Tools

llms.txt generator

Write a spec-compliant /llms.txt from your site name, a summary and a list of links grouped into sections.

Runs in your browserSEO & GEO2.6K
Free

Result

The result will appear here.

llms.txt is a Markdown file at the root of a site, proposed by Jeremy Howard of Answer.AI, that gives an AI agent a short, curated map of where the useful content is. The format is precise enough to parse: an H1 with the name, a blockquote summary, optional notes, then H2 sections that are lists of links with a short description after a colon. Fill in the name, summary and one link per line as Section | Title | URL | note, and the generator writes the file in the order the specification at llmstxt.org (AnswerDotAI/llms-txt) requires.

How it works

  • Headings typed into the notes are turned into bold text, because the spec allows every kind of Markdown there except headings.
  • A section named Optional is always moved to the end: by the spec's convention it holds links an agent may skip when context is short.
  • Square brackets in link titles are escaped and spaces or parentheses in URLs are percent-encoded, so each link still parses as [name](url).

Where your data goes

Nowhere. This tool runs entirely in your browser: the text you paste is processed by the page and is never transmitted to a server or written to a log.

This tool is free and needs no account. Its results exist only in your open page and are not saved anywhere.

What it costs

This tool is free, with no sign-in and no points.

Common questions

Where should I link to — HTML pages or Markdown?
The spec recommends linking to Markdown versions where you have them: the same URL with .md appended, such as page.html.md or index.html.md. Plain HTML links still work, but every page the agent follows then costs it the markup as well. Absolute URLs are safest; the tool counts relative ones so you can check them.
Is llms.txt the same thing as robots.txt?
No. robots.txt says which crawlers may fetch what; llms.txt is read on demand by an agent helping a user, and says where the best information is. They complement each other: you can block training crawlers in robots.txt and still publish an llms.txt for assistants that are allowed to visit.
Does anything actually read it?
Documentation platforms such as Mintlify and GitBook generate llms.txt automatically, the major AI labs publish one for their own developer docs, and the spec notes that Chrome's Lighthouse checks for one in its agentic browsing audits. It is cheap to add, and it is most useful for documentation that coding agents look up.

The open-source behind it

This tool is a self-contained implementation. AnswerDotAI/llms-txt (Apache-2.0) does the same job as a library — if you need this behaviour inside your own program, start there rather than calling a web page.

AnswerDotAI/llms-txt

Also known as

  • llms.txt generator
  • llms.txt
  • create llms.txt
  • llms.txt example
  • llms.txt format