llms.txt Generator

Describe your site once and get an llms.txt file that tells AI assistants what it is and which pages matter most. Built in your browser, nothing uploaded.

Your site

Becomes the blockquote under the title. This is the line an assistant reads first.

llms.txt

# Your site name

A site name is required — the file must open with a single H1 naming the project or site.

No summary. The blockquote under the title is where an assistant learns what your site actually is, in one sentence.

No links yet. The point of the file is pointing assistants at the pages that explain your site best.

What the file looks like

The format is deliberately plain markdown with a fixed shape: an H1 naming the site, a blockquote summarising it in one sentence, an optional paragraph of context, then H2 sections containing bullet links written as - [Title](https://example.com/page): what it covers. A section named Optional carries a specific meaning in the convention: those links may be skipped when context is limited.

This tool assembles that structure, checks your URLs are absolute, and flags the pieces that are missing or empty. To control which AI crawlers can reach your site in the first place, see the AI Crawler Access Checker.

Frequently asked questions

What is llms.txt, exactly?

A plain markdown file at the root of your site that tells AI assistants what the site is and which pages are worth reading. The idea, proposed at llmstxt.org in 2024, is that a model working with a limited context window is better served by a short curated index than by crawling your whole site and hitting navigation, cookie banners, and scripts.

Where do I put the file?

At the root of your domain, reachable at https://yoursite.com/llms.txt, served as plain text or markdown. In most frameworks that means dropping it in your public or static directory. It doesn't need to be linked from anywhere, and it doesn't replace robots.txt or your sitemap, which do different jobs.

Do AI assistants actually read it?

Honestly: some do, many don't, and none are required to. It's a community convention rather than a ratified standard, with growing but uneven adoption. The practical case for adding one is that it costs ten minutes, can't hurt anything, and is trivially removable. Treat it as a low-cost bet, not a traffic strategy.

What should go in the Optional section?

Links you'd be happy for an assistant to skip when it's short on context — background pages, an about page, changelogs, secondary docs. The convention gives that specific heading that meaning, so it's a way of ranking your own content rather than just listing it. Everything else belongs in a normally named section like Docs, Guides, or API.

Is this the same as blocking AI crawlers?

No, it's the opposite. llms.txt helps assistants understand a site you want them to represent well. If your goal is to keep AI crawlers out, that's a robots.txt job — the AI Crawler Access Checker on this site shows which of them your current rules allow or block.

Related tools

Redirect Chain CheckerSitemap ValidatorRobots.txt GeneratorRobots.txt Checker

Command Palette

Search for a command to run...