Check your llms.txt before an AI reads it.
We read your llms.txt against the llms.txt proposal and its best practices, and show which important pages it points to.
- Just your domain
- No signup
- Results gone in 24 hours
What llms.txt is
A Markdown file at `/llms.txt` that tells a language model what your site is and where its most useful pages are. It is a proposal from llmstxt.org, not a standard, and nothing requires it.
Its shape is simple: one `# Title` first, an optional `>` summary, then `## Sections` listing links as `- Name: notes`. A section called `Optional` marks links a model can skip when it is short of room.
What this checks
Whether it is a file at all — a server error, or your app's HTML page answering where the file should be.
The title, which is the proposal's one requirement.
The links: list items that are not links, relative addresses a model cannot resolve, and links without a short description.
Best practice: a one-line summary, sections that hold only links, and whether your homepage and pages like documentation, about and contact are in it. Judged from the file alone — we do not open the pages it links to.
Length. It is meant to fit in a model's context next to the question; the full text belongs in `/llms-full.txt`.
Not having one is fine
If there is no llms.txt we say so, and that is all. It is optional, and a checker that colours its absence red is how people end up publishing an empty one.
llms.txt questions
Does llms.txt affect my Google ranking?
No. Google does not use it. It is read by some AI tools and assistants when they are pointed at your site.
Is llms.txt the same as robots.txt for AI?
No. robots.txt says what crawlers may fetch; llms.txt suggests what is worth reading. To stop AI crawlers, use robots.txt — our robots.txt checker shows which ones your rules allow.
What is llms-full.txt?
A companion file with the full text of your documentation in one place. llms.txt stays short and points to it.