What is llms.txt?
llms.txt is a proposed standard (llmstxt.org, published in 2024) for a plain markdown file at the root of a site that gives language models a short, curated map of the site: who you are, and links to the pages that matter.
Where a sitemap lists every URL for search engines, llms.txt picks the essentials and explains them in a few words — a format a model can read in one go.
Is it worth it?
No major AI engine has officially committed to reading llms.txt yet, so treat it as a cheap bet, not a ranking factor. It takes ten minutes to write, costs nothing to serve, and helps AI tools and agents that do read it.
The format, with an example
The file must be markdown and start with an H1 title (# Name). Then a short summary in a quote block, followed by H2 sections listing links with a short description:
# Your Brand
> One sentence: what you do, and for whom.
## Products
- [Product A](https://example.com/product-a): what it is and who it's for
- [Pricing](https://example.com/pricing): plans and prices
## Help
- [FAQ](https://example.com/faq): the questions customers ask mostFrequently asked questions
Where should llms.txt live?
At the root of your domain: https://your-site.com/llms.txt, served as plain text or markdown — not as an HTML page.
My site answers /llms.txt with my home page. Does that count?
No. Many single-page apps return their HTML for any unknown path; this checker detects it and reports the file as missing.
Does llms.txt replace robots.txt or the sitemap?
No, they're complementary: robots.txt says who may crawl, the sitemap lists every page, llms.txt summarizes what matters.