llms.txt
llms.txt is an emerging standard plain-text file at the root of a website that helps AI engines understand the site's purpose, key pages, and preferred content. It functions like robots.txt but for LLM-facing crawlers.
What it is
The llms.txt file is a markdown-formatted document hosted at /llms.txt that tells large language models what the site is about, where to find canonical content, and what to prioritize. It typically includes a one-paragraph site description, a categorized list of key URLs (core pages, guides, case studies), and links to deeper resources. A companion file, llms-full.txt, may include a longer plain-text snapshot of the site's main content for direct ingestion. The standard was proposed by Jeremy Howard in 2024 and has been adopted by Anthropic, OpenAI, Mintlify, and others.
Why it matters for GEO
Without llms.txt, AI crawlers must extract meaning from JS-rendered HTML, often missing key facts. With it, you control the framing — you tell the model what your brand does and which pages matter most. This is one of the cheapest, highest-leverage GEO investments.
The CiterLabs perspective
CiterLabs serves both /llms.txt and /llms-full.txt at citerlabs.com, and offers a free /tools/llms-txt-generator for any site.
- llms-full.txt — llms-full.
- robots.txt — robots.
- Generative Engine Optimization (GEO) — Generative Engine Optimization (GEO) is the practice of structuring a brand's content, entity footprint, and third-party signals so that AI engines like ChatGPT, Perplexity, Claude, and Google AI Overviews cite that brand inside their generated answers.
Want to be cited for terms like llms.txt?
CiterLabs runs 60-day GEO Sprints with a +20pt citation-share lift guarantee or 100% refund. Apply in two minutes — async by default, no call required.