HomeResourcesThe llms.txt standard: the official specification — always current

Standard

The llms.txt standard: the official specification — always current

· updated · 6 min read

The llms.txt standard is a deceptively simple idea: a Markdown file at /llms.txt that gives AI systems a clear, curated map of your most important content — instead of leaving them to guess from randomly crawled HTML. So you never rely on an outdated summary, we mirror the official specification live here: when the standard changes at the source, this section changes with it automatically.

The official specification — live

This is the official llms.txt specification by Jeremy Howard, first published on Sep 3, 2024. It is pulled live from the canonical source and refreshes automatically — so this overview stays in sync with the standard itself.

From the specification: Agents now use websites constantly: a coding agent fetches a library’s documentation to get an API call right, and a chat assistant with search reads pages to answer questions about a product. When this proposal was first written in 2024, this was largely a prediction. Today it is routine. But web pages are built for people. An HTML page wraps its information in navigation, ads, and JavaScript, and converting it back into clean text is difficult and imprecise. Context windows, while larger than they were, are still too small for most websites in their entirety, and every wasted token costs ti…

What the standard covers:

Background  ·  Proposal  ·  Format  ·  Section name  ·  Optional  ·  Existing standards  ·  Example  ·  Docs  ·  Examples  ·  Directories  ·  Integrations  ·  Next steps

Source: the official specification at llmstxt.org — refreshed automatically · last change detected Aug 11, 2026.

Why a standard at all?

Language models increasingly rely on website content, yet struggle with limited context windows and HTML bloated with navigation, ads and JavaScript. llms.txt solves this as elegantly as robots.txt once did for search engines: you provide a concise, link-rich overview — and the machine gets the essentials immediately, in the order you choose.

Implemented in three steps

  1. Create: gather your project name, description and key links — fastest with our llms.txt generator or from ready-made templates.
  2. Validate: use the validator to confirm the file is reachable and spec-compliant.
  3. Publish & keep current: place the file at your domain root (https://your-domain.com/llms.txt) and update it on major changes. To stay visible, also list yourself in the directory.

Always current, with zero upkeep: the section above is pulled automatically from the canonical source; when the standard changes, this page's modified date moves with it — readers stay current and search engines reliably detect fresh content.

Free live checkAre you already cited by ChatGPT?Enter your domain — see live whether AI names your website as a source, or your competitor.Check now →

Ready to get found by AI?

Check in seconds how well AI systems read your website — or list yourself in the directory for free.

List your website for free →

All resources