Free tool, no signup
llms.txt validator
An llms.txt file is a Markdown map of a site for AI tools: one # title, a > summary line, then ## sections of [name](url) links. This validator fetches /llms.txt (or reads what you paste), checks it against the llmstxt.org format and lists each problem with its line and the fix.
A valid llms.txt
One # title, a > summary, then ## sections of links with a colon before each note. ## Optional holds what tools may skip.
# Acme
> Acme is invoicing software for freelancers in the US and UK.
## Docs
- [Pricing](https://acme.com/pricing): plans, limits and what each costs
- [Getting started](https://acme.com/docs/start): send a first invoice in five minutes
## Optional
- [Changelog](https://acme.com/changelog)Questions
What does a valid llms.txt need?
Only a single # title on the first line is required by the llmstxt.org format. A useful file also has a > summary under the title and at least one ## section listing '- [Page name](https://example.com/page): what it covers' links. A file with no links gives AI tools nowhere to go, so we count that as an error.
Does llms.txt help ChatGPT or Google cite my site?
Nobody has shown that any major AI assistant ranks or cites pages because of llms.txt. It's cheap to add and some agent tools read it, so treat it as hygiene rather than a ranking lever, and measure citations directly instead of assuming.
What about llms-full.txt?
llms-full.txt is an optional companion that holds the full text of your key pages in one file. We check that it answers, but we don't validate its contents, because the format leaves it free-form.
Why does my llms.txt show as HTML?
Many site builders answer every unknown URL with the homepage. If /llms.txt returns your HTML with HTTP 200, there is no real file there, even though the address loads.