Features

Multi-AI Delegation

Delegate tasks to the right AI for the job. Claude plans, Codex executes, Gemini analyzes.

7 Workflow Modes

| Level | Description | |-------|-------------| | Lite | Instant execution, no planning | | Lite-Plan | Quick planning then execute | | Plan | Standard planning workflow | | TDD-Plan | Test-driven development | | Brainstorm | Multi-role ideation | | Five-Phase | Professional 5-phase collaboration | | Ralph Loop | Iterative AI loop until completion |

Smart Routing

Auto-detect the best AI for your task based on content analysis.

Report Generation

Generate professional reports with auto-generated diagrams.

Real-time Dashboard

Visual workflow management with WebSocket live updates.

Unified Sessions

Single session ID syncs across all AI agents.

Installation

Prerequisites

• Node.js >= 18.0.0
• Python >= 3.9
• Claude Code CLI
• Codex CLI (optional)
• Gemini CLI (optional)

Quick Install (Recommended)

# Clone and run the installer
git clone https://github.com/SexyERIC0723/Multi-AI-Workflow.git
cd Multi-AI-Workflow
./install.sh

# Restart terminal or source your shell config
source ~/.zshrc  # or ~/.bashrc

# Verify installation
maw --version

The installer will:

• Install MAW CLI to ~/.maw/
• Set up global maw command
• Install Claude Code slash commands
• Configure your PATH

Manual Installation

# 1. Clone the repository
git clone https://github.com/SexyERIC0723/Multi-AI-Workflow.git
cd Multi-AI-Workflow

# 2. Install Node.js dependencies
npm install

# 3. Build the project
npm run build

# 4. Install Python bridges
pip install -e bridges/

# 5. Copy to global directory
mkdir -p ~/.maw/bin
cp -r maw ~/.maw/

# 6. Create global command
echo '#!/bin/bash
node ~/.maw/maw/bin/maw.js "$@"' > ~/.maw/bin/maw
chmod +x ~/.maw/bin/maw

# 7. Add to PATH (add to ~/.zshrc or ~/.bashrc)
echo 'export PATH="$HOME/.maw/bin:$PATH"' >> ~/.zshrc

# 8. Install slash commands for Claude Code
mkdir -p ~/.claude/commands
cp claude-commands/*.md ~/.claude/commands/

# 9. Restart terminal and verify
maw --help

Installation Structure

After installation, your ~/.maw directory will look like:

~/.maw/
├── bin/
│   └── maw              # Global command
├── maw/                  # MAW CLI
│   ├── bin/maw.js
│   └── dist/
└── skills/               # Installed skills
    ├── collaborating-with-gemini/
    ├── collaborating-with-codex/
    └── report-generator/

Configure API Keys (Optional)

For Gemini with proxy API:

# Edit the bridge configuration
# File: ~/.maw/skills/collaborating-with-gemini/scripts/gemini_bridge.py
# Set your API key and base URL

Quick Start

# Smart routing - auto-selects best AI
maw run "Analyze this codebase structure"

# Run a simple workflow
maw workflow lite "Fix typos in README"

# Standard planning workflow
maw workflow plan "Implement user authentication"

# 5-phase professional workflow
maw workflow five-phase "Refactor the authentication module"

# Delegate to specific AI
maw delegate codex "Write unit tests" --cd .
maw delegate gemini "Analyze this architecture"

# Open the dashboard
maw view

Workflow Modes

1. Lite Mode - Instant Execution

User Task ────────► Direct Execute ────────► Result

Best for: Simple fixes, small changes, one-time tasks

maw workflow lite "Add comments to this function"
maw workflow lite "Format this file"
maw workflow lite "Change all console.log to logger.debug"

2. Lite-Plan Mode - Quick Planning

User Task ────► Quick Plan (1-2 steps) ────► Execute ────► Result

Best for: Medium complexity tasks, quick development

maw workflow lite-plan "Add error handling to API"
maw workflow lite-plan "Implement simple caching"

3. Plan Mode - Standard Planning (Default)

User Task
    │
    ▼
┌──────────┐
│  Plan    │  ← Analyze requirements, design solution
└────┬─────┘
     │
     ▼
┌──────────┐
│  Review  │  ← Check plan feasibility
└────┬─────┘
     │
     ▼
┌──────────┐
│ Execute  │  ← Implement step by step
└────┬─────┘
     │
     ▼
┌──────────┐
│  Verify  │  ← Confirm results
└────┬─────┘
     │
     ▼
  Result

Best for: Daily development, standard features

maw workflow plan "Implement user login"
maw workflow plan "Add database connection pool"
maw workflow plan "Refactor error handling"

4. TDD-Plan Mode - Test-Driven Development

User Task
    │
    ▼
┌────────────────┐
│ Write Tests    │  ← RED: Define expected behavior
│ (RED)          │
└───────┬────────┘
        │
        ▼
┌────────────────┐
│ Run Tests      │  ← Confirm tests fail
│ (Confirm Fail) │
└───────┬────────┘
        │
        ▼
┌────────────────┐
│ Implement      │  ← GREEN: Write minimal code to pass
│ (GREEN)        │
└───────┬────────┘
        │
        ▼
┌────────────────┐
│ Refactor       │  ← REFACTOR: Optimize with test safety
│ (REFACTOR)     │
└───────┬────────┘
        │
        ▼
  Done (with tests)

Best for: Core business logic, APIs, critical features

maw workflow tdd-plan "Implement order calculation"
maw workflow tdd-plan "Add user permission validation"
maw workflow tdd-plan "Implement payment interface"

5. Brainstorm Mode - Multi-Role Ideation

User Topic
    │
    ▼
┌─────────────────────────────────────────┐
│           Multi-Role Discussion          │
│                                         │
│  ┌──────────┐  ┌──────────┐  ┌────────┐ │
│  │ Architect│  │Developer │  │  QA    │ │
│  └────┬─────┘  └────┬─────┘  └───┬────┘ │
│       │             │            │      │
│       └──────────┬──┴────────────┘      │
│                  │                      │
│                  ▼                      │
│         Discussion & Debate             │
└─────────────────────────────────────────┘
                   │
                   ▼
          ┌──────────────┐
          │  Conclusion  │
          │ Best Solution│
          └──────────────┘

Best for: Architecture decisions, technical choices, complex analysis

maw workflow brainstorm "API design approach"
maw workflow brainstorm "Database selection"
maw workflow brainstorm "Performance optimization strategy"

Roles: | Role | Focus | |------|-------| | Architect | Overall design, scalability, tech debt | | Developer | Implementation difficulty, efficiency, code quality | | QA | Testability, edge cases, potential issues |

6. Five-Phase Mode - Professional Multi-AI Collaboration

User Task
    │
    ▼
┌─────────────────────────────────────────────────────────┐
│ Phase 1: CONTEXT                           [Claude]     │
│ - Analyze project structure                             │
│ - Understand existing code                              │
│ - Gather relevant information                           │
└─────────────────────────────────────────────────────────┘
    │
    ▼
┌─────────────────────────────────────────────────────────┐
│ Phase 2: ANALYSIS                    [Codex + Gemini]   │
│