llms.txt Generator
Fill in your site name, a one-line summary and the pages that matter, and get a spec-compliant llms.txt to serve at your site root — ready to copy.
llms.txt is a proposal from llmstxt.org: a Markdown file at /llms.txt that gives language models a short, curated map of your site — what it is, and which pages to read first — instead of leaving them to guess from a crawl. A number of documentation sites and developer tools have adopted it. It is not a Google ranking signal — Google has said it does not currently use the file — so treat it as an AI-readiness nicety, not an SEO lever. The format is small and strict: an H1 with the site name, an optional blockquote summary, optional prose, then ## sections of - [Title](URL): note bullets. This generator produces exactly that shape so you do not have to remember it. CrawlX checks whether your site serves an llms.txt and parses its structure on every crawl as part of its AI-readiness scoring.
Three steps
Describe the site
Enter the site name (this becomes the required H1), a one-sentence summary, your homepage URL and, if useful, a short paragraph a model should read first.
List the pages that matter
Add a section for each group — Docs, Guides, Pricing — and paste one link per line as Title | URL | optional note. Use a section called Optional for lower-priority pages, as the spec suggests.
Copy and publish
Generate, copy the output and save it as /llms.txt at your site root, served as text/plain or text/markdown.
Common questions
What is llms.txt?
A proposed convention (llmstxt.org) for a Markdown file at /llms.txt that gives language models a concise, curated overview of your site and links to its most useful pages. It is meant to be read at inference time, not to control crawling — that remains robots.txt's job.
Does llms.txt help my Google rankings?
No. Google has said it does not use llms.txt, and no major search engine treats it as a ranking signal. Its value is in helping AI assistants find your best pages quickly; do not expect it to move search traffic.
Which sites actually use it?
Adoption is real but uneven: a number of documentation-heavy sites and developer tools serve one, and some frameworks generate it automatically. Many large publishers do not. It costs little to add, which is why CrawlX reports whether one exists rather than treating its absence as an error.
Where does the Optional section come from?
The llmstxt.org spec singles out a section named Optional as the one a model may skip when it needs a shorter context. Everything else is treated as primary.
Is my input sent anywhere?
No — the file is built entirely in your browser.
Keep going
Audit your whole site, not just one check
CrawlX runs 150+ technical checks in the cloud and ships the fix as a pull request. Free for 500 URLs.