OpenManus: Build AI Agents Without Restrictions

Manus is incredible, but OpenManus can achieve any idea without an Invite Code 🛫! Create powerful AI agents with this open-source platform built by the MetaGPT community.

OpenManus Web Interface

Our Team

Our team members @mannaandpoem, @XiangJinyu, @MoshiQAQ, @didiforgithub, @stellaHSR, and @Xinyu Zhang, we are from @MetaGPT etc. The prototype is launched within 3 hours and we are keeping building!

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

Method 1: Using conda

1. Create a new conda environment:

conda create -n open_manus python=3.12
conda activate open_manus

2. Clone the repository:

git clone https://github.com/mannaandpoem/OpenManus.git
cd OpenManus

3. Install dependencies:

pip install -r requirements.txt

Method 2: Using uv (Recommended)

1. Install uv (A fast Python package installer and resolver):

curl -LsSf https://astral.sh/uv/install.sh | sh

2. Clone the repository:

git clone https://github.com/mannaandpoem/OpenManus.git
cd OpenManus

3. Create a new virtual environment and activate it:

uv venv
source .venv/bin/activate  # On Unix/macOS
# Or on Windows:
# .venv\Scripts\activate

4. Install dependencies:

uv pip install -r requirements.txt

Configuration

OpenManus requires configuration for the LLM APIs it uses. Follow these steps to set up your configuration:

1. Create a config.toml file in the config directory:

cp config/config.example.toml config/config.toml

2. 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

Quick Start

One line for run OpenManus:

python main.py --web

Then input your idea via terminal!

Web Interface

You can also use OpenManus through a user-friendly web interface:

uvicorn app.web.app:app --reload

or

python web_run.py

Then open your browser and navigate to http://localhost:8000 to access the web interface. The web UI allows you to:

  • Interact with OpenManus using a chat-like interface
  • Monitor AI thinking process in real-time
  • View and access workspace files
  • See execution progress visually

For unstable version, you also can run:

python run_flow.py

Roadmap

After comprehensively gathering feedback from community members, we have decided to adopt a 3-4 day iteration cycle to gradually implement the highly anticipated features.

Enhance Planning capabilities, optimize task breakdown and execution logic

Introduce standardized evaluation metrics (based on GAIA and TAU-Bench) for continuous performance assessment

Expand model adaptation and optimize low-cost application scenarios

Implement containerized deployment to simplify installation and usage workflows

Enrich example libraries with more practical cases, including analysis of both successful and failed examples

Frontend/backend development to improve user experience

Acknowledgement

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!