Free tool

llms.txt generator

Build a spec-shaped llms.txt file in the browser: add your site name, a one-line description, and sections of links, then copy or download the result. The output comes from the same generation code the Rebilder gateway serves merchants with — deterministic, your words verbatim, nothing invented.

llms.txt

llms.txt example

Here is the generator's own output for a small outdoor-gear store — a complete, valid llms.txt example: site name as the H1, a one-line description as the blockquote, and two link sections with notes.

llms.txt
# Basecamp Supply Co

> Outdoor packs and trail gear. Prices, stock, shipping, and returns linked below.

## Products

- [Alpine Trail Pack 28L](https://basecamp-supply.example/products/alpine-trail-pack-28l): $148.00, in stock

## Policies

- [Shipping](https://basecamp-supply.example/policies/shipping): Free US shipping on orders over $75
- [Returns](https://basecamp-supply.example/policies/returns): 60-day returns

What is llms.txt?

llms.txt is a plain-markdown file served at the root of your site (/llms.txt) that gives AI systems a compact map of what matters: who you are and where your key pages live. The spec shape is simple — an H1 with the site name, a blockquote with a one-line description, then H2 sections containing markdown link lists (- [title](url): note).

This llms txt generator produces exactly that shape. It runs the same generateLlmsTxt function that ships in the Rebilder gateway SDK — deterministic, injected values only, no generated copy: every title, URL, and note in the file comes verbatim from what you type.

How to serve llms.txt

  1. Fill in the generator above and download the file (or copy it).
  2. Serve it at your site root as /llms.txt with a plain-text content type — a static file next to robots.txt works.
  3. Keep it current: regenerate when products, prices, or policy pages change. A stale llms.txt misleads exactly the readers it was meant to help.

If your store runs the Rebilder gateway, you can skip the manual step entirely: the gateway generates llms.txt live from your wired product and policy sources, so it never drifts from your catalog. See Serving llms.txt from the gateway.

Honest answer: how much does llms.txt move?

Content negotiation vs. llms.txt, accurate retrieval
~4.2x
300k-domain study, mid-2026
Citation lift from llms.txt alone
None measured
Same 300k-domain study, mid-2026
Context reduction from gateway markdown
98.6%
Rebilder before/after capture: 91,226 B → 1,315 B

llms.txt is worth shipping: it costs nothing to serve and some agents fetch it. But a mid-2026 study across 300k domains measured content negotiation — answering Accept: text/markdown with clean markdown on your actual pages — at roughly 4.2x more effective than llms.txt for accurate retrieval, and found no citation lift from llms.txt alone. The file is a map; what moves retrieval is what agents find when they follow it.

That second layer is what the Rebilder gateway does: one middleware install detects agent traffic and serves each product page as clean markdown rendered from your source of truth — in our captured before/after, 91,226 bytes of PDP HTML became a 1,315-byte markdown page with the price on line 4. Humans and search crawlers keep your site untouched.

Frequently asked questions

What is llms.txt?

A plain-markdown file at /llms.txt that gives AI systems a compact map of your site: an H1 site name, a blockquote description, and H2 sections of links with optional notes.

Is this llms.txt generator free?

Yes — free, no account, no watermark. It runs entirely in your browser using the same open generation code the Rebilder gateway SDK ships.

Where do I put the llms.txt file?

At the root of your site, so it resolves at https://yoursite.com/llms.txt — the same place robots.txt lives. Any static-file host works; see Serving llms.txt from the gateway to generate it live from your catalog instead.

Does llms.txt improve AI citations on its own?

The honest reading of the data: a mid-2026 study across 300k domains found no citation lift from llms.txt alone, and measured content negotiation (serving agents clean markdown on your actual pages) at roughly 4.2x more effective for accurate retrieval. Ship llms.txt because it is free — pair it with content negotiation because that is what moves the numbers.