Skip to main content
OpenManus-RL is an open-source project jointly led by Ulab-UIUC and MetaGPT. It is an extended version of OpenManus, an open-source replica of Manus. Inspired by the success of RL-tuned reasoning LLMs such as Deepseek-R1 and QwQ-32B, it aims to explore new paradigms for RL-based LLM agent tuning. The project regularly publishes test progress and tuned models on agent benchmarks such as GAIA and AgentBench. To help you get the most out of OpenManus, we have prepared a detailed tutorial — from environment setup to integrating with Myrouter, a step-by-step guide to using OpenManus!

​
1. Prerequisites

​
(1) Obtain an API Key

Register and log in to Myrouter. Enter invitation code [YGHNZ0] during registration to receive a $2 sign-up bonus. Example Image1 Example Image2 Open the [API Key] management page, click the Add button, enter a custom key name, and generate an API key. Example Image3

​
(2) Generate and Save the API Key

Note: The key is stored encrypted on the server and cannot be viewed again after creation. Please save your key securely. If lost, you will need to delete it from the console and create a new one. Example Image4

​
(3) Obtain the Model ID You Want to Use

Find the desired model in the Myrouter Model Hub and copy the model ID and base URL.
  • Gemini-3-pro-preview
  • Gemini-2.5-pro
  • Claude-sonnet-4-5
  • Gpt-5.1
  • Gpt-4o
For other model IDs, maximum context lengths, and pricing, refer to the Model Hub.

​
2. Install OpenManus

For detailed installation instructions, refer to the Installation Guide. The following installation tutorial uses Windows as an example, following “Method 2” from the installation guide.
  1. Install uv (a fast Python package manager):
curl -LsSf https://astral.sh/uv/install.sh | sh
  1. Clone the repository:
git clone https://github.com/FoundationAgents/OpenManus.git
cd OpenManus
  1. Create and activate a virtual environment:
uv venv --python 3.12
source .venv/bin/activate  # Unix/macOS
Windows:
.venv\Scripts\activate
  1. Install dependencies:
uv pip install -r requirements.txt

​
3. Configure OpenManus

OpenManus requires configuring the LLM API to use. Follow these steps:
  1. Create a config.toml file in the config directory (you can copy from the example):
cp config/config.example.toml config/config.toml
  1. Edit config/config.toml, change [model], [base_url], and [api_key], and add your API key and custom settings:
# Global LLM configuration
[llm]
model = "gpt-4o"  # To change the model, copy the model name from the Myrouter website
base_url = "https://api.myrouter.ai/openai"
api_key = "Paste your Myrouter API Key here"  # Change this
max_tokens = 4096
temperature = 0.0
# Optional specific LLM model configuration
[llm.vision]
model = "gpt-4o"  # To change the model, copy the model name from the Myrouter website
base_url = "https://api.myrouter.ai/openai"
api_key = "Paste your Myrouter API Key here"  # Change this

​
4. Quick Start OpenManus

Run OpenManus with a single command: 
python main.py
Then enter your creative prompt after enter your prompt!