llms.txt

llms.txt is a community proposal for a Markdown file, served at /llms.txt on a website's root, that gives language models and other AI tools a short, curated overview of a site and links to its most useful pages. It was proposed by Jeremy Howard of Answer.AI, and the proposal is documented at llmstxt.org.

It is a proposal, not a formal internet standard. Check the proposal text for the current details before you rely on any of them.

The proposed format

The proposal describes a plain Markdown file with a simple structure:

• H1 title: The name of the site or project. This is the only required element.
• Blockquote summary: A summary of what the site or project is.
• Optional prose: Paragraphs or lists with extra context for the reader. These sections should not contain headings.
• H2 link sections: Each section groups links in the form - [Page title](url): short description.
• ## Optional section: By convention in the proposal, links here are secondary and can be skipped when a shorter overview is needed.

Sample

The following example follows the proposed structure. The URLs are placeholders.

# Example Project
 
> Example Project is an open-source library for parsing and validating configuration files.
 
The documentation covers the current major version. Older versions are archived.
 
## Documentation
 
- [Getting started](https://example.com/docs/start): Installation and a first working example.
- [API reference](https://example.com/docs/api): Functions, parameters, and return values.
- [Configuration formats](https://example.com/docs/formats): Supported file formats and their limits.
 
## Optional
 
- [Changelog](https://example.com/changelog): Release history.
- [Contributing](https://example.com/contributing): How to report issues and submit changes.

Adoption limits

• Not a standard: llms.txt has not been adopted as a standard by a standards body such as the IETF or W3C.
• Not required: No search engine or AI provider is obliged to read it, and websites work normally without it.
• Support varies: Some tools and documentation platforms read or generate the file, and many do not. Check the documentation of the specific tools you care about rather than assuming support.
• No guaranteed crawling: Publishing the file does not mean any crawler or assistant will fetch it.
• No guaranteed effect: It should not be relied on to change search rankings or to cause AI tools to cite your pages.
• Keep it current: A file that points to outdated or removed pages can mislead its readers.

llms.txt vs robots.txt

The two files are often confused, but they do different jobs.

llms.txt does not allow or block anything. To control which crawlers may access your site, use robots.txt along with your server's access controls.

For setup steps, see our llms.txt implementation guide.