A map of your site for AI tools, in one small file.

Paste a page list or your sitemap XML and get a valid llms.txt — plus an llms-full.txt variant — checked for format errors and ready to publish at your domain root.

  • Your site details never leave the device
  • No sign-up · no limits · no crawling
  • llms.txt + llms-full.txt
  • Format checks included

Build your llms.txt

Becomes the H1 — the only required part of llms.txt.
Relative paths in your list (/docs/start) are resolved against this.
Becomes the blockquote under the H1. Keep it to one or two lines.

One page per line: “Title | https://example.com/page | short description”, or just a bare URL — the title is derived from the path. Lines starting with # are ignored.

Up to 500 pages per file. Pages are grouped into sections automatically by their first path segment (/docs/… → “Docs”) — uncheck “Group pages into sections” below to keep one flat list.

Both files are generated; this only switches the preview.
Sections come from the first part of each URL’s path.
Try a sample:

Generated in your browser — nothing is uploaded. Fill in your site details and paste a page list or sitemap to start.

No file yet. Everything stays on this device. Downloads are plain text.

Privacy you can verify, not just trust

Your page list describes your site — which pages you value, how it is organised, what it is about. Sending it to a hosted generator means handing that map to a stranger’s server, and the server-side generators rate-limit you for the trouble. This one can’t: your text is processed entirely in your browser. Your site details never leave the device — the only third-party requests are the site’s own analytics, which count page views — and it uploads nothing, ever. There is no file fetched after load for the generation itself. Don’t take our word for it:

New cross-origin requests during use: 0
  1. Press F12 to open developer tools, then the Network tab.
  2. Generate an llms.txt above. Watch: apart from the site’s analytics, nothing new is requested — no uploads, and no site data ever leaves your device.
  3. Extra credit: disconnect your internet after this page loads — generating still works.

How to create an llms.txt file without uploading your site map

llms.txt is a small Markdown file that sits at the root of a website and tells a language model what the site is and which pages matter. It was proposed in September 2024 by Jeremy Howard of Answer.AI, and revised as v2 in August 2026. Big documentation sites publish one — the proposal’s own examples include developer docs — and several platforms now generate one automatically. But it is a proposal, not a standard: no standards body maintains it, no AI company is obliged to read it, and support varies from tool to tool.

This tool builds the file where your data already is: on your own device. When you paste a page list or a sitemap, your browser:

  1. Reads your pages — one per line as “Title | URL | description”, a bare URL, or the raw XML of your sitemap.xml. Titles are derived from the URL path when you do not supply one, and relative paths are resolved against the site URL you type in.
  2. Groups them into sections — by the first part of each URL’s path, so /docs/… pages become a “Docs” section and /blog/… pages become “Blog”. Turn grouping off for one flat list.
  3. Writes both files — llms.txt, and llms-full.txt with a short excerpt after each link — then checks the result: a missing H1, a non-absolute URL, a duplicate link, a link with no description, or a file that has grown past 100 links.

What makes this generator different

The established generators are either server-side crawlers — they fetch your site, read up to a few dozen pages, and rate-limit you — or command-line tools you install and run. The free browser generators that do exist take a form and write the file, but they cap the pages, hide the format rules, or leave you to guess what is wrong when the output is malformed. None of them, as far as we could find, combine all four things this page does: sitemap XML pasted straight in and parsed on-device, a live editable preview of both files, a checks table that names every format problem in plain English, and no server, no sign-up and no rate limit at all. This page is that combination — free, fully client-side, with a live network-request counter so you can verify the privacy claim yourself.

When is an llms.txt worth the ten minutes — and when is it not?

It is worth it for a documentation site, a blog with a clear best-of list, or any site whose most useful pages are not obvious from the homepage: one text file, no code, no change to your existing pages. It is not worth it as an SEO move — Google says it ignores the file for Search, and there is no public evidence it earns citations. It is also not a fix for a site AI cannot read: if your pages are blocked to AI crawlers or load as an empty shell, a map of them helps nobody. Fix the access first, then add the map.

Honest limitations

A proposal, not a standard

llms.txt was proposed in 2024 and revised in 2026. No standards body maintains it and no AI company has said its crawlers read third-party files. Publishing one is voluntary and cheap — not a guarantee of anything.

No ranking or citation claim

Google says it ignores llms.txt for Search, including AI Overviews and AI Mode. Nothing here promises traffic, rankings or mentions — only a correctly formatted file.

It never crawls your site

The tool works only on the text you paste. It cannot check that your URLs exist, fetch your page titles, or write excerpts for llms-full.txt. Check your links before publishing.

Descriptions are yours to write

A link without a description is valid but barely useful — and a sitemap gives no descriptions at all. The best files are curated by hand: pick your most important pages and say, in one line each, why they matter.

Small by design

The proposal says the file should fit in context. A 500-page dump of your sitemap is not a map, it is a sitemap in another format — and this tool warns you past 100 links for exactly that reason.

It grants and blocks nothing

llms.txt is a guide, not a gate. It does not replace robots.txt, it does not block crawlers, and it does not give any model permission it did not already have.

Frequently asked questions

What is llms.txt?

llms.txt is a small Markdown file placed at the root of a website (/llms.txt) that gives large language models a short, curated map of the site: its name, a one-line summary, and sections of links to its most important pages, each with a brief description. It was proposed by Jeremy Howard of Answer.AI in September 2024, with a revised version (v2) in August 2026. It is a proposal, not a ratified web standard.

Will llms.txt improve my Google rankings or get AI tools to cite me?

There is no public evidence that it will. Google says it ignores llms.txt for Search, including AI Overviews and AI Mode, and that you do not need one to appear there. No major AI company has said its crawlers read third-party llms.txt files. Treat it as a low-cost, voluntary map for the agents that do read it — not as a ranking lever or a citation guarantee.

Do my site details upload anywhere?

No. Everything you type or paste is processed entirely in your browser — your site details and page list never leave the device, and the only third-party requests are the site’s own analytics, which count page views. You can verify it yourself with the network-request counter in the privacy section below the generator.

What format does my page list need to be in?

One page per line. The full form is “Title | https://example.com/page | short description”, but a bare URL works too — the title is derived from the page path. If you fill in the site URL field, relative paths like /docs/start are resolved against it. Lines starting with # are ignored. Or switch to sitemap mode and paste your sitemap.xml instead.

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

llms-full.txt is the optional companion file from the same proposal: the same structure, but with a short excerpt of each page after its link. You do not need it — llms.txt on its own is the whole proposal. This tool builds both, using the descriptions you supply as the excerpts, so you can publish the full file too if you want.

What checks does the generator run?

Errors mark things that would make the file malformed or useless: a missing site name (the H1 is the only required part), no pages at all, or a link that is not an absolute http:// or https:// URL. Warnings are advice: a link without a description, a duplicate URL, a page with no title, an empty section, or more than 100 links — the proposal says the file should stay small enough to fit in context.

How do I publish the file once it is generated?

Download llms.txt and put it at the root of your website, so it opens at https://yourdomain.com/llms.txt — the same level as robots.txt. On most platforms that means the public/ or web-root folder, or a static-file location your host exposes. Then open that URL in a browser to confirm it loads as plain text.

Is llms.txt the same as robots.txt or a sitemap?

No. robots.txt controls access — which crawlers may fetch which pages. A sitemap lists every URL for search engines. llms.txt is different: a short, human-curated selection of your most important pages, with descriptions, written for language models to read. The proposal is explicit that a sitemap does not substitute for it, and it grants or blocks nothing.

What does this tool NOT do?

It does not crawl your site, fetch your pages, or check that your URLs exist — it works only on the text you paste, so check your links before publishing. It does not write the page excerpts for llms-full.txt; those come from the descriptions you supply. And it does not promise any search or AI-visibility benefit: llms.txt is a proposal, and support varies between AI tools.