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

# Markdown twin

_Also known as: Markdown mirror, .md twin_

**A markdown twin is a clean markdown version of an HTML page, served at the same path plus .md, so agents can read the content without parsing the page.**

A **markdown twin** is a parallel, machine-friendly copy of a page. Append `.md` to a canonical URL (or negotiate via the `Accept` header) and you get the same content as structured markdown - no navigation, ads, or client-side rendering to wade through.

Twins give agents a stable, low-noise source that stays in sync with the human page, which improves both accuracy and citation.

## In GraphCanon

Most GraphCanon pages - tools, categories, trust reports, and this glossary - expose a ".md" twin. Metadata advertises it, and content negotiation serves it to agents automatically.

## See also

- [MCP & agent docs](/docs/mcp)
- [llms.txt index](/llms.txt)

## Related terms

- [llms.txt](/glossary/discovery-for-agents/llms-txt.md)
- [Structured data (JSON-LD)](/glossary/discovery-for-agents/structured-data.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/_