llms.txt generator
Enter a domain. SagBot drafts an llms.txt from up to 50 of its pages. Tick, rename and reorder, then copy or download the file.
Enter a domain to draft its llms.txt. You can edit everything before you copy it.
The generator reads the site's robots.txt, then its sitemap. With no sitemap it uses the links on the homepage. It keeps pages on the same site and skips pagination, tag and author archives, feeds, media files and anything robots.txt blocks for SagBot.
For up to 50 of those pages it reads only the head: the title, the meta description, the canonical URL and noindex. Pages marked noindex are left out. Pages are grouped into sections by the first part of their path, and legal pages go to the Optional section.
Editing happens in your browser. SagBot keeps the draft for an hour so repeat requests don't fetch the site again, and stores nothing you change.
Questions
What is llms.txt?
A Markdown file at the root of a site, proposed at llmstxt.org. It starts with the site's name as a heading, adds a one-line summary, then lists the pages worth reading in sections, each link with a short description.
Where do I put the file?
At the root of your site, so it opens at https://example.com/llms.txt. Serve it as plain text. Then run the llms.txt checker to confirm it loads and is well formed.
Does Google use llms.txt?
No. Google Search doesn't use llms.txt, and no answer engine promises to read it. It is cheap to add and some AI tools and agents read it, so it is worth having once the basics are in place.
Why only 50 pages?
llms.txt is meant to be a short, curated map, not a copy of the sitemap. The cap also keeps the load on your site small: one request per page, a few at a time. Add more links by hand if you need them.
Is the generator free?
Yes. It is free for everyone and needs no account.