llms.txt generator: a draft file from your sitemap

Enter a domain. We read your homepage and sitemap, fetch titles and descriptions of up to 20 pages, and build a draft llms.txt in the llmstxt.org format that you can edit, copy or download.

What llms.txt is

llms.txt is a plain Markdown file at the root of a site (https://example.com/llms.txt) that gives language models a short, curated map of the content: what the site is, and which pages matter most. The format comes from the llmstxt.org proposal:

• an H1 with the name of the site or project (the only required part);
• a blockquote with a one- or two-sentence summary;
• optional paragraphs with more context;
• H2 sections with Markdown link lists: - [Page title](https://…): short note;
• an optional section named Optional for links that can be skipped when context is short.

It is a community proposal, not an official standard, and support by AI products varies. Think of it as a cheap, low-risk addition: it does not replace robots.txt, sitemaps or good pages. Our llms.txt guide covers what it can and cannot do.

How the generator builds the draft

1. Homepage. We fetch your home page and take the site name (from og:site_name or the title) and the summary (from the meta description).
2. Sitemap. We look for sitemaps listed in robots.txt, then /sitemap.xml, /sitemap_index.xml and /wp-sitemap.xml, and read up to 50 URLs from your domain. Tag, category, author and pagination URLs are skipped.
3. Pages. We fetch up to 20 of the shallowest pages in parallel with a short timeout and use their titles and meta descriptions as link notes. Pages marked noindex are left out.
4. Sections. Pages are grouped by their first URL folder (for example /blog/ or /docs/); top-level pages go to "Main pages", the rest of the sitemap URLs go to "Optional".

Edit before you publish

The result is a draft. Before uploading it:

• rewrite the summary so it says plainly what the site is and who it is for;
• keep the 10–30 pages that best explain your site (guides, pricing, docs, key articles) and drop thin or outdated ones;
• make each note a short factual description, not a slogan;
• save the file as UTF-8 text named llms.txt in your site root.

On WordPress you can upload the file to the root folder via your host's file manager or use a plugin; see how to add llms.txt to WordPress. Then run the AI crawler checker to confirm the file is found and that robots.txt lets the AI search bots in.

Limits

To keep the tool fast and polite to your server we read at most 50 sitemap URLs and fetch at most 20 pages, each with a few seconds' timeout. Sites that render content only with JavaScript, block unknown bots, or have no sitemap will get a thinner draft; add the missing pages by hand.

FAQ

Do I need llms.txt for SEO?

No. llms.txt is not a ranking factor for Google or Bing and is not required by any search engine. It is an optional file that some AI tools and agents may read to understand your site faster.

Where do I put the file?

In the root of your domain, so it opens at https://your-domain/llms.txt as plain text. On WordPress, upload it to the folder that contains wp-config.php or use a plugin that serves it.

Why are some of my pages missing?

The generator reads at most 50 sitemap URLs and fetches 20 pages, skipping tags, categories, pagination and noindex pages. Add any important page by hand before publishing.

What is llms-full.txt?

Some sites also publish llms-full.txt with the full text of key pages in one file. The llmstxt.org proposal focuses on llms.txt; llms-full.txt is a convention used by some documentation tools.

Does the generator store my site?

The result is cached for one hour so repeat requests are fast. No account is needed, and we only fetch your homepage, robots.txt, sitemap and up to 20 pages.

Other free tools: AI crawler checker · Sponsored link checker · All tools

Updated: 2026-10-16