A markdown file served at /llms.txt that summarizes a website for large language models: what it is, and links to the pages that matter most.

Do AI companies read llms.txt?

It is a community proposal, not an official standard, and no major AI provider has committed to using it. It costs minutes to add, and AI coding tools and agents increasingly fetch it.

Does llms.txt replace robots.txt or a sitemap?

No. robots.txt controls crawler access, sitemap.xml lists every URL, and llms.txt is a short curated summary. Keep all three.

What is llms.txt, and how do you add one?

A two-minute file that tells AI models what your site is and which pages matter.

The short answer

llms.txt is a plain markdown file served at the root of your domain (https://yoursite.com/llms.txt). It gives large language models a short, curated summary of your site, instead of making them guess from navigation menus, cookie banners and JavaScript. The format was proposed by Jeremy Howard of Answer.AI in 2024.

The format

Only the first line is required. In order:

An # H1 with the name of the site or project.
A > blockquote with a one- or two-sentence summary.
Optional paragraphs with anything else a model should know.
Optional ## sections, each a list of links: - [Title](url): note. A section called ## Optional marks links a model can skip when context is short.

Copy-paste example

# Acme Plumbing

> Acme Plumbing is a licensed plumber serving Brisbane, Australia.
> 24/7 emergency call-outs, hot water systems, and blocked drains.

Prices on the site are in AUD and include GST.

## Services
- [Emergency plumbing](https://acme.example/emergency): 24/7, 1-hour response
- [Hot water systems](https://acme.example/hot-water): repair and install

## Company
- [About us](https://acme.example/about): licences and service area
- [Contact](https://acme.example/contact): phone, email, booking

## Optional
- [Blog](https://acme.example/blog)

How to publish it

Static sites and most hosts

Put the file in your public or web root folder so it is served at /llms.txt with a text/plain or text/markdown content type.

WordPress, Shopify, Wix and other CMSs

Use the platform's file manager or an llms.txt plugin. Whatever you use, open yoursite.com/llms.txt in a browser afterwards: you should see raw text, not your home page. Many CMSs return the home page with a 200 status for unknown paths, which looks like success but is not.

Frequently asked questions

Do ChatGPT, Claude or Google actually read it?

Honestly: it is a community proposal, not an official standard, and no major AI provider has committed to using it for search answers. AI coding assistants and agents do fetch it, and it costs minutes to add. Treat it as cheap insurance, not a ranking switch.

Does it replace robots.txt or my sitemap?

No. robots.txt decides which crawlers may enter, sitemap.xml lists every URL, and llms.txt is the short guided tour. Keep all three.

What about llms-full.txt?

Some sites also publish /llms-full.txt with the full text of their docs in one file. Useful for documentation sites; unnecessary for most small business sites.

Check yours

Aeoray checks whether your llms.txt exists and is real text rather than an HTML page, alongside six other AI-visibility signals.

Scan your site free

More guides: allowing AI crawlers in robots.txt · JSON-LD for AI answers · the full AEO checklist.