Group links by section. Anything in a section named "Optional" is marked low-priority, an agent on a tight context budget may drop it. Write descriptions with real facts (versions, limits, retry counts).
#
Spec-compliant output: one H1, a third-person blockquote, sectioned links in - [Title](URL): Description format. Runs entirely in your browser, nothing is uploaded.
How to use it
llms.txt is a curated Markdown index at your domain root that tells a coding agent where your best docs live. The value is in the descriptions: pack them with concrete facts so an agent can often answer without a second fetch. Keep sections broad (four good ones beat twenty), and reserve Optional for changelogs and deprecated guides, never your core API reference.
This generator enforces the structural rules; validate an existing file with the linter, and read the evidence on where the file actually helps.
How to use it
- Enter your priority pages by section.
- Generate a spec-compliant llms.txt.
- Copy or download and serve it at /llms.txt.
Frequently asked questions
What is an llms.txt file?
A plain-text index, served at yourdomain.com/llms.txt, that points AI crawlers to the pages worth citing: a single H1, a blockquote summary and sectioned links with descriptions. It takes minutes to ship and most sites have not.
Does llms.txt actually help?
It is not a guaranteed ranking lever, and search crawlers largely ignore it today, but coding agents and some AI tools read it, and it is a cheap, low-risk way to steer crawlers to your best pages. Pair it with crawl access and schema.
Is the llms.txt Generator free to use?
Yes. The llms.txt Generator is completely free, with no sign-up, no usage limits and no watermark on the output.
Is my data private?
Yes. The llms.txt Generator runs entirely in your browser. Nothing you paste or enter is uploaded, stored or sent to any server.
Related tools and reading
Keep going with the playbooks and tools behind this one.