OpenManus is an open-source, general AI agent framework by FoundationAgents, implemented in Python to rapidly build chain-of-thought LLM-based agents with intelligent task-processing capabilities. It supports reinforcement learning tuning methods (e.g., GRPO) to enhance performance in complex workflows. Licensed under MIT, the project boasts over 45.7k stars and more than 50 contributors, enabling easy deployment and customization for AI-driven automation.
Source code: https://github.com/FoundationAgents/OpenManus/tree/main
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_manus python=3.12conda activate open_manus- Clone the repository:
git clone https://github.com/mannaandpoem/OpenManus.gitcd OpenManus- 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/mannaandpoem/OpenManus.gitcd OpenManus- Create a new virtual environment and activate it:
uv venv --python 3.12source .venv/bin/activate # On Unix/macOS# Or on Windows:# .venv\Scripts\activate- Install dependencies:
uv pip install -r requirements.txtplaywright installOpenManus 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 key
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
Libre Depot original article,Publisher:Libre Depot，Please indicate the source when reprinting:https://www.libredepot.top/5652.html
