OpenManus is an open-source alternative to the groundbreaking Manus AI agent, developed by the MetaGPT community. Manus itself is a revolutionary AI Agent designed for everything from task planning to execution and capable of handling complex workflows without human intervention. While Manus is currently in invite-only mode, which restricts its capabilities to be utilized by broader community, OpenManus democratizes these capabilities by providing a free, open-source, and customizable version of Manus for developers and researchers. Built in just three hours, OpenManus is catching eyes of many enthusiasts who were eager to play with Manus, but couldn’t do so because of the invite restrictions.
In this article, we will explore how to install OpenManus locally. Though it is supposed to be used with OpenAI or other API keys, we have found a way for you to use it for free using Ollama models!
Prerequisites
The minimum system requirements for this use case are:
- GPUs: RTX 4090 or RTX A6000
- Disk Space: 200 GB
- RAM: At least 16 GB.
- Nvidia CUDA installed.
- Anaconda set up
Note: The prerequisites for this are highly variable across use cases. A high-end configuration could be used for a large-scale deployment.
Step-by-step process to install and run OpenManus locally or on Cloud
For the purpose of this tutorial, we’ll use a GPU-powered Virtual Machine by NodeShift since it provides high compute Virtual Machines at a very affordable cost on a scale that meets GDPR, SOC2, and ISO27001 requirements. Also, it offers an intuitive and user-friendly interface, making it easier for beginners to get started with Cloud deployments. However, feel free to use any cloud provider of your choice and follow the same steps for the rest of the tutorial.
Step 1: Setting up a NodeShift Account
Visit app.nodeshift.com and create an account by filling in basic details, or continue signing up with your Google/GitHub account.
If you already have an account, login straight to your dashboard.
Step 2: Create a GPU Node
After accessing your account, you should see a dashboard (see image), now:
- Navigate to the menu on the left side.
- Click on the GPU Nodes option.
- Click on Start to start creating your very first GPU node.
These GPU nodes are GPU-powered virtual machines by NodeShift. These nodes are highly customizable and let you control different environmental configurations for GPUs ranging from H100s to A100s, CPUs, RAM, and storage, according to your needs.
Step 3: Selecting configuration for GPU (model, region, storage)
- For this tutorial, we’ll be using the RTX 4090 GPU; however, you can choose any GPU of your choice based on your needs.
- Similarly, we’ll opt for 200GB storage by sliding the bar. You can also select the region where you want your GPU to reside from the available ones.
Step 4: Choose GPU Configuration and Authentication method
- After selecting your required configuration options, you’ll see the available VMs in your region and according to (or very close to) your configuration. In our case, we’ll choose a 1x RTX 4090 GPU node with 12 vCPUs/96GB RAM/200 GB SSD.
2. Next, you’ll need to select an authentication method. Two methods are available: Password and SSH Key. We recommend using SSH keys, as they are a more secure option. To create one, head over to our official documentation.
Step 5: Choose an Image
The final step would be to choose an image for the VM, which in our case is Nvidia Cuda, where we’ll deploy and run the inference of our model.
That’s it! You are now ready to deploy the node. Finalize the configuration summary, and if it looks good, click Create to deploy the node.
Step 6: Connect to active Compute Node using SSH
- As soon as you create the node, it will be deployed in a few seconds or a minute. Once deployed, you will see a status Running in green, meaning that our Compute node is ready to use!
- Once your GPU shows this status, navigate to the three dots on the right and click on Connect with SSH. This will open a pop-up box with the Host details. Copy and paste that in your local terminal to connect to the remote server via SSH.
Step 7: Set up the project environment with dependencies
- Create a virtual environment using Anaconda.
conda create -n open_manus python=3.12 && conda activate open_manus
Output:
2. Once you’re inside the environment,
- Clone the official OpenManus repository model.
- Move inside the project directory.
git clone https://github.com/mannaandpoem/OpenManus.git && cd OpenManus
Output:
3. Install project dependencies as mentioned in requirements.txt.
pip install -r requirements.txt
Output:
Step 8: Install Ollama
Next, we’ll set up Ollama, from where we can install our models and use them to run OpenManus agent.
- Install Ollama dependencies.
sudo apt install pciutils lshw
Output:
2. Install ollama.
curl -fsSL https://ollama.com/install.sh | sh
Output:
3. Start Ollama server.
ollama serve
Output:
Step 9: Install LLMs for OpenManus
Now, once Ollama server is up and running, we’ll proceed to install two models, one will be for language and other for vision to support our OpenManus agent.
- Open a new local terminal and connect it with SSH if you’re using cloud GPU (e.g. NodeShift).
- Install
qwq model for language processing.
ollama run qwq
Output:
3. Install minicpm-v for vision processing.
ollama run minicpm-v
Output:
Step 10: Configure Project Settings
Since, we have our models installed locally. We’ll set our environment variable to use the local models instead of an API key.
1. For this, if you’re using a remote server (e.g. NodeShift GPU), you’ll first need to connect your local VS Code editor to your remote server via SSH with the following steps:
a) Install the “Remote-SSH” Extension by Microsoft on VS Code.
b) Type “Remote-SSH: Connect to Host” on the Command Palette.
c) Enter the host details, such as username and SSH password, and you should be connected.
2. Edit the llm and llm.vision configuration to use Ollama as shown below.
3. Also, if your remote server or machine doesn’t support GUI and runs purely in CLI, then you’ll also need to change the headless settings of the project in order to let the agent work without any errors.
Skip this step if your machine has a GUI support.
To allow headless mode:
- Go to
/app/tool/browser_use_tool.py file inside the project.
- Ensure
headless is set to "True" as shown below.
Warning: Doing the above step ensures the Agent runs successfully and logs the results in the console, but you’ll not be able to see the results visually in browser as the agent doesn’t access the browser in headless mode.
Step 11: Run the Agent
Finally, we can run and see the steps the model performs in our console.
- Open the terminal in VS code and run the following command
python main.py
It will ask you for the prompt. We are giving the prompt as mentioned below:
I need a 7-day Japan itinerary for April 15-23 from Seattle, with a $2500-5000 budget for my fiancée and me. We love historical sites, hidden gems, and Japanese culture (kendo, tea ceremonies, Zen meditation). We want to see Nara's deer and explore cities on foot. I plan to propose during this trip and need a special location recommendation. Please provide a detailed itinerary and a simple HTML travel handbook with maps, attraction descriptions, essential Japanese phrases, and travel tips we can reference throughout our journey.
Output:
As you may see above, the agent has started working on the task as mentioned in the prompt. Below are some more snapshots of the task execution step-by-step:
After the task has ended, if you’re in the headed mode (headless=False), you’ll be able to see an html file opening in the browser, which may look like this:
Conclusion
Installing OpenManus locally empowers developers to experiment with an open-source AI agent without invite restrictions. By leveraging Ollama models, users can bypass API key dependencies and run OpenManus for free, making AI experimentation more accessible. While using everything in your machine for free feels lucrative, it expects your single computer to have a great compute power to handle all the Ollama processing along with the Agent workflow. But having a powerful compute doesn’t have to be restricted like Manus! That’s why NodeShift’s affordable and few-click cloud deployment ensures developers focus more on innovation and less on computation.
