Neuronum Docs | Getting Started

Getting Started

Quick Start Guide

This guide will walk you through installing the Neuronum SDK, deploying your first Agent with Neuronum Server, and making your first API call.

Protocol Note: The Neuronum SDK is powered by an end-to-end encrypted communication protocol based on public/private key pairs derived from a randomly generated 12-word mnemonic. All data is relayed through neuronum.net, providing secure communication without the need to set up public web servers or expose your infrastructure to the public internet.

⚠️ Development Status: The Neuronum SDK is currently in early stages of development and is not production-ready. It is intended for development, testing, and experimental purposes only. Do not use in production environments or for critical applications.

Requirements

Python >= 3.8
CUDA-compatible GPU (for Neuronum Server)
CUDA Toolkit (for Neuronum Server)

Step 1: Installation

Create and activate a virtual environment

Bash

python3 -m venv ~/neuronum-venv
source ~/neuronum-venv/bin/activate

Install the Neuronum SDK

Bash

pip install neuronum==2026.01.0.dev1

Note: Always activate this virtual environment (source ~/neuronum-venv/bin/activate) before running any neuronum commands.

Create a Neuronum Cell (secure Identity)

Bash

neuronum create-cell

Step 2: Deploy with Neuronum Server

Start the Neuronum Server to deploy your AI model as an agentic backend:

Bash

neuronum start-server

This command will:

Clone the neuronum-server repository (if not already present)
Create a Python virtual environment
Install all dependencies (vLLM, PyTorch, etc.)
Start the vLLM server in the background
Launch the Neuronum Server

Note: The initial setup may take some time as it downloads and installs the required dependencies.

Step 3: Call Your Agent

Now that your server is running, you can interact with your Agent using "kybercell" (official Neuronum Client) or build your own custom Client using the Neuronum Client API.

Python API

For programmatic access and integration into your applications:

Python

import asyncio
from neuronum import Cell

async def main():
    async with Cell() as cell:
        cell_id = "id::cell"  # Target cell to communicate with

        # Send a prompt to your Agent
        prompt_data = {
            "type": "prompt",
            "prompt": "Explain what a black hole is in one sentence"
        }
        tx_response = await cell.activate_tx(cell_id, prompt_data)
        print(tx_response)

if __name__ == '__main__':
    asyncio.run(main())

Next Steps

Now that you have your Agent up and running, explore more capabilities:

Client API - Learn about knowledge management, tool management, and task scheduling
Tools CLI - Create custom MCP-compliant tools to extend your Agent's functionality
Server Configuration - Customize your server settings and model parameters
E2EE Protocol - Learn how Neuronum keeps your data secure

Need Help? For more information, visit the GitHub repository or contact us.