llms.txt Generator

How to Use the llms.txt Generator

Name and summarise your site

Give the project a name and a single-line summary. The name becomes the file's H1; the summary becomes the blockquote that tells an AI model, in one sentence, what the site is and who it serves.

Add sections of links

Group your most important URLs under headings like Docs, Guides, or About. One link per line as Title | URL | note — the note is an optional hint about what the page covers.

Copy or download

The file assembles live in spec-compliant Markdown. Copy it or download llms.txt directly. It all runs in your browser — nothing you type is sent anywhere.

Publish it at your site root

Upload the file so it is reachable at https://yoursite.com/llms.txt. Keep it updated as your key pages change — it is a living map, not a one-off.

llms.txt: A Map of Your Site for AI Models

What llms.txt is and why it appeared

An llms.txt file is a small Markdown document you place at the root of your website — /llms.txt — that lists your most important pages in a clean, machine-readable form. The proposal, introduced by Jeremy Howard of Answer.AI in 2024, addresses a real problem: large language models work best with concise, structured context, but a typical web page is buried in navigation, ads, scripts, and boilerplate. Rather than make a model crawl and guess, llms.txt hands it a curated index — here is what this site is, and here are the pages that actually matter.

The format is deliberately simple. It starts with an H1 — the project name — followed by a blockquote summary. After that you can add optional prose, then one or more ## sections, each containing a Markdown list of links written as [title](url): notes. That's the whole spec. Because it is just Markdown, it is readable by humans, trivially parseable by machines, and cheap to maintain. Some sites also publish an llms-full.txt with the actual page content inlined, but the base llms.txt — a tidy table of contents — is the right place to start.

"robots.txt tells a crawler where it may not go. llms.txt tells a model where it should look first."

What it does and doesn't do

It's worth being clear-eyed: llms.txt is an emerging convention, not a guaranteed, universally honoured standard. Adoption is growing across documentation sites and developer tools, but no model is obliged to read it, and it does not block or grant access to anything — that's the job of robots.txt and your server. What it does do is make your site easier and cheaper for AI tools to understand correctly, which matters as more people reach your content through AI assistants rather than a classic search results page. Treat it as good housekeeping for the AI era: low effort, no downside, and increasingly expected. Fill in your key pages, publish the file, and keep it current.

10 Facts About llms.txt

01

llms.txt lives at the root of your site — /llms.txt — just like robots.txt.

02

It was proposed by Jeremy Howard of Answer.AI in 2024 to give models clean, curated context.

03

The format is plain Markdown: an H1 name, a > blockquote, then ## sections of links.

04

Each link is written as [title](url): note in a Markdown list — readable by people and machines alike.

05

It is a discovery aid, not an access control — it never blocks or permits crawling.

06

robots.txt says where not to go; llms.txt says where to look first.

07

Some sites also ship llms-full.txt with full page content inlined for deeper context.

08

It is an emerging convention — adoption is growing, but no model is obliged to read it.

09

Documentation sites and developer tools were the earliest adopters of the format.

10

This generator builds the file entirely in your browser — nothing you type is uploaded.

Frequently Asked Questions

It is a small Markdown file placed at the root of your site (/llms.txt) that lists your most important pages in a clean, machine-readable form. It gives AI models curated context about your site instead of making them crawl and guess from cluttered HTML.
At the root of your domain, so it resolves at https://yoursite.com/llms.txt — the same place robots.txt lives. Upload it via your host, CDN, or static-site build output.
It is an emerging convention proposed in 2024, not a formally ratified standard. Adoption is growing across documentation and developer sites, but no AI model is obliged to read it. It is low-effort, good-practice housekeeping rather than a guarantee.
robots.txt is an access directive — it tells crawlers which paths they may or may not fetch. llms.txt is a discovery aid — it points models at your most useful pages. One restricts, the other recommends; they do different jobs and can coexist.
No. It does not grant or deny access to anything. To control crawling, use robots.txt directives (for example for GPTBot or ClaudeBot) and server-side rules. llms.txt only curates what to look at, it does not gate it.
llms.txt is a concise index — a table of contents of links. llms-full.txt is an optional, larger file that inlines the actual page content so a model has the full text in one place. Most sites start with the base llms.txt.
Only your genuinely important pages — key docs, guides, product or about pages. The value of llms.txt is curation, so a focused list of high-signal URLs beats dumping your whole sitemap into it.
No. The file is assembled entirely in your browser with plain JavaScript. Nothing you type is sent to any model, server, or third party, and nothing is saved.
No. A name and summary are enough for a valid file; the detail paragraph and any empty sections or blank link lines are simply omitted. Add as much or as little structure as your site needs.
Completely free, with no account or sign-up, and no limit on use. It runs in your browser and collects no data.

Related News

You may be interested in these recent stories from our newsroom.

No related news yet for this tool. Our editorial team publishes new pieces every week.

Browse all news →