llms.txt generator

Enter your site's address. The generator reads your sitemap, pulls the title and meta description of each page, and writes an llms.txt in the llmstxt.org format that you can copy or download.

Reads robots.txt, your sitemap and up to 50 pages. Larger sites take up to half a minute.

What an llms.txt file is

llms.txt is a plain Markdown file served at /llms.txt. It gives AI assistants and agents a short, curated map of a site, so they can find the right page without crawling everything or wading through navigation and scripts. The format is defined at llmstxt.org:

  • An H1 with the site or project name. This is the only required part.
  • A blockquote with a one-paragraph summary.
  • Optional paragraphs with more context, without headings.
  • H2 sections, each a list of links written as - [Title](url): description.
  • A section named Optional for links a tool can skip when it needs a shorter context.
# Acme

> Acme makes open source rocket telemetry tools. This file lists the docs,
> guides and API reference most useful to an AI assistant.

## Docs

- [Quick start](https://acme.dev/docs/start): Install the CLI and send a first reading.
- [Configuration](https://acme.dev/docs/config): Every option in acme.toml.

## API

- [REST API](https://acme.dev/api): Endpoints, authentication and rate limits.

## Optional

- [Changelog](https://acme.dev/changelog): Release notes by version.

How the generator builds it

It reads the Sitemap: lines in your robots.txt and /sitemap.xml, follows a sitemap index, and keeps the pages on your own domain. Shallow URLs go first, because a site's main sections usually sit one level down. It then reads up to 50 pages, five at a time, and takes each one's <title> and meta description. If there is no sitemap, it uses the links on your homepage.

Pages marked noindex are left out. A brand suffix that most titles share (“Pricing | Acme”) is trimmed and used as the site name, and links are grouped into sections by their path: docs, API, products, blog and so on, with privacy, terms, login and tag pages under Optional.

How to publish it

The file has to answer at https://yourdomain.com/llms.txt with a text/plain or text/markdown content type. On most hosts, save the download as llms.txt in the folder that serves your site's root: public/ in Next.js, Vite and Astro, static/ in SvelteKit and Hugo, the web root on a plain server.

In the Next.js App Router you can also serve it from a route handler, which lets you build the list from your CMS or database later:

// app/llms.txt/route.ts
const LLMS_TXT = `# Acme

> Acme makes open source rocket telemetry tools.

## Docs

- [Quick start](https://acme.dev/docs/start): Install the CLI and send a first reading.
`

export const dynamic = "force-static"

export function GET() {
  return new Response(LLMS_TXT, {
    headers: { "Content-Type": "text/plain; charset=utf-8" },
  })
}

After deploying, open /llms.txt in a browser and check that it shows as plain text, not your 404 page. The AI SEO checker checks this for you along with your robots.txt rules.

Questions

What is llms.txt?
A Markdown file at the root of a site, at /llms.txt, that gives AI tools a short map of it: the site's name, a one-paragraph summary, and lists of links with a line on what each page covers. Jeremy Howard of Answer.AI proposed the format in 2024 and it is documented at llmstxt.org.
Does llms.txt improve my Google rankings?
No. Google Search does not use it, and it is not a ranking signal anywhere. It is a convention that some AI assistants, coding tools and agents read when they want a compact view of a site, which is most useful for documentation and product sites.
Which pages does the generator include?
It reads the Sitemap lines in your robots.txt and /sitemap.xml, follows a sitemap index up to six files, and keeps pages on your own domain. Shallow URLs come first, up to 50 pages. Pages marked noindex and anything that is not HTML are skipped. With no sitemap, it uses the links on your homepage.
Should I edit the output before publishing it?
Yes. Treat it as a first draft. Cut pages an AI tool does not need, move the most useful ones to the top, rewrite weak descriptions, and add a short paragraph under the summary if the site needs context. Links under the Optional heading are the ones a tool may skip when it is short on space.
What is the difference between llms.txt and llms-full.txt?
llms.txt is the index: titles, links and one-line descriptions. llms-full.txt is a common companion that puts the full text of the pages in one file. This tool writes llms.txt only.
Is llms.txt the same as robots.txt?
No. robots.txt tells crawlers what they may fetch. llms.txt does not allow or block anything; it only points to the pages worth reading. If robots.txt blocks a crawler, an llms.txt will not change that.
Do you store the URLs I enter?
No. The server fetches public pages from your site, builds the file and returns it. Nothing is saved. Requests identify themselves with a fabwaseem-tools user agent, and each visitor can run the tool 10 times in 10 minutes.