English | 简体中文
Alaye App is a desktop management assistant for AI tools, designed to provide developers with a unified and convenient experience for configuring and managing AI tools.
Alaye App integrates a modern user interface with powerful backend services, helping developers manage multiple AI tools in one application.
Phase 1 Features (Current Version):
- Claude AI Project Management: Easily scan, configure, and manage multiple Claude AI projects
- Plugin & Extension Support: Support for Claude plugin marketplace, MCP server configuration, and Hooks management
- Cross-Platform: Support for Windows, macOS, and Linux operating systems
Future Plans: Continuously expanding support for more AI tools and advanced capabilities
- Frontend: Next.js 16 + React 19 + TypeScript + Tailwind CSS
- Backend: Python 3.12 + PyWebView
- Cross-Platform Terminal: pexpect (Unix) / pywinpty (Windows)
- Python: 3.12 or higher
- Node.js: Recommended 18 or higher
- Operating System: Windows 10/11, macOS 11.1+, or major Linux distributions
git clone <repository-url>
cd alaye-appRecommended to use uv for fast installation (automatically installs all Python dependencies, including PyQt6 on Linux):
# Install uv (if not already installed)
pip install uv
# Install Python dependencies
uv sync
# Install frontend dependencies
cd frontend && npm install && cd ..cp .env.example .envMain configuration items in .env file:
ALAYE_APP_ENV: Runtime mode (development/export/browser)PORT: Development server port (default 3000)
Development Mode (with frontend hot reload):
# Terminal 1: Start frontend
cd frontend && npm run dev
# Terminal 2: Start backend (make sure ALAYE_APP_ENV=development in .env)
python main.pyProduction Mode (desktop application):
# 1. Build frontend
cd frontend && npm run build && cd ..
# 2. Start application
uv run python main.pyBrowser Mode (for web testing):
# Set ALAYE_APP_ENV=browser in .env, then start
uv run python main.py
# Visit http://127.0.0.1:8000Package the application as a standalone executable without requiring Python environment:
# 1. Build frontend
cd frontend && npm run build && cd ..
# 2. Execute build (choose the script for your platform)
./scripts/build.sh # Linux/macOS
scripts\build.bat # Windows (CMD)
scripts\build.ps1 # Windows (PowerShell)After building, the executable file is located in the dist/ directory.
- Claude project scanning and management
- Claude settings configuration
- MCP server management
- Hooks configuration management
- Plugin marketplace support
- Multi-project support
- Cross-platform desktop application
- Tool Extensions: CodeX, Gemini
- Feature Extensions: Analytics dashboard, advanced AI capabilities
This project is open-sourced under the MIT License. For details, please see the LICENSE file in the project root directory.
Issues and Pull Requests are welcome!
For questions or suggestions, please contact us through GitHub Issues.
We would like to express our sincere gratitude to the following tools and services that helped make this project possible:
- Claude Code - For providing powerful AI-assisted coding capabilities that significantly accelerated our development process
- Doubao - For generating the beautiful application icon used throughout the project
