English | 中文
Manus is incredible, but OpenManus 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 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.
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_manus python=3.12
conda activate open_manus
- Clone the repository:
git clone https://github.com/mannaandpoem/OpenManus.git
cd 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.git
cd OpenManus
- Create a new virtual environment and activate it:
uv venv
source .venv/bin/activate # On Unix/macOS
# Or on Windows:
# .venv\Scripts\activate
- Install dependencies:
uv pip install -r requirements.txt
OpenManus requires configuration for the LLM APIs it uses. Follow these steps to set up your configuration:
- Create a
config.toml
file in theconfig
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:
# 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
# HoneyHive configuration (optional, for evaluation)
[honeyhive]
api_key = "your_honeyhive_api_key" # Replace with your HoneyHive API key
project = "openmanus-trace"
source = "development"
session_name = "OpenManus Session"
OpenManus includes an integrated evaluation system powered by HoneyHive that automatically evaluates each agent run. To enable this feature:
-
Make sure you have the HoneyHive SDK installed:
pip install honeyhive
-
Configure HoneyHive in your
config.toml
file as shown above. -
Alternatively, you can set your HoneyHive API key as an environment variable:
export HH_API_KEY=your_honeyhive_api_key
You can get your API key from the HoneyHive dashboard after creating an account at honeyhive.ai.
For more details on the evaluation system, see EVALUATION.md and HONEYHIVE_EXPERIMENTS.md.
One line for run OpenManus:
python main.py
Then input your idea via terminal!
For unstable version, you also can run:
python run_flow.py
We welcome any friendly suggestions and helpful contributions! Just create issues or submit pull requests.
Or contact @mannaandpoem via 📧email: [email protected]
Join our networking group on Feishu and share your experience with other developers!
Thanks to anthropic-computer-use and browser-use for providing basic support for this project!
OpenManus is built by contributors from MetaGPT. Huge thanks to this agent community!
@misc{openmanus2025,
author = {Xinbin Liang and Jinyu Xiang and Zhaoyang Yu and Jiayi Zhang and Sirui Hong},
title = {OpenManus: An open-source framework for building general AI agents},
year = {2025},
publisher = {GitHub},
journal = {GitHub repository},
howpublished = {\url{https://github.com/mannaandpoem/OpenManus}},
}