llms.txt generator and checker

What llms.txt is

The format, in order:

• One H1 with the name of the site or project. It’s the only required part.
• A blockquote with a short summary.
• Optional notes: paragraphs or lists, but no headings.
• Sections under H2 headings, each a list of links written as - [title](url), with an optional : note after the link.
• A section called Optional, by convention, for links an agent can skip when it’s short on room.

The links should point to pages an agent can read easily. If your pages have plain Markdown versions, link to those.

Does llms.txt help AI search?

There's no public evidence that it does. AI companies haven't confirmed that they use llms.txt for their answers or rankings. Google's AI optimization guide says an llms.txt file "will neither harm nor help your site's visibility or rankings in Google Search", and that you don't need AI text files to appear in its generative AI features.

It’s still cheap to add, and it helps the agents that do read it, like coding assistants opening a docs site. It doesn’t replace pages crawlers can read, or robots.txt access. If your robots.txt blocks an AI crawler, an llms.txt won’t let it in. The third tab above checks that.

An llms.txt example

A small file for a made-up invoicing product. The name, summary and links are the parts that matter; keep each note to one line.

# Example

> Example makes invoicing software for small teams. This file lists the pages an AI agent should read first.

Prices on these pages are in US dollars.

## Docs

- [Quick start](https://example.com/docs/start.md): set up an account and send a first invoice
- [API reference](https://example.com/docs/api.md): every endpoint, with examples

## Product

- [Pricing](https://example.com/pricing): plans and what each includes

## Optional

- [Changelog](https://example.com/changelog): what changed, by month

What the checker looks at

The checker reads the file line by line and gives a line number with each finding. Lines inside ``` code blocks are skipped.

For a domain, our server reads https://yourdomain/llms.txt, follows up to three https redirects and stops after five seconds or 500 KB. The sitemap import reads only /sitemap.xml at the root and lists up to 200 pages. If your sitemap is an index of other sitemaps, we list them, and you open one and paste it. A pasted file never leaves your browser. The format was checked against llmstxt.org on 28 October 2026.

FAQ

What is llms.txt?

llms.txt is a Markdown file at the root of a site, at /llms.txt. It names the site, sums it up in one line and lists the pages an AI agent should read, in sections. It was proposed by Jeremy Howard in September 2024, and the proposal is at llmstxt.org.

Does Google use llms.txt?

Not for Google Search. Google's AI optimization guide says an llms.txt file "will neither harm nor help your site's visibility or rankings in Google Search", and that you don't need AI text files to appear in its generative AI features. Google's AI Overviews use the pages Googlebot crawls and indexes, so normal SEO is what counts there.

Where do I put llms.txt?

At the root of your domain, so it opens at yourdomain.com/llms.txt, served as plain text. The proposal also allows one under a path, like /docs/llms.txt, covering only the pages under it.

What’s the difference between llms.txt and llms-full.txt?

llms.txt is a short index: a summary and links. llms-full.txt is a common extra file that puts the full text of those pages in one place. It isn’t part of the llmstxt.org format, and both are optional.

Is llms.txt the same as robots.txt?

No. robots.txt tells crawlers what they may fetch. llms.txt suggests what an agent should read once it’s allowed in. An llms.txt does nothing for a crawler your robots.txt blocks, which is why the third tab checks that.

Read next

• AI crawler checker, the same crawler check with a guide to each AI agent
• Sitemap checker, to check the sitemap your llms.txt links come from
• Technical SEO: indexing, rendering and AI crawlers
• How to get cited in AI answers
• How we get startups named in ChatGPT and Perplexity
• Where AI answers get their sources