Free llms.txt checker and generator
A clean, correct llms.txt for your site in a minute
Check the llms.txt you have against the format at llmstxt.org, line by line, or let Crawlnote read your sitemap and write one for your first 25 pages.
- Free, no sign-up
- Results with line numbers
- Respects robots.txt
Sample result for an example site
- PassFile found
https://example.com/llms.txt answered HTTP 200.
- PassOne H1 titleline 1
Title "Example Site".
- PassSummary blockquoteline 3
Summary: "Invoicing for small studios."
- FailAbsolute URLsline 8
Relative URL "/docs/start". Use a full address that starts with https://.
- WarnLinks answerline 10
https://example.com/help redirects (HTTP 301). Link the final address.
- PassOptional sectionline 13
Readers that need a shorter context may skip its links.
Illustrative sample for example.com, not a real customer site.
How it works
From domain to file in three steps
No account and no install. Crawlnote fetches only public pages and shows you everything it read.
Enter your domain
Type example.com or any page URL. Crawlnote works from the site root.
Crawlnote reads the site
robots.txt first, then your sitemap or home page links, then up to 25 pages: titles and descriptions only.
Copy or download
Review the file, copy it or download llms.txt, and upload it to the root of your site. Then run the checker on it.
The checker
What the checker looks at
Every rule of the llmstxt.org format, plus the things that break in practice: wrong content types, relative links and dead pages.
One H1 title
The file starts with a single "# Name" line. A missing or second H1 is a fail, with its line number.
Summary blockquote
An optional "> summary" right under the title. Missing is a note, misplaced is a warning.
H2 sections
Links sit in lists under "## Section" headings. Empty or duplicate sections and deeper headings are flagged.
Link lists
Each item is "- [name](url): notes". Loose text, empty names and notes without the colon are flagged.
Absolute, live URLs
Relative URLs fail. Up to 25 links get a HEAD request: 200, redirect or 404, per line.
The Optional section
A section named exactly "Optional" may be skipped by readers, so it should come last. Near-misses are flagged.
The generator
A spec-valid file from your sitemap
Crawlnote groups your pages into H2 sections by the first part of their path, writes an H1 from your site name and a summary from your home page description, and puts legal and account pages in an Optional section.
- Reads sitemap.xml, sitemap indexes and robots.txt Sitemap: lines
- Falls back to home page links when there is no sitemap
- Shows "N of M pages found" when your site is larger
- Each file is run through the checker before you see it
Sample generated file for an example site
# Example Site > Invoicing for small studios: quotes, invoices and payment reminders. ## Pages - [Home](https://example.com/): What Example Site does and who it is for - [Pricing](https://example.com/pricing): Plans and what each includes ## Docs - [Getting started](https://example.com/docs/start): Create an account and send a first invoice - [Reminders](https://example.com/docs/reminders): How payment reminders are scheduled ## Optional - [Privacy](https://example.com/privacy): How customer data is handled
Illustrative sample for example.com.
Pricing
Free for 25 pages
The checker and the 25-page generator are free. A full-site version is planned.
Free
$0
- Check any public llms.txt
- Generate llms.txt for the first 25 pages
- Copy or download the file
- HEAD checks on up to 25 links
Full site
$19one-time
- llms.txt for every page in your sitemap
- llms-full.txt with the text of those pages
- One payment, no subscription
Not on sale yet. Leave your email and we will write once when it is ready.
Honest about the format
What llms.txt can and cannot do
llms.txt is a proposal, not a standard every service follows. Some services read it, others do not, and some major search engines have said they do not use it. Crawlnote makes the file correct; it cannot make anyone read it, and it does not promise rankings or traffic.
New to the format? Read what llms.txt is, see example files, or compare llms.txt and robots.txt.
FAQ
Questions
What is llms.txt?
A Markdown file at the root of a website (example.com/llms.txt) that lists the site's key pages with a one-line note each, proposed at llmstxt.org. It gives software that reads websites a short, clean index instead of making it parse every page.
Will an llms.txt file bring me traffic or better rankings?
llms.txt is a proposal, not a standard every service follows. Some services read it, others do not, and some major search engines have said they do not use it. Crawlnote makes the file correct; it cannot make anyone read it, and it does not promise rankings or traffic.
What does the generator read?
Your robots.txt, your sitemap (including a sitemap index and Sitemap: lines in robots.txt) and then up to 25 pages: the home page first, then top-level pages before deeper ones. If there is no sitemap, it uses the links on your home page. It writes the title and meta description of each page (or its first paragraph) into the file.
Does it store my site or the file?
No. The check and the generated file are shown to you and not saved. Crawlnote keeps only daily totals (how many checks and files were made) and, for rate limiting, a one-way hash of your IP address for about two hours.
What does the $19 full-site option do?
It will generate llms.txt for every page in your sitemap, plus llms-full.txt with the text of those pages. It is not on sale yet: you can leave your email and we will write once when it opens. Nothing is charged on this site today.
How do I stop Crawlnote from reading my site?
Add "User-agent: Crawlnote" and "Disallow: /" to your robots.txt. Crawlnote checks robots.txt before every page it fetches. Details are on the crawler page (/bot).
Check your llms.txt now
One domain, a few seconds, a line-by-line list of what passes and what to fix.