llms.txt is a plain-text file you place at the root of your site
(yoursite.com/llms.txt) that gives large language models a clean, curated map and
summary of your most important pages. It was proposed by Jeremy Howard of Answer.AI in 2024 as a
convention; adoption is still emerging, but it is low effort and forward-looking.
Why it helps
A normal web page is full of navigation, ads, and scripts that make it noisy for a model to read. llms.txt gives an assistant a short, human-readable index of what matters on your site and where to find it, in clean Markdown, so it can represent you more accurately. Think of it as a curated table of contents written for AI, complementing (not replacing) your sitemap.
The format
It is just Markdown, with a simple shape:
- An
#H1 with your site or brand name. - A
>blockquote with a one-line summary of what you do. ##sections grouping links to your key pages, each as a Markdown link with a short description.
An example
# Acme Analytics
> Acme Analytics is privacy-first web analytics for small teams.
## Key pages
- [Product](https://acme.example/product): what Acme does and who it is for.
- [Pricing](https://acme.example/pricing): plans and what each includes.
- [Docs](https://acme.example/docs): setup and API reference.
## About
- [Company](https://acme.example/about): who we are and how to reach us.Some sites also publish an llms-full.txt with the full text of key pages inlined, for
models that want more context. Keep the main llms.txt short and curated.
How to publish it
- Create a file named
llms.txt. - Fill in your brand line, summary, and links to your most important pages.
- Upload it to your site root so it is reachable at
yoursite.com/llms.txt. - Verify it loads as plain text (not an HTML error page).
llms.txt vs robots.txt vs sitemap.xml
- robots.txt sets access rules for crawlers (who may fetch what).
- sitemap.xml lists every URL for search engines to crawl.
- llms.txt is a short, curated, human-and-LLM-readable summary of your best pages.
They are complementary. You want all three. You can see a live example at crawlyze.com/llms.txt.