geo-fundamentals

llms.txt

Also known as: LLM-Readable Site Overview, AI Context File, Markdown Site Summary

A Markdown file placed at /llms.txt that provides a curated, LLM-friendly overview of a website's content, designed to fit within AI context windows.

What is llms.txt?

llms.txt is a proposed standard for a Markdown file hosted at the root of a website (e.g., example.com/llms.txt) that provides a concise, curated overview of the site's most important content specifically for large language models. Unlike sitemaps which list all pages, llms.txt offers a selective summary with brief descriptions and links to key resources—formatted to fit within an LLM's limited context window. The goal is to help AI assistants quickly understand what a site offers and access its most relevant documentation or content at inference time.

Why It Matters

LLMs have limited context windows and cannot efficiently crawl entire websites during inference. llms.txt solves this by providing a pre-curated briefing document that gives AI assistants immediate access to essential information about your site. This is especially valuable when users ask chatbots questions about your product, library, or service—the llms.txt file helps ensure accurate, well-informed responses rather than hallucinations or outdated information.

Use Cases

Developer Documentation

Help AI coding assistants understand your library or API by linking to key docs and examples

Product Information

Give AI chatbots accurate context about your product when users ask questions

Curated Content Access

Provide a selective summary of your most important pages, not an exhaustive list

Framework & Library Support

Enable AI tools to provide accurate code suggestions and answers about your technology

Context Window Optimization

Structure content to fit within LLM token limits while covering essential information

Optimization Techniques

Effective llms.txt files use clean Markdown formatting with a clear title (H1), an optional blockquote description, and organized sections with descriptive links. Each link should include a brief explanation of what the page contains. Use an 'Optional' section for secondary content that can be skipped if context is limited. Keep the file concise—prioritize quality over quantity to fit within typical LLM context windows.

Metrics

Success of llms.txt implementation can be measured by monitoring AI assistant accuracy when answering questions about your site, tracking llms.txt file requests in server logs, and gathering user feedback on AI-generated responses related to your content.

How LLMs Interpret This

LLMs interpret llms.txt as a curated briefing document that provides essential context about a website. It's designed for inference time—when a user asks an AI assistant about a topic, the assistant can fetch and include the relevant llms.txt content to provide accurate, up-to-date information within its context window.

Code ExampleTypeScript

1# Acme Documentation
2 
3> Acme is a TypeScript framework for building modern web applications with server-side rendering and edge deployment.
4 
5Key features:
6- Server-side rendering with streaming support
7- Edge-first deployment architecture  
8- Built-in authentication and database adapters
9 
10## Getting Started
11 
12- [Quick Start Guide](https://docs.acme.dev/quickstart.md): Set up your first Acme project in 5 minutes
13- [Core Concepts](https://docs.acme.dev/concepts.md): Understanding routing, data fetching, and rendering
14- [API Reference](https://docs.acme.dev/api.md): Complete API documentation
15 
16## Examples
17 
18- [Todo App](https://github.com/acme/examples/todo.md): Basic CRUD application demonstrating core patterns
19- [Auth Example](https://github.com/acme/examples/auth.md): Authentication flow with multiple providers
20 
21## Optional
22 
23- [Migration Guide](https://docs.acme.dev/migration.md): Upgrading from v1 to v2
24- [Contributing](https://github.com/acme/acme/CONTRIBUTING.md): How to contribute to Acme

Resources

llms.txt Official Specification

llms.txt Directory

Geordy llms.txt Generator

Export Structured Data

schema.json

{
  "@context": "https://schema.org",
  "@type": "DefinedTerm",
  "name": "llms.txt",
  "alternateName": [
    "LLM-Readable Site Overview",
    "AI Context File",
    "Markdown Site Summary"
  ],
  "description": "A Markdown file placed at /llms.txt that provides a curated, LLM-friendly overview of a website's content, designed to fit within AI context windows.",
  "inDefinedTermSet": {
    "@type": "DefinedTermSet",
    "name": "AI Optimization Glossary",
    "url": "https://geordy.ai/glossary"
  },
  "url": "https://geordy.ai/glossary/geo-fundamentals/llms-txt"
}

Details

Category: geo-fundamentals
Type: technique
Level: developer
GEO Readiness: Unstructured

Keywords

llms.txtLLM contextAI-readable contentMarkdown site summaryLLM documentationAI context fileinference timecontext window