---
title: "llms.txt"
type: "glossary-term"
category: "Discovery for agents"
canonical_url: "https://www.graphcanon.com/glossary/discovery-for-agents/llms-txt"
updated: "2026-07-09"
---

# llms.txt

**llms.txt is a plain-text file at a site's root that gives AI crawlers a curated, compact map of the most useful pages - like robots.txt, but for LLMs.**

**llms.txt** is an emerging convention: a markdown-formatted file served at `/llms.txt` that points language-model crawlers at a site's most important, machine-readable content. It saves them from guessing at navigation or parsing cluttered HTML.

A companion `/llms-full.txt` can inline the full content in one file. Together they make a site legible to agents by intent, not by scraping.

## In GraphCanon

GraphCanon publishes "/llms.txt" as an index of its markdown twins, API, and key surfaces, and "/llms-full.txt" with the whole corpus - so agents can read the graph as data.

## See also

- [llms.txt](/llms.txt)
- [Full corpus](/llms-full.txt)

## Related terms

- [Markdown twin](/glossary/discovery-for-agents/markdown-twin.md)
- [Generative engine optimization (GEO)](/glossary/discovery-for-agents/generative-engine-optimization.md)

[Discovery for agents](/glossary/discovery-for-agents.md) · [All glossary terms](/glossary.md)

---

**Machine-readable endpoints**

- JSON: [`/api/graphcanon`](/api/graphcanon)
- LLM index: [/llms.txt](/llms.txt)
- Full corpus: [/llms-full.txt](/llms-full.txt)

_GraphCanon - The knowledge graph for AI development. https://www.graphcanon.com/_