Is llms.txt the same as robots.txt?

No. robots.txt tells crawlers which paths they may fetch; llms.txt points AI tools to your best content and explains the site. One is about access, the other about guidance.

What is llms-full.txt?

A companion file that inlines a site's full content into one Markdown document, so an AI tool can load everything in a single request instead of following links.

Do AI crawlers respect llms.txt?

It is an emerging convention, not a mandated standard, so support varies by tool. It costs little to publish and helps tools that do read it.

Does this send my data anywhere?

No. Utilumo's developer tools parse and transform input inside the browser tab. Nothing is uploaded, stored, or logged.

Explainer1 min readUpdated August 11, 2026

What is an llms.txt file?

Short answer

llms.txt is a Markdown file at /llms.txt that helps AI tools and agents find a site's most useful pages and understand it quickly. It starts with an H1 site name, an optional summary, and H2 sections of links. It is a community proposal for guidance and discovery — not an access-control mechanism.

A curated map for AI tools

Web pages are full of navigation, scripts, and markup that are noisy for a language model. llms.txt is a small Markdown file that points AI tools and agents straight to your most useful pages, in a format they can read at a glance. Think of it as a hand-picked table of contents for machines.

# Example

> A short summary of what the site is and who it is for.

## Primary resources

- [Docs](https://example.com/docs): Getting started and guides.
- [API](https://example.com/api): Endpoint reference.

## Optional

- [Full catalog](https://example.com/llms-full.txt)

A minimal llms.txt

Where it goes

Publish the file at the root of your domain, at https://example.com/llms.txt, served as plain text or Markdown. Many sites also add a companion llms-full.txt that inlines the full content in one file for tools that want everything at once.

The structure

An H1 (# Name) with the site or project name — the only required part
An optional blockquote (> ...) with a short summary
H2 sections (## Primary resources) grouping links
Link lists in the form - [Name](url): description
An optional ## Optional section that tools may skip to save context

It guides, it does not enforcellms.txt is a discovery and guidance file, not access control. To express crawler preferences, use robots.txt. To keep a page private, use authentication — llms.txt cannot restrict anything.

llms.txt is a community proposal, not an official web standard, so support depends on the specific AI tool. Publishing one is low-cost and forward-looking, but do not assume every crawler reads it.

Try it: llms.txt GeneratorEnter your site details and resource links to generate an llms.txt locally.Open tool

References

The /llms.txt proposal (llmstxt.org) — llmstxt.org