Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.cyberwave.com/llms.txt

Use this file to discover all available pages before exploring further.

Cyberwave is in Private Beta.

Request early access to get access to the Cyberwave dashboard.

Want to try Cyberwave without any setup first? See Try a Real Robot Live to control a real SO101 arm from your browser in under 2 minutes.

​
Build Your Own Setup

Ready to go beyond the demo? This guide takes you from zero to a working Physical AI application. You will:
  1. Create a virtual environment and add a digital twin of your robot
  2. Build applications using the Python SDK, MCP server, or REST API from your laptop, with no hardware required
  3. Connect real hardware so the same code drives a physical robot

​
Part 1: Develop in Simulation

Start here. No hardware required.

​
Step 1: Create an Environment

An environment is a 3D virtual space that mirrors your real-world robot setup. It’s where your digital twins live, sensors stream data, and controllers send commands, all in real time.
  1. Go to the Cyberwave dashboard and click New Environment.
  2. Give your environment a name and description.

​
Step 2: Add a Digital Twin

A digital twin is a virtual replica of your physical robot, it mirrors the robot’s structure, joints, sensors, and behavior in real time within your environment.
  1. Inside your environment, click Add from Catalog in the left panel.
  2. Browse the catalog, find your robot, and add it to the environment.
  3. Position the twin to match your physical setup.

Browse Catalog

Explore our robot catalog

​
Step 3: Build Your Application

With your environment and digital twin ready, you can start building immediately. Your application code runs anywhere, laptop, cloud server, CI pipeline and talks to Cyberwave Cloud over the API.

Python SDK

Control twins, capture frames, trigger workflows, and manage infrastructure programmatically

MCP Server

Let AI agents (Claude, GPT, Cursor) manage your robotics setup through natural language

REST API

Direct HTTP access to every Cyberwave operation from any language
Install the Python SDK on your development machine: 
pip install cyberwave
Generate an API key by going to Profile Settings and clicking Create an API Key. Then export it: 
export CYBERWAVE_API_KEY=your_api_key

​
Step 4: Control Your Twin in Simulation

You can control your digital twin in simulation in two ways: through the dashboard UI or through code.
Control your twin directly from the Cyberwave platform, no code needed.
  1. Open your environment in the Cyberwave dashboard.
  2. Switch to Simulation mode.
  3. Click the Assign Controller button on your twin.
  4. Select a controller from the list, for example:
    • Keyboard: control individual joints using keyboard keys
  5. Start moving the twin using the assigned controller. You’ll see the digital twin responding in the 3D environment in real time.
Your twin is being controlled in simulation. Use this to explore how the robot behaves before writing any code or connecting real hardware.

​
Part 2: Connect Real Hardware

Once your application works in simulation, connect it to the physical robot. These steps run on the machine that is physically connected to the robot, an edge device (Raspberry Pi, Jetson) or your laptop if the robot is plugged in directly via USB.
If you’re only working in simulation or building application code, you can skip Part 2 for now and come back when you’re ready to connect hardware.

​
Step 5: Install the Cyberwave CLI

The Cyberwave CLI and Edge Core require a 64-bit architecture (arm64/aarch64) on Raspberry Pi. If you are using a 32-bit OS or architecture, please wait for an updated version.
SSH into your edge device:
ssh <edge-device-username>@<edge-device-ip>
Then install the CLI:
curl -fsSL https://cyberwave.com/install.sh | bash

​
Optional: Authenticate the CLI

If you want to pre-authenticate the CLI before installing the Edge Core, you can log in with your API key. This is a one-time step, it writes a credentials.json file with your token, workspace, and related settings so the CLI (and Edge Core) can use them automatically.
  1. Go to Profile Settings in the Cyberwave dashboard.
  2. Click Create an API Key and copy the generated key.
  3. Run the login command:
cyberwave login --token YOUR_API_KEY
This step is optional. If you skip it, cyberwave edge install will prompt you to log in interactively during installation. Pre-authenticating is useful if you’re scripting the setup or want to avoid the interactive login during install.

​
Step 6: Install the Edge Core

The Edge Core runs on the robot’s machine and bridges your physical hardware to the Cyberwave cloud. 
sudo cyberwave edge install
If you already authenticated with cyberwave login, the installer skips the login step and goes straight into environment selection and pairing prompts after installing cyberwave-edge-core. Otherwise, it will prompt you to log in first.

​
Step 7: Pair Hardware with the Digital Twin

Follow the prompts in your terminal:
  1. Select the environment you created in Step 1.
  2. Select the digital twin you added in Step 2.
  3. The appropriate driver will be automatically installed and configured for your robot.
Your physical robot is now paired with its digital twin and syncing in real time.
Your application code from Part 1 now drives the physical robot. Switch the SDK to live control so your actions affect the real robot: 
cw = Cyberwave(api_key="your_api_key")
cw.affect("live")

​
Next Steps

Architecture

Understand the full system architecture

Python SDK

Full SDK reference and examples

MCP Server

Let AI agents manage your infrastructure

SO101 Robot Arms

Set up teleoperation and datasets

UGV Beast

Get started with the UGV Beast

Unitree Go2

Connect the Go2 quadruped