SyberAgent 2.0 is a versatile, multi-agent AI system designed to coordinate specialized agents for document processing, image analysis, audio transcription, search, data analysis, and natural language interaction. It leverages LangGraph for orchestration and FastAPI with WebSocket support to enable real-time communication between clients and agents. After starting the server, you can interact with it through a chat-style interface to request complex tasks like analyzing a PDF, extracting tables, performing OCR on images, or transcribing audio. The system distributes tasks across dedicated agents (e.g., FileProcessingAgent, ImageProcessingAgent, AudioProcessingAgent, WebSearchAgent, DataAnalysisAgent, ConversationalAgent) to optimize performance and maintain modularity.

Prerequisites:

• Python 3.8+
• pip
• Internet access to install dependencies

1. Clone the repository

git clone https://github.com/cyberzhang1/SyberAgent.git
cd SyberAgent

2. Create and activate a virtual environment

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

3. Install dependencies

pip install -r requirements.txt

4. Configure environment variables

# Copy example env file if available, or create your own
cp .env.example .env

Edit .env to set API keys and config:

API_KEY=your_api_key_here

TAVILY_API_KEY=your_tavily_key_here

BASE_URL=https://api.deepseek.com/v1

MODEL=deepseek-chat

5. Run the server
```bash
python main.py

6. Optional: run with development settings or tests as needed

Tips and notes:

• Ensure API keys are kept secret and not committed to version control.
• The system supports multiple AI models; configure BASE_URL and MODEL to target your preferred backend.
• For large documents or media, consider increasing MAX_FILE_SIZE and adjusting OCR/processing engine options in core/config.py.
• If you encounter performance issues, enable asynchronous handling and verify that the runtime has sufficient CPU/GPU resources.
• Use the provided examples in the README as templates for interacting with different agents (document processing, image analysis, audio transcription).