Musai is incredible, but Musai can achieve any idea without an Invite Code 🛫!
Our team members @Xinbin Liang and @Jinyu Xiang (core authors), along with @Zhaoyang Yu, @Jiayi Zhang, and @Sirui Hong, we are from @MetaGPT. The prototype is launched within 3 hours and we are keeping building!
It's a simple implementation, so we welcome any suggestions, contributions, and feedback!
Enjoy your own agent with Musai!
We're also excited to introduce Musai-RL, an open-source project dedicated to reinforcement learning (RL)- based (such as GRPO) tuning methods for LLM agents, developed collaboratively by researchers from UIUC and Musai.
seo_website.mp4
We provide two installation methods. Method 2 (using uv) is recommended for faster installation and better dependency management.
- Create a new conda environment:
conda create -n open_musai python=3.12
conda activate open_musai- Clone the repository:
git clone https://github.com/FoundationAgents/Musai.git
cd Musai- Install dependencies:
pip install -r requirements.txt- Install uv (A fast Python package installer and resolver):
curl -LsSf https://astral.sh/uv/install.sh | sh- Clone the repository:
git clone https://github.com/FoundationAgents/Musai.git
cd Musai- Create a new virtual environment and activate it:
uv venv --python 3.12
source .venv/bin/activate # On Unix/macOS
# Or on Windows:
# .venv\Scripts\activate- Install dependencies:
uv pip install -r requirements.txtplaywright installMusai requires configuration for the LLM APIs it uses. Follow these steps to set up your configuration:
- Create a
config.tomlfile in theconfigdirectory (you can copy from the example):
cp config/config.example.toml config/config.toml- Edit
config/config.tomlto add your API keys and customize settings:
# Global LLM configuration
[llm]
model = "gpt-4o"
base_url = "https://api.openai.com/v1"
api_key = "sk-..." # Replace with your actual API key
max_tokens = 4096
temperature = 0.0
# Optional configuration for specific LLM models
[llm.vision]
model = "gpt-4o"
base_url = "https://api.openai.com/v1"
api_key = "sk-..." # Replace with your actual API keyOne line for run Musai:
python main.pyThen input your idea via terminal!
For MCP tool version, you can run:
python run_mcp.pyFor unstable multi-agent version, you also can run:
python run_flow.pyCurrently, besides the general Musai Agent, we have also integrated the DataAnalysis Agent, which is suitable for data analysis and data visualization tasks. You can add this agent to run_flow in config.toml.
# Optional configuration for run-flow
[runflow]
use_data_analysis_agent = true # Disabled by default, change to true to activateIn addition, you need to install the relevant dependencies to ensure the agent runs properly: Detailed Installation Guide
We welcome any friendly suggestions and helpful contributions! Just create issues or submit pull requests.
Or contact @mannaandpoem via 📧email: mannaandpoem@gmail.com
Note: Before submitting a pull request, please use the pre-commit tool to check your changes. Run pre-commit run --all-files to execute the checks.
Join our networking group on Feishu and share your experience with other developers!
Thanks to PPIO for computing source support.
PPIO: The most affordable and easily-integrated MaaS and GPU cloud solution.
Thanks to anthropic-computer-use and browser-use for providing basic support for this project!
Additionally, we are grateful to AAAJ, MetaGPT, OpenHands and SWE-agent.
We also thank stepfun(阶跃星辰) for supporting our Hugging Face demo space.
Musai is built by contributors from MetaGPT. Huge thanks to this agent community!
@misc{musai2025,
author = {Xinbin Liang and Jinyu Xiang and Zhaoyang Yu and Jiayi Zhang and Sirui Hong and Sheng Fan and Xiao Tang},
title = {Musai: An open-source framework for building general AI agents},
year = {2025},
publisher = {Zenodo},
doi = {10.5281/zenodo.15186407},
url = {https://doi.org/10.5281/zenodo.15186407},
}