What is llms.txt?

llms.txt is a proposed web standard (defined at llmstxt.org) analogous to robots.txt, but designed for AI language models rather than traditional search crawlers. Where robots.txt tells bots which pages to crawl or avoid, llms.txt provides a structured, plain-text summary of what a site is, who created it, what it offers, and how AI systems should interpret and cite it.

A well-formed llms.txt file typically includes: the entity name and description, the person or company behind the site, a list of key pages with their purposes, the services or products offered, and guidance for AI systems on how to attribute information from the site. It's written in Markdown-like plain text, optimised for tokenisation and direct inclusion in an LLM's context window.

While llms.txt is not yet an official standard adopted by major AI labs, it represents a proactive GEO (Generative Engine Optimisation) signal. Sites that publish this file are more machine-legible — making it easier for AI systems to build an accurate, complete picture of the entity when generating answers about the business or its services.