The Protocol
Explained.
Technical Documentation & Inquiries
01What is llms.txt?
llms.txt is a machine-readable file placed at the root of a website to provide Large Language Models (LLMs) with high-context information for better crawling and citation.
02How to use an llms.txt generator?
Enter your URL into the Citeable engine above. It will crawl your site and generate formatted llms.txt and llms-full.txt files in seconds.
03Is there an llms.txt standard?
Yes. It is an emerging standard designed to improve how AI agents like Perplexity, ChatGPT, and Claude interpret website data and reduce hallucinations.
04llms.txt vs robots.txt?
robots.txt controls access for traditional search crawlers; llms.txt provides context for AI agents. One blocks, the other informs.
05Where to host the file?
Place the generated file in your root directory: yourdomain.com/llms.txt.
06What is llms-full.txt?
While llms.txt is a brief index, llms-full.txt contains the complete markdown context of your site for deeper AI comprehension.
07Does this help with SearchGPT?
Absolutely. Providing structured markdown context makes your site significantly more likely to be used as a primary citation in AI-native search results.
08Is the generator free?
The Citeable web engine is free for manual generation. Our WP Plugin automates this for high-velocity publishers.
09What format is used?
The protocol uses standard Markdown, utilizing headers and lists to create a hierarchy that LLMs can easily parse.
010Does it work with any tech stack?
Yes. Once generated, the text files can be hosted on any platform including Next.js, WordPress, Webflow, or custom static sites.