Skip to main content
Connect AI to the physical world. Any robot. Any model. Simulation or real. Cyberwave turns every robot and sensor into a digital twin that your code, your models and your agents can drive, with the same API from the browser to the factory floor.

Try it now

Drive a real robot

2 min · browser only. Control a real SO-101 in our Milan lab from your browser.

Hello Robot in simulation

5 min · no code. Add a twin, press Simulate, drive it with your keyboard.

Your first AI loop

20 min · Python + webcam. A camera spots a cup; the arm picks it and sorts it, in the free Playground sim.

The platform at a glance

AI agents on top, your robots at the bottom, Cyberwave in between. Agents plan and configure; perception models, controllers and learned policies act through digital twins. Cyberwave Edge connects the twins to real hardware. You get in through the dashboard, the Python SDK, the CLI, REST and MQTT, or MCP. Cyberwave architecture. AI agents on top build the environment, control robots and define workflows. Below them your AI: perceive, control, learn. Then the Cyberwave platform: digital twins and environments, simulation, controllers and handover, catalog, data and training. Then Cyberwave Edge: Edge Core, drivers and workers on Raspberry Pi, Jetson, x86 or macOS. At the bottom your hardware: arms, quadrupeds, rovers, drones, cameras and sensors. Ways in: dashboard, Python SDK, CLI, REST and MQTT, MCP.

How AI reaches a robot

AI agents

Describe what you want. Agents build the environment, control the robot and write workflows, and you approve every plan.

AI models

Models that perceive (detection, depth, speech), reason (VLMs, LLMs) or act (VLA, RL), on the edge or in the cloud.

Control

Five ways to drive your robots: manual input, skills, workflows, VLA models and RL policies. Switch any time.

Learn

Every run becomes data. Datasets train the next model, which deploys back to the same twin.
How it all fits together →

What it looks like in code

Get an API key under API tokens. cw.affect("simulation") starts a MuJoCo instance, which uses credits; "playground" is free. Stuck? See troubleshooting.

Works across form factors

Arms, quadrupeds, rovers, drones and cameras all become digital twins with the same API. What a twin can do (move joints, grip, drive, fly, stream video) comes from its capabilities, not its brand. How hardware works →

Arms

SO-101, UR, Piper, OpenArm…

Quadrupeds & rovers

Go2, Spot, UGV Beast…

Drones

DJI Mini, PX4 Vision…

Cameras & sensors

USB, RTSP, GigE, RealSense…
Is your device supported? Check the compatibility table, or add your robot.

Choose your path

Developers

Python SDK, CLI, MCP.

ML engineers

Record, train a VLA or RL policy, and deploy it.

No-code builders

Workflows, from simulation to fleet.

Robot makers

Get your hardware listed and supported.

Integrators & enterprises

Deployment, security, fleet ops.

Get help

Troubleshooting, Discord, status.

See it in 60 seconds