Skip to main content
To start working with MAGI, you’ll need:
  1. A basic understanding of Markdown
  2. A text editor for creating .mda files
  3. Optionally, the url2mda tool to convert web content to MAGI format

​
Understanding MAGI Components

MAGI has three optional components that enhance standard Markdown:
  1. YAML Front Matter: Provides structured metadata (like title, doc-id).
  2. ai-script blocks: Embeds JSON instructions for AI/LLM processing.
  3. Footnotes with JSON: Defines typed relationships between documents (e.g., [^ref1]: {"rel-type": ...}).
MAGI ComponentsEach component is optional - use only what you need.

​
Creating a Simple MAGI File

Create a file with the .mda extension. Here’s an example structure: 
---
doc-id: "example-123"
title: "My First MAGI Document"
description: "A simple example of MAGI format"
tags: ["example", "getting-started"]
created-date: "2024-06-10T10:00:00Z"
---

# Hello MAGI

This is standard Markdown content.

(Your ai-script block would go here - see below)

This document is related to our documentation[^ref1].

[^ref1]: See JSON definition below.

​
Adding AI Instructions

Inside your .mda file, you can add an ai-script block like this: 
{
  "script-id": "summary-request",
  "prompt": "Summarize this document briefly.",
  "priority": "medium",
  "auto-run": true
}

​
Convert Web Content with url2mda

The easiest way to test MAGI is with our url2mda service, which converts web pages to MAGI format: 
curl -X POST https://url2mda.sno.ai/convert \
  -H "Content-Type: application/json" \
  -d '{
    "url": "https://example.com",
    "subpages": false
  }'
Try it out in your browser: https://url2mda.sno.ai

​
Explore the Open Source Toolkit

MAGI is fully open source and includes tools like url2mda that you can run locally:
  1. Clone the repository: git clone https://github.com/snoai/magi-markdown
  2. Navigate to the url2mda directory: cd magi-markdown/apps/url2mda
  3. Install dependencies: pnpm install
  4. Run locally: pnpm dev
View MDA examples in the docs/mda-examples directory to see MAGI in action for various use cases. You’re now ready to create AI-friendly content with MAGI. That’s it! You’re now ready to create AI-friendly content with MAGI.