Reads your sitemap from our server and drafts an llms.txt: a title, a one-line summary and your pages grouped into sections, in the format proposed at llmstxt.org. It is a draft to edit, not a finished file, and llms.txt is a proposal that no search engine or AI assistant is required to follow. For founders who want to give AI assistants a short guide to their site.
How to use it
Enter your site's address or the address of its sitemap. You can leave out https://.
- Type or paste your site address, or the sitemap address, and press Generate draft.
- Read the draft: the title and summary come from your home page, and the links from your sitemap.
- Edit it: rename the links, add a short note after each, and delete pages that do not explain your product.
- Copy or download the file and place it at the root of your domain, as /llms.txt.
How Reavlo tests this
This tool runs on our server, because a browser cannot read another site's files. Nothing about the request is stored or logged: not the address, not the sitemap.
The format. The draft follows the llms.txt proposal: an H1 title, an optional blockquote summary, and H2 sections that hold lists of links in the form - [name](url): notes. It is a proposed convention. Nobody has to read it, and the tool makes no claim that it improves how often your site appears in AI answers.
Where the pages come from. The sitemap you give, or the ones your robots.txt declares, or /sitemap.xml. Sitemap indexes are followed up to 5 files. Only pages on your own site are used, and files such as images, feeds and PDFs are left out. If there is no sitemap, the links on your home page are used instead, and the tool says so.
The title and the summary. The title is the home page title and the summary is its description meta tag. If the home page cannot be read, the title is your domain name.
Sections and names. A page belongs to the section named after the first part of its path, and pages directly under the root go in a section called Main. Link names are made from the last part of the address, because the tool does not open every page. This is why the draft needs editing.
Limits. At most 100 pages are listed, and the tool says when pages were left out. It does not check that the pages are good, public or fresh. If your site already has an llms.txt, the tool reports it and does not replace it.
Questions
Is the address I enter stored?
No. The address goes to our server only to fetch your pages and sitemap, and neither it nor the files are stored or written to a log. Analytics records only that the tool ran, never the address.
Will llms.txt make AI assistants cite my site?
Not as far as anyone can promise. It is a proposal, and the major assistants have not said they use it. It costs little to add, but do not expect a guaranteed effect.
Where do I put the file?
At the root of your domain, so that it answers at /llms.txt, in the same place as robots.txt.
Why are the link names so plain?
They are made from the page addresses, because the tool does not open each page. Rename them and add a short note after each link so the file explains your site.
Should I list every page?
No. Keep the pages that explain what your product does, how it works and what it costs. A short file is easier to use than a long one.