llms.txt Generator

What An llms.txt File Is

An llms.txt file is a plain text file at the root of a website, written in Markdown, that gives AI assistants a short, structured summary of the site: who the business is, what it does, and which pages hold the answers. It was proposed in September 2024 by Jeremy Howard of Answer.AI, and the format is published at llmstxt.org.

A web page is built for people. It carries navigation, scripts, cookie banners and design. A language model reading that page has to dig the facts out of the markup. An llms.txt file skips the digging. It hands over the facts and the links in the cleanest format a model can read.

What This Generator Builds

The tool follows the published structure, in this order:

1. An H1 with the business name. The only required line.
2. A blockquote summary. One sentence that says what you do, for whom and where. It is the line an assistant is most likely to repeat.
3. Key details. Plain facts in a short paragraph: licences, guarantees, what you do and do not offer.
4. H2 sections of links. Each link is a Markdown list item with a title, a full URL and an optional note.
5. An Optional section. Secondary pages a model can skip when its context is short.

Relative links are converted to full URLs using the website you enter, because a file read outside your site has no base address to resolve them against. The checks under the result flag a missing name, a summary that runs too long, links that are not full URLs and the same page listed twice.

Where To Put The File

The file must load at yourdomain.com/llms.txt and be served as plain text. How you get it there depends on the platform:

• Any host with file access: upload llms.txt to the public root, the same folder that holds robots.txt.
• WordPress: upload it to the site root by SFTP or your host's file manager, or use your SEO plugin's llms.txt feature if it has one. If you use the plugin, read its output, because generated files often describe the site in vague terms.
• Hosted builders: some builders do not allow files at the root. Check your platform's documentation for root file or redirect support before you publish.

When it is live, open the URL in a browser. You should see the raw text, not a 404 and not a styled page.

Does It Help You Rank In AI Search?

Honest answer: it is a proposal, not a standard that the major AI search products have said they rank on. No one can promise that an llms.txt file gets you cited by ChatGPT, Gemini or Google's AI features.

It is still worth the ten minutes, for three reasons. It costs nothing to publish. It forces you to write the one sentence summary and the list of pages that matter, which is the same clarity every answer engine rewards on the pages themselves. And assistants that browse a site, or tools that load a site into a model's context, do read it when it is there.

Treat it as one part of AI search readiness, not the whole thing. The pages it links to still need to answer their question in the first lines, carry structured data, and agree with what the rest of the web says about you. That work is where visibility in AI answers is decided.

Write It Like A Fact Sheet

• Use the words your customers use. "Roof repair in Calgary" beats "envelope solutions".
• State facts, not adjectives. Service area, hours, licences and what is included. A model repeats facts more reliably than claims.
• Link the pages that answer questions. Services, pricing, service areas, contact. Skip login pages, carts and thank you pages.
• Keep it current. When you add a service or change a price, update the file the same day. An out of date llms.txt is worse than none, because it is the version an assistant trusts.

Agencies can run this for every client in one sitting and add it to the launch checklist. It is a small deliverable, and it opens the conversation about the bigger one: making the whole site readable to the engines that are starting to answer for it.