llms.txt generator

What this generator creates

The llms.txt proposal uses Markdown. A file starts with one H1 title and can add a short blockquote summary, notes, and H2 sections containing links. A section named Optional identifies secondary pages that can be skipped when a consumer needs a shorter context.

Read the current llms.txt proposal and format before publishing the file. This generator checks its own fields and creates that basic structure. It does not fetch the linked pages or prove that another service reads them.

llms.txt does not improve Google rankings

Google Search says it ignores llms.txt files for visibility and rankings. Publish one only when an agent or service you care about explicitly uses it. Keep normal crawling, indexing, internal links, and useful page content as separate work.

See Google's current generative AI search guidance for that distinction.

Choose the pages yourself

This web tool reads URLs from the sitemap files you submit. It does not crawl the pages or decide which ones matter, so review the selected URLs before you publish the file.

Check the published file

Check the Markdown shape with the llms.txt validator before and after you publish it.

What to put in llms.txt

Think of the file as a reading list for an agent that has a few seconds to understand your site. Start with what the site is in one sentence. Then link the pages that answer the questions people ask most: documentation, pricing, setup, policies. Leave out blog archives, tag pages and anything a reader would skip.

Put the pages that matter less under an Optional heading. An agent short on space can drop that section and still get the main picture.

Where to publish the file

Save it as /llms.txt at the root of the site, served as plain text or Markdown. It does not replace robots.txt or the sitemap, and it does not control which crawlers can read the site.

Check your llms.txt with your agent

The seo crawl command checks whether /llms.txt exists and whether its links load, along with Markdown copies of your pages and the robots.txt rules for AI search and AI training crawlers. Your agent can update the file in your codebase when pages move. Ask:

Check whether example.com has an llms.txt with working links, and list the pages that are missing from it

The crawl runs from the CLI on your machine. Install it and run setup:

npm i -g seo && seo start

Or add the hosted MCP server to your agent and sign in with Google:

llms.txt generator questions