Skip to main content
Glama

MAGI is a high-performance, task-based AI orchestrator designed to bring structure, persistence, and specialized intelligence to autonomous development. It operates as a bridge between your preferred AI models and your local environment, functioning simultaneously as a powerful interactive CLI and a background Model Context Protocol (MCP) server.

🌟 Why MAGI? (Key Benefits)

  • Professional Interactive UI: Inspired by Claude Code, featuring dimmed reasoning for better focus, real-time action spinners, and clean result boxes.

  • Hybrid Power: Use it directly in your terminal for dedicated focus, or annex it to your favorite AI client (Gemini CLI, Claude Desktop) via MCP.

  • Persistent Orchestration: Unlike standard chat interfaces, MAGI manages its own state in a local .magi directory, including progress logs, activity history, and strict Guardrails (Signs) to prevent AI loops.

  • Native SDK Integration: Fast and secure connections to official Google Gemini, Anthropic Claude, and OpenAI SDKs. No middleman proxies.

  • Zero-Touch Automation: Registration and skill installation happen automatically. Just install and start orquestrating.


Related MCP server: Agentic Control Framework (ACF)

πŸ“¦ Installation

Install MAGI Orchestrator globally via npm to get the magi command:

# Official installation
npm install -g magi-orchestrator

Note: The automatic registration script (postinstall) will detect your Gemini CLI and Claude Desktop configurations and inject the MAGI server/skill automatically.


πŸš€ How it Operates (Quick Start)

Run tasks directly from your terminal with rich, stylized feedback.

# Execute a task iteration interactively
magi run "build-auth-layer"

Option 2: The "Annexed" Mode (Skill Injection)

Open your Gemini CLI and use the native skill:

/magi fix-login-bug MAGI will run in the background and report progress directly in your chat session.


βš™οΈ Configuration

MAGI looks for a magi-config.json file in your project directory. If not found, it uses sensible defaults.

{
  "agents": [
    {
      "name": "gemini-flash",
      "type": "gemini",
      "model": "gemini-2.0-flash"
    },
    {
      "name": "claude-sonnet",
      "type": "claude",
      "model": "claude-3-5-sonnet-20241022"
    }
  ],
  "defaultAgent": "gemini-flash",
  "stateDirectory": ".magi"
}

πŸ”‘ Authentication

Set your API keys as environment variables:

  • GEMINI_API_KEY, ANTHROPIC_API_KEY, OPENAI_API_KEY.


πŸ›  Operation Mechanics: The .magi Directory

MAGI keeps your project context clean by orchestrating everything inside the .magi folder:

  • progress.md: Tracking success criteria and current status.

  • guardrails.md: Active "Signs" learned from previous failures to guide the AI.

  • activity.log: Detailed history of every decision and action.


πŸ›  Available CLI Commands

Command

Description

magi run <task>

Start/Continue a task iteration interactively.

magi setup

Manually trigger auto-registration in AI clients.

magi serve

Start the MCP server (STDIO).

magi --version

Report the current version (v1.2.1).


Available Tools

2 tools
get_magi_statusA

Retrieve MAGI runtime status, default agent, available agent adapters, and resolved state directory.

Inputs: no named parameters.

run_magi_iterationA

Execute one MAGI iteration for a task using agentName when provided, otherwise the configured default agent.

Inputs: taskName (required), agentName.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A3.9/5.0

    Scored across 2 tools

    Disambiguation5/5

    get_magi_status and run_magi_iteration have clearly distinct purposes: one retrieves runtime status, the other executes an iteration. No overlap or ambiguity.

    Naming Consistency5/5

    Both tools follow a consistent verb_noun pattern: get_magi_status and run_magi_iteration, using snake_case throughout.

    Tool Count3/5

    With only 2 tools, the server feels thin for an 'Orchestrator' concept. However, the tools cover basic status and execution, so it is borderline appropriate.

    Completeness2/5

    The tool surface lacks many expected operations for an orchestrator, such as agent management, task listing, or configuration. Significant gaps exist.

    Maintenance

    ActivityInactive
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      Not graded
      quality
      B
      maintenance
      Orchestrates and controls multiple AI agent CLIs (Claude-Code, Gemini-cli, etc.) via a unified MCP server, enabling complex multi-agent missions with shared memory and HTTP singleton architecture.
      1,032 npm
      2
      MIT
    • A
      license
      Not graded
      quality
      B
      maintenance
      Multi-agent AI orchestrator that runs parallel coding agents in isolated sessions with self-improving intelligence, exposed via an MCP server for task execution and management.
      MIT