llms.txt kit

Give AI crawlers
a map of your site.

llms.txt is one small markdown file at your site's root that tells language models what your site is and what's worth reading. Fill the form — the file writes itself.

The basics
Key pages group links under headings
llms.txt

        
      

      

        
        
        
      

      
Serve it at yoursite.com/llms.txt — root of the domain, plain text, done.

    

  


  

    
Already have one? Check it.

    
Enter a domain — we fetch its /llms.txt and lint it against the spec.

    

      
      
    

    
  


  

    
What is llms.txt?

    

      
The one-paragraph version

      
A plain-markdown file served at /llms.txt that tells large language models what your site is and which pages matter, proposed by Jeremy Howard (Answer.AI) in 2024. Anthropic, Stripe, Cloudflare, and thousands of other sites publish one.

      
Do AI crawlers actually read it?

      
Adoption is growing, not universal. But it's one tiny text file: near-zero cost, and any LLM-backed tool that does fetch it will summarize and cite you correctly instead of guessing.

      
How is it different from robots.txt?

      
robots.txt says what crawlers may not touch. llms.txt is the opposite — a curated map of what they should read first, with context written by a human. (Or, in this site's case, by an AI.)