# llms.txt validator and generator

> Validate your llms.txt file against the llmstxt.org format, or generate one from your sitemap. Free, no sign-up, ready to copy or download.

URL: https://gradual.pro/en/tools/llms-txt-validator

Updated: 2026-09-30

Check whether your llms.txt follows the format language models expect, or create one from your sitemap in a minute.

## What does the validator check?

We follow the format proposed at llmstxt.org:

- A single **H1** at the top with the name of the site or business.
- A **summary** as a blockquote (“> ”) before the sections.
- **H2 sections** that group the links, such as “## Services” or “## Guides”.
- **Link lists** in the format “- [Title](URL): note”.
- **Absolute URLs**, because the file is read outside your site.

We also check that it stays under 50 KB, that it is served as text rather than as an HTML page, and whether you publish the optional llms-full.txt.

## How is the draft generated?

We read the sitemap declared in your robots.txt, or /sitemap.xml if none is declared, and take up to 60 pages in the main language. We group them by the first folder of the URL and turn each address into a readable title. The name and summary come from your homepage's title and meta description.

It is a starting point, not the finished file: check the titles, add a short note after each link explaining what the page covers, and remove anything that adds nothing, such as legal or tag pages. A good llms.txt is short and picks out what matters.

## Is an llms.txt file worth having?

It is a proposed standard, not a requirement, and not every assistant reads it yet. Even so, it costs little to maintain and helps a model find your key pages without crawling the whole site, especially when a user asks it to look at your website.

It does not replace the basics: bots being able to get in, content that shows without JavaScript and pages that answer specific questions. We check all of that in the [AI visibility checker](/en/tools/ai-visibility-checker) and explain the file in [what is llms.txt](/en/glossary/llms-txt).

1. To validate, enter your domain: we read https://yourdomain/llms.txt and check its structure line by line.
2. You see every check, passed or failed, with how to fix it, and your file with the problem lines highlighted.
3. To generate one, we read your sitemap plus your homepage's title and description, and build a draft grouped into sections.
4. Edit the draft, copy or download it, and upload it to the root of your domain.

## FAQ

### Where do I upload my llms.txt?

To the root of your domain, so it loads at https://yourdomain.com/llms.txt. On WordPress you can upload it to your hosting or use a plugin; on Shopify or Wix it depends on whether they allow root files or redirects.

### What is the difference between llms.txt and llms-full.txt?

llms.txt is an index of links with short notes. llms-full.txt is optional and gathers the full content of your key pages in Markdown in a single file, so a model can read it without visiting each page.

### Does it replace my sitemap or robots.txt?

No. The sitemap lists every URL for search engines and robots.txt says who can crawl. llms.txt is an annotated selection of your most useful pages for a language model. All three work side by side.

### Do you store my llms.txt?

No. We read the file to validate it and cache the result for an hour to avoid fetching it again. The draft is edited in your browser.