It's a simple implementation, so we welcome any suggestions, contributions, and feedback!
Enjoy your own agent with OpenManus!
We're also excited to introduce OpenManus-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 OpenManus.
Project Demo
Installation
We provide two installation methods. Method 2 (using uv) is recommended for faster installation and better dependency management.
1uv venv --python 3.122source .venv/bin/activate # On Unix/macOS3# Or on Windows:4# .venv\Scripts\activate
Install dependencies:
uv pip install -r requirements.txt
Browser Automation Tool (Optional)
playwright install
Configuration
OpenManus requires configuration for the LLM APIs it uses. Follow these steps to set up your configuration:
Create a config.toml file in the config directory (you can copy from the example):
cp config/config.example.toml config/config.toml
Edit config/config.toml to add your API keys and customize settings:
toml
1# Global LLM configuration2[llm]3model="gpt-4o"4base_url="https://api.openai.com/v1"5api_key="sk-..."# Replace with your actual API key6max_tokens=40967temperature=0.089# Optional configuration for specific LLM models10[llm.vision]11model="gpt-4o"12base_url="https://api.openai.com/v1"13api_key="sk-..."# Replace with your actual API key
Quick Start
One line for run OpenManus:
python main.py
Then input your idea via terminal!
For MCP tool version, you can run:
python run_mcp.py
For unstable multi-agent version, you also can run:
python run_flow.py
Custom Adding Multiple Agents
Currently, besides the general OpenManus 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.
toml
1# Optional configuration for run-flow2[runflow]3use_data_analysis_agent=true# Disabled by default, change to true to activate
In addition, you need to install the relevant dependencies to ensure the agent runs properly: Detailed Installation Guide
How to contribute
We welcome any friendly suggestions and helpful contributions! Just create issues or submit pull requests.
We also thank stepfun(阶跃星辰) for supporting our Hugging Face demo space.
OpenManus is built by contributors from MetaGPT. Huge thanks to this agent community!
Cite
bibtex
1@misc{openmanus2025,
2 author = {Xinbin Liang and Jinyu Xiang and Zhaoyang Yu and Jiayi Zhang and Sirui Hong and Sheng Fan and Xiao Tang},
3 title = {OpenManus: An open-source framework for building general AI agents},
4 year = {2025},
5 publisher = {Zenodo},
6 doi = {10.5281/zenodo.15186407},
7 url = {https://doi.org/10.5281/zenodo.15186407},
8}
