If you’ve ever imagined having your own Jarvis (Just A Rather Very Intelligent System), an AI that can code, browse the web, plan projects, and even chat with you through voice, all while staying completely offline and private, AgenticSeek is that vision made real. This open-source, fully local alternative to invite dependant AI assistants like Manus AI brings next-gen capabilities directly to your device. On your command, AgenticSeek autonomously chooses the right AI agent, fetches information from the internet, writes or debugs code, fills out web forms, and even builds a plan to execute your task. And it does all this without needing any API usage, and can be operated locally, meaning your data never goes to an external unknown server.
In this guide, we’ll walk you through a comprehensive and step-by-step process to install AgenticSeek locally so you can start experiencing this privacy-first, voice-enabled AI agent today.
Prerequisites
The minimum system requirements for this use case are:
- GPUs: RTX 4090 or RTX A6000 (for smooth execution).
- RAM: At least 48 GB.
- Disk Space: 100 GB (may vary across models)
- Nvidia Cuda installed.
Step-by-step process to install and run AgenticSeek locally
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 RTX A6000 GPU, however, you can choose any GPU of your choice as per the “Prerequisites”.
- 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 A6000 48GB GPU node with 48 vCPUs/84GB 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, click on Connect with SSH, and copy the SSH details that appear.
As you copy the details, follow the below steps to connect to the running GPU VM via SSH:
- Open your terminal, paste the SSH command, and run it.
2. In some cases, your terminal may take your consent before connecting. Enter ‘yes’.
3. A prompt will request a password. Type the SSH password, and you should be connected.
Output:
Step 7: Set Up Project Environment
- Make sure you have Anaconda installed and set up in the system, then start by creating a virtual environment with
conda
.
conda create -n agenticseek python=3.11 -y && conda activate agenticseek
Output:
2. Install Ollama with dependencies.
apt install pciutils lshw
curl -fsSL https://ollama.com/install.sh | sh
Output:
3. Start the Ollama server.
ollama serve
Output:
4. Open another terminal, connect to remote server and install deepseek-r1:70b
.
ollama run deepseek-r1:70b
5. Check if model is installed.
ollama list
Output:
Step 8: Clone AgenticSeek & Install Project Dependencies
- Clone the official repo of the agent.
git clone --depth 1 https://github.com/Fosowl/agenticSeek.git
Output:
2. Install all the project requirements.
./install.sh
Output:
3. Install other dependencies that are not mentioned in the above script but necessary for the model to run successfully.
apt-get install libportaudio2
conda install -c anaconda pyaudio
Output:
Step 9: Configure and Start the Agent Server
Once everything is installed, we’ll connect our local VSCode editor to the remote server and write the Python code. We’ll then use this code to configure model and edit the code if needed before running it for inference.
If you’re using a GPU through a remote server (e.g., NodeShift), you can connect it to your visual studio code editor by following the steps below:
a) Install the “Remote-SSH” Extension by Microsoft on VS Code.
b) Type “Remote-SSH: Connect to Host” on the Command Palette.
c) Click on “Add a new host”.
d) Enter the host details, such as username and SSH password, and you should be connected.
- Edit the contents of
config.ini
as shown below to match the ollama provider.
Create a rough workspace to save all the work files that Agent will produce during inference and place the path of that directory in work_dir
.
2. Move inside llm_server
directory and install the requirements.
pip3 install -r requirements.txt
3. Start the Agent server at port 5000.
python3 app.py --provider ollama --port 5000
Output:
Step 10: Set Up Client Machine
Our agent is successfully up and running. Now, its the time to setup client system with backend and frontend interface from where we’ll chat with the Agent and obtain the response.
Repeat the Step-9 in the local system (not inside the remote server) to set up the project in this system, as our local system will work as the client side.
- Edit the contents of
config.ini
file to point to the remote server for making agent calls.
Create a rough workspace to save all the work files that Agent will produce during inference and place the path of that directory in work_dir
.
2. Make sure all the routes mentioned in the llm_provider.py
contain the “http
” prefix.
3. Start all the required frontend services inside the Docker desktop.
Move inside the agenticSeek
directory and then run this command.
./start_services.sh
Output:
Our frontend services have started successfully, let’s move on to start the backend server.
4. If you’re on a remote machine (e.g., NodeShift GPU), you’ll need to do SSH port forwarding in order to make the agent server accessible for the backend server to make calls to.
Run the following command in your local terminal after replacing:
<YOUR_SERVER_PORT>
with the PORT allotted to your remote server (For the NodeShift server – you can find it in the deployed GPU details on the dashboard).
<PATH_TO_SSH_KEY>
with the path to the location where your SSH key is stored.
<YOUR_SERVER_IP>
with the IP address of your remote server.
ssh -L 5000:localhost:5000 -p <YOUR_SERVER_PORT> -i <PATH_TO_SSH_KEY> root@<YOUR_SERVER_IP>
Output:
5. Logout of Hugging Face to remove any expired credentials.
huggingface_hub logout
6. Export SEARXNG_BASE_URL
.
export SEARXNG_BASE_URL="http://127.0.0.1:8080"
7. Start backend API server.
python3 api.py
Output:
Step 11: Access the Agent Web Interface
Access the interface at http://localhost:3000
. It’ll look something like this:
We’ll ask it to find top cafes in Rennes, France.
As shown above, Agent has responded that the creation of the file is successful. Let’s see the created file in our local system.
As you can see, it has created the file successfully.
And has mentioned the cafe names as instructed.
Conclusion
By now, you’ve seen how AgenticSeek combines powerful features like autonomous web browsing, intelligent task planning, and take actions like file creation, editing and much more, all while running 100% locally to ensure your data stays private. If you’re building projects, researching online, or just experimenting with cutting-edge AI, AgenticSeek helps you without relying on any API or other restrictions. And for developers looking to deploy or test AgenticSeek in a scalable yet private environment, NodeShift cloud offers the perfect solution, giving you full control over your compute while preserving local-first principles. It’s the ideal way to blend privacy with performance in your AI workflows.