Magic: The All-in-One Open-Source AI Productivity Platform

This repository profile is provided by osrepos.com, an open source repository discovery platform.

Magic: The All-in-One Open-Source AI Productivity Platform

Summary

Magic is the first open-source all-in-one AI productivity platform, integrating a generalist AI agent, workflow engine, instant messaging, and collaborative office system. It aims to help enterprises build and deploy AI applications to achieve significant productivity increases, offering a comprehensive suite of tools for intelligent automation and collaboration.

Repository Information

Analyzed by OSRepos on October 31, 2025

Use at your own risk

OSRepos shares public repositories for knowledge and discovery only. Any installation, execution, configuration, or use of code from these repositories is the user's own responsibility. Always review the repository, source code, dependencies, licenses, and security implications before running or installing anything. OSRepos is not responsible for issues, damages, or losses resulting from third-party repositories.

Introduction

Magic is presented as the first open-source all-in-one AI productivity platform, designed to empower enterprises of all sizes to quickly build and deploy AI applications, aiming for a 100x increase in productivity. It's not just a single AI product, but a comprehensive product matrix with rich capabilities, including:

  • Super Magic: A general-purpose AI Agent for complex task scenarios, supporting autonomous task understanding, planning, action, and error correction.
  • Magic Flow: A powerful visual AI workflow orchestration system for building complex AI Agent workflows without coding.
  • Magic IM: An enterprise-grade instant messaging system that integrates AI Agent conversations with internal enterprise communication.
  • Teamshare OS: An upcoming enterprise-grade online collaborative office system, featuring intelligent document management, Magic Table, and project collaboration.

Additionally, Magic open-sources infrastructure components like Agentlang (AI Agent Framework), Magic Lens (HTML to Markdown conversion), and upcoming tools like Magic Use (browser operation for AI Agents) and Sandbox OS.

Installation

To get started with the self-hosted Community Edition of Magic, you'll need Docker 24.0+ and Docker Compose 2.0+. The installation process is straightforward using Docker:

  1. Clone the repository:
    git clone https://github.com/dtyq/magic.git
    cd magic
  2. Start the service:
    ./bin/magic.sh start

    For background operation, use ./bin/magic.sh daemon. You can check the status with ./bin/magic.sh status and view logs with ./bin/magic.sh logs.

  3. Configure Environment Variables:

    Copy the example environment files and configure them. You must configure at least one large language model's environment variables for Magic to function normally.

    cp .env.example .env
    cp config/.env_super_magic.example .env_super_magic
  4. Access Services:
    • API Service: http://localhost:9501
    • Web Application: http://localhost:8080 (Default accounts: 13812345678 / letsmagic.ai, 13912345678 / letsmagic.ai)
    • RabbitMQ Management Interface: http://localhost:15672 (Username: admin, Password: magic123456)

Examples

Magic offers a wide range of functionalities demonstrated through various components:

  • Super Magic Case Studies: Explore how Super Magic handles complex tasks like "Analysis of Investment Insights from Buffett's 2025 Shareholders Meeting" or "SKU Sales Forecast Requirements". More examples are available on the Official Website.
  • Visual Workflows: Magic Flow provides an intuitive drag-and-drop interface for designing complex AI workflows, as illustrated in its product matrix images.
  • Collaborative AI Chat: Magic IM showcases enterprise-grade instant messaging with AI Agent integration, including group chat capabilities and knowledge base management.
  • Intelligent Office: Teamshare OS, with components like Magic Table and Magic Doc, integrates AI into document management and data organization, enhancing team collaboration.

Why Use Magic?

Magic stands out as a comprehensive solution for AI-driven productivity due to several key advantages:

  • All-in-One Platform: It consolidates multiple critical AI and collaboration tools, reducing the need for disparate systems.
  • Open Source Flexibility: Being open source, it offers transparency, extensibility, and the ability to self-host, providing greater control and customization.
  • Powerful AI Agents: Super Magic provides advanced general-purpose AI agent capabilities for complex task automation and intelligent decision-making.
  • Visual Workflow Orchestration: Magic Flow simplifies the creation of sophisticated AI workflows through a user-friendly visual interface, accessible even without coding.
  • Enterprise-Grade Features: From secure instant messaging (Magic IM) to intelligent collaborative office systems (Teamshare OS), Magic is built with enterprise needs in mind, focusing on data security, knowledge management, and team efficiency.
  • Rapid AI Application Deployment: The platform is designed to help businesses quickly build and deploy AI applications, significantly boosting productivity across various operations.

Links

Related repositories

Similar repositories that may be relevant next.

Feynman: The Open Source AI Research Agent

Feynman: The Open Source AI Research Agent

June 2, 2026

Feynman is an open-source AI research agent designed to automate and streamline complex research tasks. Built with TypeScript, it leverages multiple agents and tools to conduct in-depth investigations, literature reviews, and even experiment replications, providing source-grounded outputs.

TypeScriptAI ResearchAI Agent
CodeGraph: Supercharge AI Coding Agents with Semantic Code Intelligence

CodeGraph: Supercharge AI Coding Agents with Semantic Code Intelligence

May 25, 2026

CodeGraph is a powerful, pre-indexed code knowledge graph designed to enhance AI coding agents like Claude Code, Cursor, and Codex. It significantly reduces token usage and tool calls, offering a faster and more cost-effective way for agents to understand codebases. This 100% local solution provides semantic code intelligence, improving agent efficiency and accuracy.

TypeScriptAI AgentCode Analysis
Agentic Inbox: A Self-Hosted Email Client with AI on Cloudflare Workers

Agentic Inbox: A Self-Hosted Email Client with AI on Cloudflare Workers

May 18, 2026

Agentic Inbox is an innovative self-hosted email client that integrates an AI agent, running entirely on Cloudflare Workers. It provides a modern web interface for managing emails, enhanced by AI capabilities for reading, searching, and drafting replies. This project leverages Cloudflare's robust ecosystem, including Email Routing, Durable Objects, R2, and Workers AI, to deliver a powerful and secure email solution.

TypeScriptEmail ClientAI Agent
UI-TARS-desktop: The Open-Source Multimodal AI Agent Stack

UI-TARS-desktop: The Open-Source Multimodal AI Agent Stack

May 6, 2026

UI-TARS-desktop is an open-source multimodal AI Agent stack from ByteDance, designed to connect cutting-edge AI models with agent infrastructure. It provides both Agent TARS, a general multimodal AI agent with CLI and Web UI, and UI-TARS Desktop, a native GUI agent for local and remote computer/browser control. This powerful tool aims to enable human-like task completion through rich multimodal capabilities and seamless integration with real-world tools.

AI AgentMultimodal AIGUI Automation

Source repository

Open the original repository on GitHub.

View on GitHub
OS
OSRepos

Analysis and discovery of open source repositories. Find interesting projects and follow their updates.

Monitor your website with YourWebsiteScore

OSRepos shares public repositories for knowledge and discovery only. Any installation, execution, configuration, or use of third-party repository code is at your own risk. Always review source code, dependencies, licenses, and security implications before running anything.

© 2025 OSRepos. Built with Nuxt 3 and lots of ❤️