> ## Documentation Index
> Fetch the complete documentation index at: https://docs.getcited.in/llms.txt
> Use this file to discover all available pages before exploring further.

# llms.txt

> A plain-text file at a website's root that tells AI crawlers which pages to prioritize — the robots.txt equivalent for LLMs.

**llms.txt** is a plain-text file placed at the root of a website (e.g., `example.com/llms.txt`) that provides a structured summary of the site's most important content for AI crawlers and LLMs. It follows the llms.txt specification (llmstxt.org), serving a similar purpose to robots.txt but focused on content discovery rather than access control.

## Why it matters

AI crawlers and LLMs use llms.txt to understand which pages on a site are most relevant for answering user queries. Without it, an LLM must discover content through its own crawling and indexing — which may miss important pages or over-index low-value ones. A well-structured llms.txt file explicitly signals "these are the pages worth reading" to every AI crawler that supports the standard.

## How Cited uses it

Cited's docs site uses Mintlify, which auto-generates both `/llms.txt` (page listings with descriptions) and `/llms-full.txt` (full markdown content of every page). Both files are referenced via HTTP `link` headers on every page response.

## Related concepts

* [Fix your llms.txt and robots.txt](/playbooks/llms-txt-and-robots) — the practical optimization playbook
* [Crawl budget](/glossary/crawl-budget) — llms.txt helps crawlers allocate budget efficiently
* [What sources LLMs cite](/concepts/foundations/ai-citation-sources) — llms.txt improves discoverability