What Is llms.txt? Format, Example & Generator

What llms.txt is for

Web pages are built for people and browsers: navigation, scripts, cookie banners, and layout around the content. An AI system working within a limited context window benefits from a short, clean map of what matters. llms.txt provides that map: who you are, in one or two sentences, and links to the pages that explain your product, documentation, pricing, and policies.

It complements robots.txt and your XML sitemap rather than replacing them. robots.txt says what crawlers may access. A sitemap lists every URL. llms.txt picks the few pages that best explain the site and describes each one.

The llms.txt format

The proposal at llmstxt.org defines a simple Markdown structure, in this order:

An H1 with the name of the site or project. This is the only required part.
A blockquote with a short summary of what the site is.
Optional paragraphs or lists with more detail, without headings.
Sections under H2 headings, each holding a list of links in the form “- [Page name](URL): short description”.
An optional section titled “Optional” for pages an AI system can skip when it needs to keep context short.

An llms.txt example

A minimal file for a software company looks like this: “# Example Co”, then “> Example Co makes invoicing software for small agencies.”, then a “## Product” section with links such as “- [Features](https://example.com/features): what the product does”, a “## Docs” section with setup and API pages, and an “## Optional” section with the blog or changelog.

Keep descriptions factual and short. Link only to pages that are public, stable, and useful on their own. The free Digraph llms.txt generator builds a correctly formatted file from your inputs.

Do AI systems actually use llms.txt?

Support is uneven, and providers change their behavior over time. Google’s guidance for AI Overviews and AI Mode says there are no extra requirements beyond normal Search eligibility and does not mention llms.txt, so do not expect it to change Google AI results. Some AI tools, coding assistants, and documentation platforms read llms.txt when a user or agent points them at a site.

That makes llms.txt low-cost and low-risk, but not a substitute for the work that does move AI answers: crawlable pages, clear content, accurate facts, and mentions on sites AI systems trust.

How to add llms.txt to your site

Creating the file takes a few minutes. Keeping it accurate is the part teams forget.

List the 10–30 pages that best explain your product, docs, pricing, and policies.
Write a one-line factual description for each page.
Generate the file and save it as llms.txt at the root of your domain, served as plain text.
Check that every linked page is public, indexable, and not blocked in robots.txt.
Update the file when key pages are added, renamed, or removed.

Common questions

What is llms.txt?

llms.txt is a proposed Markdown file at the root of a website that summarizes the site and lists its most useful pages for AI systems. It was proposed in 2024 and is published at llmstxt.org.

Does llms.txt help with Google AI Overviews?

Not that Google has said. Google’s guidance for AI Overviews and AI Mode says no special files or markup are needed beyond normal Search eligibility, and it does not mention llms.txt.

Is llms.txt the same as robots.txt?

No. robots.txt tells crawlers which URLs they may access. llms.txt is a curated summary and reading list. It does not allow or block anything.

Where do I put llms.txt?

At the root of your domain, so it loads at https://yourdomain.com/llms.txt, served as plain text.

What is llms-full.txt?

Some sites also publish llms-full.txt, a single file containing the full text of their key pages, often documentation. It is a common convention alongside the proposal rather than part of its core format.

Sources and methodology

Digraph publishes this guidance and provides AI visibility software. Worked examples are illustrative unless explicitly identified as measured results. A research sample does not establish total market coverage or guarantee future recommendations.