by haoyu-haoyu
Multi-AI orchestration framework for Claude Code — coordinate Claude, Codex, and Gemini with 7 workflow modes, parallel execution, and session unification
# Add to your Claude Code skills
git clone https://github.com/haoyu-haoyu/Multi-AI-WorkflowGuides for using ai agents skills like Multi-AI-Workflow.
Last scanned: 5/30/2026
{
"issues": [
{
"type": "npm-audit",
"message": "@typescript-eslint/eslint-plugin: Vulnerability found",
"severity": "high"
},
{
"type": "npm-audit",
"message": "@typescript-eslint/parser: Vulnerability found",
"severity": "high"
},
{
"type": "npm-audit",
"message": "@typescript-eslint/type-utils: Vulnerability found",
"severity": "high"
},
{
"type": "npm-audit",
"message": "@typescript-eslint/typescript-estree: Vulnerability found",
"severity": "high"
},
{
"type": "npm-audit",
"message": "@typescript-eslint/utils: Vulnerability found",
"severity": "high"
},
{
"type": "npm-audit",
"message": "ajv: ajv has ReDoS when using `$data` option",
"severity": "medium"
},
{
"type": "npm-audit",
"message": "body-parser: Vulnerability found",
"severity": "medium"
},
{
"type": "npm-audit",
"message": "brace-expansion: brace-expansion: Zero-step sequence causes process hang and memory exhaustion",
"severity": "medium"
},
{
"type": "npm-audit",
"message": "express: Vulnerability found",
"severity": "medium"
},
{
"type": "npm-audit",
"message": "flatted: flatted vulnerable to unbounded recursion DoS in parse() revive phase",
"severity": "high"
},
{
"type": "npm-audit",
"message": "minimatch: minimatch has a ReDoS via repeated wildcards with non-matching literal in pattern",
"severity": "high"
},
{
"type": "npm-audit",
"message": "path-to-regexp: path-to-regexp vulnerable to Regular Expression Denial of Service via multiple route parameters",
"severity": "high"
},
{
"type": "npm-audit",
"message": "picomatch: Picomatch: Method Injection in POSIX Character Classes causes incorrect Glob Matching",
"severity": "high"
},
{
"type": "npm-audit",
"message": "qs: qs's arrayLimit bypass in comma parsing allows denial of service",
"severity": "medium"
},
{
"type": "npm-audit",
"message": "uuid: uuid: Missing buffer bounds check in v3/v5/v6 when buf is provided",
"severity": "medium"
},
{
"type": "npm-audit",
"message": "ws: ws: Uninitialized memory disclosure",
"severity": "medium"
}
],
"status": "WARNING",
"scannedAt": "2026-05-30T16:37:14.199Z",
"npmAuditRan": true,
"pipAuditRan": true
}Multi-AI-Workflow is an open-source ai agents skill for AI coding assistants such as Claude Code, Codex CLI, and ChatGPT, built by haoyu-haoyu. Multi-AI orchestration framework for Claude Code — coordinate Claude, Codex, and Gemini with 7 workflow modes, parallel execution, and session unification. It has 109 GitHub stars.
Multi-AI-Workflow returned warnings in SkillsLLM's automated security scan. It has no critical vulnerabilities, but review the flagged issues in the Security Report section before adding it to your workflow.
Clone the repository with "git clone https://github.com/haoyu-haoyu/Multi-AI-Workflow" and add it to your Claude Code skills directory (see the Installation section above).
Multi-AI-Workflow is primarily written in TypeScript. It is open-source under haoyu-haoyu on GitHub, so you can review or fork the full source.
Yes. SkillsLLM lists many other AI Agents skills you can browse and compare side by side. Open the AI Agents category from the badge at the top of this page, or use the Related Skills and comparison links further down to weigh Multi-AI-Workflow against similar tools.
No comments yet. Be the first to share your thoughts!
Requires a passing catalog security scan. Resolve the flagged issues and resubmit to enable featuring.
__ __ _ __ __
| \/ | /_\ \ \ / /
| |\/| |/ _ \ \ \ /\ / /
| | | / ___ \ \ V V /
|_| |_/_/ \_\_\_/\_/
Multi-AI Workflow Framework
Claude + Codex + Gemini = Unstoppable
Features | Installation | Quick Start | Workflow Modes | Usage in Claude Code
MAW (Multi-AI Workflow) is a revolutionary CLI framework that orchestrates multiple AI agents to work together seamlessly. Imagine having Claude's reasoning, Codex's code execution, and Gemini's multimodal capabilities all working in harmony on your projects.
┌──────────────────────────────────────────────────────────────┐
│ │
│ [CLAUDE] [CODEX] [GEMINI] │
│ Planning & Code Execution Multimodal │
│ Reasoning & Analysis Analysis │
│ │
│ \ | / │
│ \ | / │
│ \ | / │
│ v v v │
│ +-------------------------------+ │
│ | MAW ORCHESTRATOR | │
│ | Unified Session Control | │
│ +-------------------------------+ │
│ | │
│ v │
│ +-----------------+ │
│ | YOUR CODE | │
│ +-----------------+ │
│ │
└──────────────────────────────────────────────────────────────┘
Delegate tasks to the right AI for the job. Claude plans, Codex executes, Gemini analyzes.
| 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 |
Auto-detect the best AI for your task based on content analysis.
Generate professional reports with auto-generated diagrams.
Visual workflow management with WebSocket live updates.
Single session ID syncs across all AI agents.
# Clone and run the installer
git clone https://github.com/haoyu-haoyu/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:
~/.maw/maw command# 1. Clone the repository
git clone https://github.com/haoyu-haoyu/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
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/
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
# 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
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"
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"
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"
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"
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 |
User Task
│
▼
┌─────────────────────────────────────────────────────────┐
│ Phase 1: CONTEXT [Claude] │
│ - Analyze project structure │
│ - Understand existing code │
│ - Gather relevant information │
└─────────────────────────────────────────────────────────┘
│
▼
┌─────────────────────────────────────────────────────────┐
│ Phase 2: ANALYSIS [Codex + Gemini] │
│