Free SEO Tool
llms.txt Generator
Build an llms.txt file that follows the published format: an H1 with your project name, a blockquote summary, optional detail, then H2-delimited sections of markdown links with notes, plus an Optional section for anything an agent can skip. Fill the fields, copy the file, and save it at yourdomain.com/llms.txt.
How it works, plainly: this is a rule-based generator, not an AI model. Every result is assembled from tested formulas, templates and validators that run entirely in your browser — no model call, no cost, and nothing you type is uploaded.
- Free
- No signup
- Follows the published spec
- Runs in your browser
How it works
- 01 Name the project
The H1. This is the only required part of the file — everything else is optional structure on top of it.
- 02 Write the summary
One blockquote with the key information. It is the first thing an agent reads, and often the only thing it reads.
- 03 Add sections of links
One H2 per section, one link per line as Name | URL | note. The note is what tells an agent whether to fetch that page.
- 04 Park the rest under Optional
By convention an Optional section holds secondary links an agent can skip when it needs a shorter context.
Next step
FAQ
Frequently asked questions
- What is llms.txt?
- llms.txt is a markdown file at a known location that gives language models a curated, readable map of a site instead of leaving them to parse navigation and boilerplate. It was proposed by Jeremy Howard and first published on 3 September 2024; the specification reached version 2, modified 10 August 2026. The file structure, in order, is: an optional byte-order mark, an H1 with the name of the project or site — the only required section — a blockquote with a short summary of the project containing key information, then optional detail and optional H2-delimited sections containing file lists.
- Where does the file go?
- At /llms.txt on your root, or at any subpath such as /docs/llms.txt. A file covers all URLs under its path, and when several exist an agent uses the most specific applicable file. So a documentation site can ship a broad /llms.txt for the whole domain and a focused /docs/llms.txt that a docs-reading agent will prefer.
- How do I format the link lists?
- Each file list is a markdown list, containing a required markdown hyperlink [name](url), then optionally a colon and notes about the file. In this generator you write one link per line as Name | URL | note and it assembles that shape for you. Write the note as an instruction to a reader deciding whether to open the link — 'API reference for the v3 endpoints' is useful; 'our docs' is not.
- What is the Optional section for?
- By convention, a section titled Optional contains secondary information: links an agent can skip when a shorter context is needed. It is the one section heading with a defined meaning in the spec, which makes it the right place for changelogs, archives and long-tail reference material that would otherwise crowd out your main pages.
- Will adding llms.txt get my site into ChatGPT or Claude?
- Not by itself, and be sceptical of anyone who says otherwise. llms.txt is a published convention that a growing number of tools read, not a protocol any specific AI product has committed to honouring on your behalf. The spec's own framing is adoption-based: it notes thousands of sites publishing the format, automatic generation by documentation platforms, and publication by major AI labs including OpenAI and Anthropic. Publishing one costs nothing and makes your site easier to read; treating it as a ranking lever does not.