your site root. Nothing leaves your browser.
Key pages
# Your Product > One sentence on what this is and who it's for. ## Docs - [Pricing](https://yourproduct.com/pricing): What it costs - [Docs](https://yourproduct.com/docs): How it works
Save this as llms.txt at your site root, so it serves from https://yourproduct.com/llms.txt. It tells assistants what your site is and which pages to read — the same way robots.txt talks to crawlers.
Common questions
What is llms.txt?
A plain markdown file at your site root that tells language models what your site is and which pages are worth reading. Think robots.txt, but for assistants rather than crawlers — and instead of blocking, it curates.
Does it actually do anything yet?
It's a convention, not a standard any model is obliged to follow. Some assistants and agent frameworks fetch it; many don't yet. It costs you five minutes and one static file, and it's a well-structured summary of your site either way.
Where do I put the file?
At your site root, so it serves from yoursite.com/llms.txt as text/plain or text/markdown. If you use Next.js, a route handler at app/llms.txt/route.ts works.
Is this the same as robots.txt?
No. robots.txt controls which crawlers may fetch which paths. llms.txt doesn't grant or deny anything — it's a curated index that helps a model understand your site quickly. You want both.
Ours is live at /llms.txt if you want a real example to copy the shape of.