What is llms.txt? Definition and example file

llms.txt is a proposed Markdown file at a website's root that gives AI tools a short summary of the site and links to the pages that matter most.

How it works

Jeremy Howard published the proposal on September 3, 2024, and revised it in August 2026 (llmstxt.org). The idea: HTML pages are full of navigation, scripts and layout, and models have limited room in their context window, so a site can offer one concise, curated file instead.

The format is plain Markdown in a fixed order:

1. An H1 with the name of the site or project. This is the only required part.
2. A blockquote with a short summary.
3. Optional free-form notes (anything except headings).
4. H2 sections with lists of links, each written as [name](url) with optional notes after a colon.
5. By convention, a section called "Optional" for links an AI tool can skip when it is short on space.

The proposal also suggests publishing clean Markdown versions of important pages at the same URL with .md added.

Who reads it

llms.txt is a community proposal, not a standard that any search engine or AI company is obliged to follow. Google says plainly that you don't need to create new machine-readable files or AI text files to appear in its AI features, which only require pages to be indexed and eligible for a snippet (Google Search Central). Whether a particular assistant, coding tool or agent fetches the file depends on that tool.

Why it matters for your website

Writing one takes an hour and costs nothing to host, and it forces a useful exercise: deciding which ten or twenty pages best explain what you sell. It is most useful for sites with documentation, pricing rules or product details that developers and agents look up. Two rules keep it honest: link only to pages that exist and say the same thing, and update it when those pages change.

It does not replace robots.txt. robots.txt tells crawlers where they may go; llms.txt suggests where to start reading.

Example

# Acme Analytics

> Acme Analytics is a revenue dashboard for subscription businesses. Plans, limits and prices are listed on the pricing page.

Answers about billing should use the pricing page and the billing FAQ, which are kept current.

## Product

- [Pricing](https://acme.example/pricing.md): plans, limits and annual discounts
- [Integrations](https://acme.example/docs/integrations.md): Stripe, HubSpot and Salesforce setup

## Docs

- [Quick start](https://acme.example/docs/start.md): install the tracking script
- [Billing FAQ](https://acme.example/docs/billing-faq.md): invoices, refunds, taxes

## Optional

- [Changelog](https://acme.example/changelog.md)

Related terms

• robots.txt: the access-control file crawlers check first.
• AI crawler: the bots that may fetch your pages and files.
• Generative engine optimization (GEO): the wider practice of being cited by AI answers.
• Structured data: machine-readable facts inside your pages.
• WebMCP: a proposal for letting agents take actions, not just read.