> ## 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.

# Custom Integrations

> Bring your own hardware to Cyberwave. Create an asset, write a driver, and unlock every platform feature, typically in days instead of months.

Cyberwave ships **80+ devices** in its [catalog](https://cyberwave.com/catalog), but it's built to connect **any** device with an API, serial interface, or network protocol. If your hardware isn't in the catalog (a custom robot, an in-house prototype, or a niche industrial machine), you can integrate it yourself in two steps.

<Info>
  Teams typically bring a brand-new piece of hardware fully online with
  Cyberwave in about **2 days**, versus the **months** a bespoke integration
  usually takes, because the digital twin, transport, UI, workflows, and
  data tooling already exist. You only supply the asset and the driver.
</Info>

***

## Bring your own hardware

<Steps>
  <Step title="Create an asset for your hardware">
    Every twin starts from an **asset**, the 3D and kinematic definition of your
    hardware (a URDF plus its meshes). Upload yours to create a custom asset,
    which you can keep **private** to yourself, share with your **organization**,
    or make **public** to everyone on the platform, depending on your needs.

    <Card title="Create an Asset" icon="cube" href="/feature-reference/create-asset">
      Step-by-step: prepare a URDF ZIP and create your asset from the dashboard.
    </Card>

    Need a reference to model yours on? Download a complete sample URDF (a DJI
    Mini 4 Pro drone) showing link, joint, material, and mesh-reference structure:

    <Card title="Sample URDF: dji-mini-4-pro.zip" icon="file-zipper" href="/assets/dji-mini-4-pro.zip">
      One `base_link`, four propeller links, and four `continuous` joints in a single file.
    </Card>
  </Step>

  <Step title="Write a driver for your hardware">
    A **driver** is what makes your asset come alive. It's a small **Docker
    container** that bridges your device's native interface (ROS, serial, REST,
    gRPC, VDA5050, OPC UA, Modbus, or any other protocol) to Cyberwave's MQTT
    layer. It publishes telemetry (joint states, odometry, camera frames, sensor
    data) up to the twin and turns dashboard, SDK, and workflow commands into
    actions on the device.

    You don't have to start from scratch: scaffold a complete, production-ready
    driver with the **AI driver skill** or one of the official **SDKs**, then
    fill in the hardware-specific logic.

    <Card title="Writing Compatible Drivers" icon="code" href="/feature-reference/edge/drivers/writing-compatible-drivers">
      The full guide: container contract, the `cw-driver.yml` interface manifest,
      MQTT catalog, environment variables, and packaging.
    </Card>
  </Step>

  <Step title="Use every Cyberwave feature with it">
    That's it. With an asset and a driver, your custom hardware behaves like any
    catalog device, a first-class digital twin you can drive, record, automate,
    and simulate. Everything below works out of the box, no extra integration
    required.
  </Step>
</Steps>

***

## Everything you unlock

Once your hardware is paired, it gets the full platform, the same capabilities every catalog device enjoys:

<CardGroup cols={2}>
  <Card title="Workflows" icon="diagram-project" href="/overview/features/workflows">
    Chain perception, models, and motion into repeatable automations, low-code or in Python.
  </Card>

  <Card title="Replay & recording" icon="clock-rotate-left" href="/overview/features/replay-and-historical-data">
    Record episodes, scrub the timeline, and export datasets for training and review.
  </Card>

  <Card title="Teleoperation & remote takeover" icon="gamepad" href="/overview/features/teleoperation-and-remote-control">
    Drive your hardware from anywhere and take over from an AI policy with one click.
  </Card>

  <Card title="Controllers & models" icon="brain" href="/overview/features/models-and-datasets">
    Assign keyboard, teleop, or trained AI policies as the controller for your twin.
  </Card>

  <Card title="Simulation" icon="cubes" href="/overview/features/simulation">
    Validate behavior against the digital twin before it ever touches real hardware.
  </Card>

  <Card title="Digital twin" icon="diagram-project" href="/overview/features/digital-twin">
    A live, synced virtual mirror of your hardware that the whole platform builds on.
  </Card>
</CardGroup>

***

## Works with your existing stack

Because integration happens at the **driver** layer, Cyberwave is protocol-agnostic and sits alongside the tools your team already uses. The same driver pattern bridges any of these to the digital twin:

* **ROS 1 / ROS 2**: robot arms, mobile robots, and sensor stacks
* **VDA5050**: AGV / AMR fleet communication
* **OPC UA**: industrial automation and PLC connectivity
* **Modbus TCP / RTU**: sensor and actuator networks
* **gRPC / REST**: custom services and microservice architectures
* **Serial / USB**: direct device control (servos, microcontrollers)

Drivers run as Docker containers managed by [Edge Core](/feature-reference/edge/overview), on the edge device, on the robot, in the cloud, or on your laptop.

***

## Open-source resources

All integration libraries and reference drivers live under the [cyberwave-os](https://github.com/cyberwave-os) GitHub organization:

| Repository                                                                                   | Description                          |
| -------------------------------------------------------------------------------------------- | ------------------------------------ |
| [cyberwave-edge-core](https://github.com/cyberwave-os/cyberwave-edge-core)                   | Edge orchestrator                    |
| [cyberwave-edge-python](https://github.com/cyberwave-os/cyberwave-edge-python)               | Python Edge SDK                      |
| [cyberwave-python](https://github.com/cyberwave-os/cyberwave-python)                         | Python platform SDK                  |
| [cyberwave-edge-camera-driver](https://github.com/cyberwave-os/cyberwave-edge-camera-driver) | Reference camera driver              |
| [cyberwave-edge-so101](https://github.com/cyberwave-os/cyberwave-edge-so101)                 | Reference SO-101 arm driver          |
| [driver-skill](https://github.com/cyberwave-os/driver-skill)                                 | AI scaffolding skill for new drivers |

***

## Next steps

<CardGroup cols={2}>
  <Card title="Create an Asset" icon="cube" href="/feature-reference/create-asset">
    Upload your URDF and create a custom asset, public or private.
  </Card>

  <Card title="Writing Compatible Drivers" icon="code" href="/feature-reference/edge/drivers/writing-compatible-drivers">
    Build the driver that connects your hardware to its twin.
  </Card>
</CardGroup>