llms.txt filellms.txt is an emerging standard (llmstxt.org)
that gives large language models a concise, curated summary of your site — the way
robots.txt guides crawlers and sitemap.xml lists your pages.
When ChatGPT, Claude, or Perplexity look at your domain, an llms.txt tells
them what you do and where the important content is, in plain Markdown they parse easily.
It's a plain-text Markdown file: an # H1 with your site name, a
> blockquote one-paragraph summary, then sections of links. Here's a
template you can adapt:
# Your Company
> One or two sentences on what your company does and who it's for. Be concrete:
> the product, the audience, the core value. This is the summary an LLM will read first.
## Docs
- [Getting started](https://example.com/docs/start): set up in 5 minutes
- [API reference](https://example.com/docs/api): full endpoint list
## Product
- [Pricing](https://example.com/pricing): plans and limits
- [Changelog](https://example.com/changelog): what's new
## About
- [Company](https://example.com/about): team and mission
- [Contact](https://example.com/contact): how to reach us
Optionally also publish /llms-full.txt with the full text of your key pages
inlined, for models that want the complete content in one fetch.
It must be reachable at https://yourdomain.com/llms.txt — the root, exactly
like robots.txt. On most stacks, drop llms.txt into the folder
your server treats as the web root (e.g. public/, static/, or the
site root). Make sure it returns plain text, not your app's HTML 404 page.
Open https://yourdomain.com/llms.txt in a browser — you should see the raw
Markdown, not your homepage. Then re-grade your site to confirm the +25 landed.