SEO & AI visibility

Create an llms.txt for your site

Already have a site? Fill the fields automatically

We read one page and suggest a name, description and links. You can edit everything afterwards.

Name of your site or organisation

In one sentence: what do you do?

This becomes the summary at the top of the file.

Further context (optional)

llms.txt

Where do you put the file?

The file must be reachable at yourdomain.com/llms.txt and served as plain text. Pick your situation below.

Static site (HTML, Netlify, Vercel, GitHub Pages)

Drop llms.txt in the folder you publish — the same one as index.html or robots.txt. Nothing else is needed; these platforms serve .txt as plain text automatically.

public/
├── index.html
├── robots.txt
└── llms.txt   ←

WordPress

Upload the file over FTP or your hosting panel into your installation root — next to wp-config.php. Do not create it as a WordPress page: that yields HTML with a menu around it instead of plain text.

/public_html/
├── wp-config.php
├── robots.txt
└── llms.txt   ←

Nginx

If the file sits in your web root, Nginx already serves it. This block pins the charset and media type, so accented characters survive:

location = /llms.txt {
    default_type text/plain;
    charset utf-8;
}

Apache

Put the file in your DocumentRoot. To pin the media type, add this to .htaccess:

<Files "llms.txt">
    ForceType 'text/plain; charset=utf-8'
</Files>

Flask / Django

A route beats static mapping here, because you control the media type:

@app.route('/llms.txt')
def llms_txt():
    return send_from_directory(
        app.static_folder, 'llms.txt',
        mimetype='text/plain')

Checking that it works

Request the file the way a crawler would. You want a 200, and text/plain or text/markdown — no 404, no redirect and no text/html:

curl -sI https://jouwdomein.nl/llms.txt

Then reference it from your robots.txt, so crawlers meet the file without having to guess:

# llms.txt: https://jouwdomein.nl/llms.txt

An llms.txt is a short text file in your website's root in which you describe what your site is and which pages matter. Where robots.txt says what a crawler may not do, llms.txt says what a language model should know — in plain language, without the navigation, cookie banners and scripts around it. Fill in your details below and you get a file you can publish straight away, plus the instructions for your type of server.

What people use this for

Point ChatGPT and Claude at your services and documentation instead of your cookie policy
Give in one sentence the context your individual pages don't convey
Put your key resources at the top and the peripheral ones under 'Optional'

What others think of this tool

No reviews for this tool yet. Yours would be the first.

Frequently asked questions

What exactly is llms.txt?

A markdown file at https://yourdomain.com/llms.txt holding a title, a short summary and a number of link sections. The idea comes from a 2024 proposal by Jeremy Howard: a language model trying to understand your site needs no menus, banners or scripts, but a clean list of what lives where. The file is as readable for people as it is for a model.

Do ChatGPT and Claude actually read this file?

Honest answer: none of the major providers has publicly confirmed that they fetch llms.txt by default. It is a proposal gaining traction, not a settled standard like robots.txt. It costs you ten minutes and one small file, and it forces you to write down clearly what your site actually offers. That last part is a gain you keep either way.

How is this different from robots.txt and sitemap.xml?

Robots.txt grants permission: which crawler may access which path. Sitemap.xml gives completeness: here are all my URLs with their modification dates. Llms.txt gives meaning: this is who we are and these are the pages to read to understand us. The three don't compete — they answer different questions and you want all three.

Where should the file live?

In your domain's root, reachable at https://yourdomain.com/llms.txt — just like robots.txt. Not in a subfolder and not behind a redirect. It must be served as plain text (Content-Type text/plain or text/markdown); if your server offers it as a download or wraps it in HTML, a crawler can do little with it. The instructions below cover this per server type.

What is llms-full.txt and do I need one?

Llms.txt is the table of contents: short description plus links. Llms-full.txt is the expanded version containing the text of those pages itself, so a model gets everything in one fetch without following links. Start with llms.txt. An llms-full.txt mainly pays off for documentation and knowledge sites with many related pages, and it needs maintenance: stale content hurts more than no content.