Free llms.txt Generator and Checker

Enter your domain. If your site has an llms.txt, you get a line-by-line check against the llmstxt.org format and Chrome Lighthouse's rules, with a fix for each problem it finds. If it doesn't, you get a ready-to-edit draft built from your sitemap.

Free, no signup. Have a draft? Paste it instead.

The file is optional. Google says it won't change your Search rankings, details below.

ryandoser.com/llms.txt
  1. # Ryan DoserH1 title
  2. > AI marketing strategy, Claude Code workflows,Summary
  3. > and automation systems from Ryan Doser...
  4. ## Key pagesH2 section
  5. - [Services](https://ryandoser.com/services/):Link works
  6. Overview of all offers
  7. - [AI Visibility Audit](https://ryandoser.com/Link works
  8. ai-visibility-audit/): Free audit that...
This site's own file, checked November 17, 2026: 14 checks passed, no warnings, no failures.
Paste a draft llms.txt to check it

Checked in your browser against the same format rules. Nothing is sent to a server, so link and serving checks are skipped.

What this llms.txt checker tests

This tool writes the file and checks it, using the copy that's live on your site: how it loads, what it says and whether its links work.

  • Lighthouse's rules. No server error, per Chrome's documentation, plus the content rules DebugBear reports: an H1, at least 50 characters and at least one [text](url) link. This tool doesn't run Lighthouse itself.
  • The llmstxt.org format. The H1 is the only required part. Everything else is checked as a suggestion: a summary blockquote, H2 sections of - [name](url): notes links and an "Optional" section. Relative links (missing the https:// part) and duplicate links get flagged as cleanup.
  • The links themselves. The first 20 links get fetched, and broken ones are flagged. A broken link leads an agent to an error page.
  • How the file is served. Status code, content type and redirects. It also catches sites that show a web page at /llms.txt instead of the text file.
  • The extras. Markdown copies of your listed pages, /llms-full.txt and a rel="describedby" link from your homepage. All optional, all reported as such.

What is an llms.txt file?

An llms.txt file is a short markdown file, usually at the root of a website, designed to tell language models what the site is and which pages matter. Jeremy Howard of Answer.AI proposed the format at llmstxt.org. Here is the shape the spec describes:

# Acme Analytics

> Acme Analytics is web analytics software for small online stores.

Acme runs in the browser and needs no cookie banner.

## Docs

- [Quick start](https://acme.example/docs/start.md): Install the script in five minutes
- [API reference](https://acme.example/docs/api.md): Every endpoint with examples

## Optional

- [Changelog](https://acme.example/changelog.md): Release history

The H1 with the site name is the only required part. After it comes an optional one-line summary in a blockquote, optional plain paragraphs, and optional H2 sections that list links. A section named "Optional" holds secondary links an agent can skip when it needs less context.

The spec also suggests a clean markdown copy of each important page, at the page's URL with .md added (or index.html.md for folder URLs), so an agent can read the page without the menus and scripts.

Does llms.txt help with AI search?

Google: no

Google's AI optimization guide says you don't need AI text files to appear in Google Search or its AI features, and that an llms.txt "will neither harm nor help your site's visibility or rankings in Google Search, as Google Search ignores them."

ChatGPT and Claude: unconfirmed

OpenAI and Anthropic publish llms.txt files for their own docs. That shows they publish one, not that their assistants read yours, and neither has documented that they do. OpenAI's crawler docs point site owners to robots.txt, not llms.txt.

Chrome Lighthouse: checked

Lighthouse 13.3 added an experimental Agentic Browsing audit that checks llms.txt. It's about AI agents that browse sites, not search rankings, and a missing file only counts as "not applicable."

Ahrefs also found little activity in its sample. It checked 137,000 domains, and about 28% had an llms.txt. Of roughly 38,000 valid files, 97% got zero requests in May 2026 (more in my AI search myths post). The file is cheap to keep. If you publish one, keep its links and notes current, and spend your real effort on the pages it points to.

How the generator builds your file

  1. Finds your sitemap. It reads the sitemap listed in robots.txt, or tries /sitemap.xml, /sitemap_index.xml and /wp-sitemap.xml. No sitemap? It uses the links on your homepage.
  2. Picks up to 40 pages. Pages your homepage links to come first, then a spread across your sections, so one big blog doesn't crowd out everything else. Tag pages, logins, carts, form pages and old campaign pages get skipped.
  3. Reads each page's own words. The title (with your brand name trimmed off) becomes the link name, and the meta description becomes the note. No AI rewriting, so the draft says what your pages say. Check it before you publish.
  4. Groups and formats. Pages are grouped by folder (Blog posts, Docs, Services), privacy and terms pages go under "Optional", and the result follows the llmstxt.org format.

If a page's title or description is weak or out of date, the draft will be too. That's worth fixing on the page itself, since search results show those same words.

How to add llms.txt to your site

  • Any site with file access: save the file as llms.txt and upload it to your root folder. Open yoursite.com/llms.txt in a browser. You should see plain text, not your homepage. Hosted builders that don't allow uploads may have an llms.txt setting or none at all.
  • WordPress: Yoast SEO and All in One SEO can generate the file for you. llmstxt.org lists both, along with Wix and docs platforms like Mintlify and GitBook.
  • Static and app hosts (Cloudflare Pages, Netlify, Vercel): put the file in your public or static folder. If /llms.txt shows your app instead, a fallback route is catching it. Serve static files before the fallback.
  • Then run the checker again to confirm it loads as text, the first 20 links work and Lighthouse's rules pass.

llms.txt vs robots.txt vs llms-full.txt

FileWhat it doesPart of a standard?
robots.txtTells crawlers what they may fetch. This is how you allow or block GPTBot, ClaudeBot and others.Yes (Robots Exclusion Protocol)
llms.txtA short reading list of your key pages for language models. Blocks nothing.Proposed format at llmstxt.org
llms-full.txtThe full text of your pages in one file, mostly used by docs sites.Community convention, not in the spec

Frequently asked questions

How do I check if my llms.txt file is valid?

Type your domain into the checker at the top of this page. It fetches yoursite.com/llms.txt and checks it against the llmstxt.org format. It also runs the checks behind Chrome's Lighthouse llms.txt audit: no server error, plus the three content rules DebugBear reports (a main heading, or H1, at least 50 characters and at least one markdown link). Then it tests the first 20 links in the file, how the file is served and whether your pages have markdown copies. Each problem it finds comes with a plain-English fix. Working on a draft? Paste it instead.

How do I create an llms.txt file?

Enter your domain above. If your site has no llms.txt, or a broken one, the generator reads your sitemap, picks your key pages, and writes a draft in the llmstxt.org format using each page's own title and meta description. Edit the draft, save it as llms.txt and upload it to the root of your site so it loads at yoursite.com/llms.txt as plain text.

Does llms.txt help my site show up in ChatGPT or Google AI Overviews?

Google says no, and nobody else has confirmed it does. Google's AI optimization guide says Google Search ignores llms.txt, including its AI features, and that the file will neither help nor hurt your rankings. OpenAI and Anthropic publish llms.txt files for their own docs, but neither has documented that its assistants read the one on your site. Chrome's Lighthouse does check it in an experimental audit for AI agents that browse websites. It's cheap to keep, so add one if you like, but don't build your AI search strategy on it.

What does the Lighthouse llms.txt audit check?

Lighthouse 13.3 added an experimental Agentic Browsing category with an llms.txt audit. Chrome's documentation says a server error fails the audit and a missing file (a 404) is marked not applicable, because the file is optional. DebugBear's write-up of the audit adds three content checks: the file needs an H1, at least 50 characters and at least one link in [text](url) format. This checker tests all of those, without running Lighthouse itself.

Where do I put the llms.txt file?

In the root of your website, so it loads at https://yoursite.com/llms.txt. Serve it as plain text (text/plain or text/markdown), not as a web page. The spec also allows a file in a subfolder, like /docs/llms.txt, that covers only the pages under that folder.

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

llms.txt is a short map: your site name, a one-line summary and links to your key pages. llms-full.txt is a community convention, popular with documentation sites, that puts the full text of your pages in one file. llms-full.txt is not part of the llmstxt.org spec, so this checker treats it as a bonus, not a requirement.

Is llms.txt the same as robots.txt?

No. robots.txt tells crawlers what they may and may not fetch. llms.txt is a reading list that points language models to your most useful pages. It doesn't block or allow anything. To control AI crawlers like GPTBot or ClaudeBot, use robots.txt.

Do you save the sites I check?

This site doesn't keep a history of the domains you check. Results are cached by site for 10 minutes so repeat checks and share links load fast, and there's a fair-use limit per visitor so the free tool stays up for everyone. Pasted drafts are checked in your browser and not sent to this site's servers.

Sources

Format rules from llmstxt.org. Lighthouse behavior from Chrome's llms.txt audit documentation and DebugBear's write-up of its content checks. Google's position from its AI optimization guide. This tool isn't affiliated with any of them. Page last updated November 17, 2026.

The AI SEO System I use to rank in Google & AI search. Runs in Claude or any AI setup.

Get my system

Free AI Marketing Guide

Get the free AI Marketing Guide

The systems I use to run my agency solo. No coding needed to start:

Join over 10,000 subscribers getting my weekly AI marketing newsletter. Unsubscribe anytime. Privacy policy.