Welcome to SAM-GPT an AI-powered multi-agent system! This project aims to help users streamline processes and automate repetitive tasks using a combination of NLP and multi-agent systems. We've designed a modular and scalable architecture that allows for easy extensibility and adaptability. Feel free to explore the code, contribute, or leave some feedback!
(This is a project in progress. It is not production-ready.)
- Natural Language Processing (NLP)
- Autonomous task generation and delegation
- Command Line Interface (CLI) for user interaction
- Plan generation using state-of-the-art AI models
- Modular and scalable multi-agent design
- Vector embeddings for agent communication, collaboration and memory
- Continuous and approval modes for safer user control
- Clone the repository:
git clone https://github.com/PriNova/SAM-GPT.git
cd SAM-GPT- Create a virtual environment and install the dependencies:
python3 -m venv venv
source venv/bin/activate
pip3 install -r requirements.txt-
Set up your API keys and other configuration settings in a .env file or as environment variables.
-
Before running the application, you need to rename the
.env.templatefile to.envand fill in your OpenAI API key. You can find your API key here. -
Run the application:
python3 samgpt.pyThe application supports a command-line interface for interacting with the multi-agent system. Run the app and follow the prompts to input your goals and manage tasks.
The general project structure, use-cases, and roadmap can be found here. You can find detailed documentation for the functions, classes, and modules in the source code.
We love contributions! If you're interested in helping out, here's what you can do:
- Fork the repository and create your branch (
git checkout -b feature/YourFeature). - Commit your changes (`git commit -m 'Add some feature').
- Push to the branch (
git push origin feature/YourFeature). - Open a Pull Request.
Please follow the Code of Conduct when contributing to this project.
Feel free to open an issue or submit a pull request for bug fixes, new features, or other improvements. We appreciate your support!
This project is MIT licensed.
If you have any questions, feel free to reach out to us!
Discussion: Discussions
Issues: Issue