New Research: Supply Chain Attack on Axios Pulls Malicious Dependency from npm.Details →
Socket
Book a DemoSign in
Socket

gemini-code-flow

Package Overview
Dependencies
Maintainers
1
Versions
1
Alerts
File Explorer

Advanced tools

Socket logo

Install Socket

Detect and block malicious and high-risk dependencies

Install

gemini-code-flow

AI-powered development orchestration for Gemini CLI - adapted from Claude Code Flow by ruvnet

latest
Source
npmnpm
Version
0.1.0
Version published
Maintainers
1
Created
Source

Gemini Code Flow 🚀

AI-powered development orchestration for Gemini CLI - adapted from Claude Code Flow by ruvnet

🌟 Overview

Gemini Code Flow brings the powerful SPARC methodology and multi-agent orchestration capabilities to Google's Gemini CLI platform. This tool enables developers to leverage multiple AI agents working in parallel to write, test, and optimize code systematically.

🙏 Attribution

This project is adapted from the excellent Claude Code Flow by ruvnet. Full credit goes to the original author for the innovative SPARC methodology and multi-agent orchestration concepts.

✨ Features

  • Multi-Agent Orchestration: Run up to 10 Gemini agents in parallel
  • 17 SPARC Development Modes: Specialized agents for every development need
  • Persistent Memory: Share knowledge across agents and sessions
  • Multimodal Support: Leverage Gemini's ability to process images, PDFs, and sketches
  • Large Context Window: Utilize Gemini's 1M token context for complex codebases
  • Google Search Integration: Ground responses with real-time information

🛠️ SPARC Development Modes

  • 🏗️ Architect - System design and architecture
  • 🧠 Auto-Coder - Clean, modular implementation
  • 🧪 Tester (TDD) - Test-driven development
  • 🪲 Debugger - Troubleshooting and bug fixes
  • 🛡️ Security Reviewer - Security audits
  • 📚 Documentation Writer - Comprehensive documentation
  • 🔗 System Integrator - Component integration
  • 📈 Deployment Monitor - Post-launch monitoring
  • 🧹 Optimizer - Performance optimization
  • Ask - Task formulation guide
  • 🚀 DevOps - Deployment and infrastructure
  • 📘 SPARC Tutorial - Interactive learning
  • 🔐 Database Admin - Database management
  • 📋 Specification Writer - Requirements and pseudocode
  • ♾️ MCP Integration - External service connections
  • ⚡️ SPARC Orchestrator - Complex workflows
  • 🎨 Designer - UI/UX with multimodal capabilities

📦 Installation

Prerequisites

  • Node.js 18+
  • Gemini CLI installed globally
# Install Gemini CLI first
npm install -g @google/gemini-cli

# Install Gemini Code Flow
npm install -g gemini-code-flow

🔐 Authentication Options

Gemini Code Flow supports multiple authentication methods:

Free usage with generous limits:

  • 60 requests per minute
  • 1,000 requests per day
  • Access to Gemini 2.5 Pro with 1M token context
# Simply login with your Google account when prompted
gemini-flow init --sparc
# No API key configuration needed!

Option 2: API Key (For Professional/Enterprise Use)

For multiple simultaneous agents or usage-based billing:

# Set your API key from Google AI Studio or Vertex AI
export GEMINI_API_KEY="your-api-key-here"

Current Limitations (Preview)

  • Personal Google accounts: 60 requests/minute, 1,000/day
  • Some advanced features may require API key authentication
  • For the latest usage limits and capabilities, see Google's official announcement

🚀 Quick Start

# Initialize a new project with SPARC
gemini-flow init --sparc

# Start the orchestrator
gemini-flow start

# Run a specific SPARC mode
gemini-flow sparc architect "Design a microservices architecture"

# Launch multi-agent workflow
gemini-flow sparc "Build a REST API with authentication"

💡 Usage Examples

Simple Task

gemini-flow agent "Refactor this function to use async/await"

Complex Multi-Agent Workflow

gemini-flow sparc orchestrator "Create a full-stack application with React frontend and Node.js backend, including tests and documentation"

Multimodal Development

gemini-flow sparc designer "Convert this wireframe sketch to React components" --file ./wireframe.png

🔧 Configuration

Create a .gemini-flow.json in your project root:

{
  "maxAgents": 10,
  "memoryPath": "./gemini-memory.json",
  "authMethod": "google-account",
  "modes": {
    "architect": {
      "temperature": 0.7,
      "maxTokens": 8000
    }
  }
}

Configuration Options:

  • authMethod: "google-account" (default) or "api-key"
  • apiKey: Only needed if using "api-key" method
  • maxAgents: Number of parallel agents (consider rate limits)
  • memoryPath: Location for persistent memory storage

🤝 Contributing

We welcome contributions! Please see our Contributing Guide for details.

📄 License

MIT License - see LICENSE file for details.

🙌 Acknowledgments

  • Original Claude Code Flow by ruvnet
  • Google Gemini team for the excellent CLI tool
  • All contributors and users of this project

📚 Documentation

For detailed documentation, visit our Wiki.

🐛 Issues

Found a bug or have a suggestion? Please open an issue.

Built with ❤️ by the community, adapted from Claude Code Flow

Keywords

gemini

FAQs

Package last updated on 26 Jun 2025

Did you know?

Socket

Socket for GitHub automatically highlights issues in each pull request and monitors the health of all your open source dependencies. Discover the contents of your packages and block harmful activity before you install or update your dependencies.

Install

Related posts