llms.txt — The Ultimate Guide

llms.txt is an emerging Markdown-based file (sibling to robots.txt) that gives Large Language Models a curated index of your most important pages. Adopted by Anthropic, Cloudflare and a growing list of brands, it is rapidly becoming the de-facto standard for Generative Engine Optimization.

Why llms.txt matters

LLMs allocate a limited token budget per crawl. A well-crafted llms.txt acts as a sitemap optimized for answer extraction rather than ranking — it tells the model which pages to read first, what they mean, and how they connect.

Minimal structure

# Brand name
> One-paragraph value proposition.
## Core pages
- [Home](https://example.com/): description.
- [Pricing](https://example.com/pricing): description.
## Key resources
- [Article](https://example.com/article): description.

FAQ

Is llms.txt an official standard?

Not yet — but adoption is accelerating. Anthropic, Mintlify and Cloudflare have implemented it.

Does llms.txt replace robots.txt?

No. They complement each other: robots.txt controls access; llms.txt curates attention.

Where do I put it?

At your domain root: https://yourdomain.com/llms.txt