AI Agent System

A comprehensive AI agent framework with CLI and web interfaces, built using Python and integrating with the Symphony framework.

Features

• CLI Interface: Command-line interface for interacting with the agent system
• Orchestration Engine: Schedule and manage agent tasks and workflows
• NLP Capabilities: Natural language processing for intent recognition
• Security Framework: Role-based access control and audit logging
• Storage Adapters: Modular storage backends including SQLite
• Testing Infrastructure: Comprehensive test suite for all components
• Symphony Integration: Works with the Symphony agent coordination framework

Installation

Prerequisites

• Python 3.9+
• pip
• virtualenv (recommended)

Steps

1. Clone the repository:

   git clone https://github.com/your-repo/ai-agent.git
   cd ai-agent
   

2. Create and activate a virtual environment:

   python -m venv venv
   source venv/bin/activate  # Linux/MacOS
   venv\Scripts\activate     # Windows
   

3. Install dependencies:

   pip install -e .
   

CLI Usage

The system provides a command-line interface with these main commands:

# Start the agent system
python -m cli_interface start

# Run specific agent tasks
python -m cli_interface run-task [task_name]

# View system status
python -m cli_interface status

# Get help
python -m cli_interface --help

Web Interface

The web interface provides a dashboard for monitoring and controlling agents:

1. Start the web server:

   python -m web_interface
   

2. Access the interface at: http://localhost:8000

Features include:

• Agent status monitoring
• Task scheduling
• Performance metrics
• Security audit logs

Configuration

Configuration is managed through environment variables and config files:

1. Copy the example config:

   cp config.example.yaml config.yaml
   

2. Edit config.yaml with your settings:

   database:
     adapter: sqlite
     path: ./agent.db
   
   security:
     rbac_enabled: true
     audit_log: ./audit.log
   

Testing

Run the test suite with:

pytest tests/

Key test categories:

• Unit tests
• Integration tests
• Performance benchmarks
• Security validation

Contributing

1. Fork the repository
2. Create a feature branch
3. Submit a pull request

Please follow the coding standards and include tests with new features.

License

MIT License - See LICENSE file for details.