AgentHub is a comprehensive framework for implementing and managing various AI agents. It provides a unified interface for different types of intelligent agents, making it easier to develop, test, and deploy AI-powered solutions.
- Multiple agent implementations
- Extensible architecture
- Standardized agent interfaces
- Built-in agent evaluation framework
- Easy-to-use API
- Python >= 3.12
- Conda (recommended for environment management)
- Create a new conda environment:
conda create -n agenthub python=3.12
conda activate agenthub- Clone the repository:
git clone https://github.com/yourusername/AgentHub.git
cd AgentHub- Install dependencies:
pip install -r requirements.txt- Configure your API keys in
config/config.toml
Run the application:
python main.pyThen simply enter your prompts. Type 'exit' to quit.
Enter your prompt: write a simple calculator
...
Enter your prompt: exit
Goodbye!Contributions are welcome! Please feel free to submit a Pull Request.
This project is licensed under the MIT License - see the LICENSE file for details.