Myai Memory

🚀 MyAI Project Documentation

MyAI is a locally run AI agent system designed to offer users efficient, secure, and private AI services. Here are the detailed contents of the project:

🚀 Quick Start

Project Overview

MyAI is a locally run AI agent system, aiming to provide users with efficient, secure, and private AI services.

✨ Features

Project Architecture

Core Components

1. MCP (MyAI Control Protocol) Server
   • Responsible for coordinating and managing the synchronization of all platforms.
   • Provides support for HTTP and SSE transportation.
2. Command Line Interface (CLI)
   • Offers various commands for operating MyAI, such as --help, --remember, etc.
3. Natural Language Processing Module
   • Supports controlling the AI agent through natural language instructions.
   • It's the most reliable way to synchronize all platforms directly from the main file.
4. Cache System
   • Provides significant performance improvements, such as:
     • Memory query time optimized from ~2000ms to ~1ms (2000x improvement).
     • Platform synchronization time optimized from ~850ms to ~350ms (2.4x improvement).

Development Process

# Run in development mode
npm run dev

# Development mode with an HTTP server
npm run dev:http

# Monitor TypeScript compilation
npm run build:watch

# Run tests
npm test

# Specify test cases
npm test -- -t "platformSync"

# Format code
npm run lint

# Type checking
npm run typecheck

Security and Privacy

• All data is stored on the local device.
• Automatically adds the CLAUDE.md file to .gitignore to avoid accidental commits to the version control system.
• Supports an encrypted file system to ensure maximum security.

Troubleshooting

1. CLAUDE.md Update Failure

• Check file permissions: Use the command ls -la CLAUDE.md
• Perform an emergency sync: Run the script ./emergency-sync.sh

2. MCP Connection Failure

• Ensure the MCP server is running. Check the process: ps aux | grep myai-memory
• Check the MCP error information in the Claude Desktop logs.

3. Cache Issues

• Use the command node dist/cli.js --clear-cache to clear the cache.
• Verify that the Anthropic API key is configured correctly.

Manual Synchronization Methods

# Direct synchronization (most reliable)
cd /path/to/myAImemory
node sync-memory.js

# Emergency synchronization (used in case of permission issues)
cd /path/to/myAImemory
./safe-memory.sh sync

Logging and Debugging

• Enable debug mode: DEBUG=true npm run start
• Log file paths:
  • Linux/macOS: ~/.local/share/myai-memory/logs/
  • Windows: %APPDATA%\myai-memory\logs\

📚 Documentation

Contribution Guidelines

Contributions are welcome! Please follow these steps to submit a Pull Request:

1. Fork the repository.
2. Create a feature branch: git checkout -b feature/amazing-feature
3. Commit changes: git commit -m 'Add some amazing feature'
4. Push to the branch: git push origin feature/amazing-feature
5. Create a Pull Request.

Detailed Documentation

Refer to the project's Wiki for detailed documentation.

API Documentation

The API documentation is located in the /docs directory:

# Generate API documentation
npm run docs

📄 License

This project is open - sourced under the MIT License. See the LICENSE file for specific information.

Built with ❤️ for the AI community