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 treats every camera the same — USB webcams, IP cameras, depth cameras, infrared, industrial GigE — drop a digital twin into an environment, pair the hardware, and start consuming the stream from the dashboard, the Python SDK, or a Workflow.

​
Pick your camera

Cyberwave supports every major camera out of the box, from the classic Logitech C270 and the Intel RealSense D455 depth camera to industrial-grade machine-vision sensors like the Basler ace GigE — browse the full lineup at cyberwave.com/catalog/tag/camera. Every catalog page bundles the bill of materials, supported drivers, and troubleshooting specific to that camera — start there whenever you’re unboxing new hardware.

​
Set up a camera in 3 steps

1

Create an environment and add the camera

From the dashboard, click New Environment, then Add from Catalog and search for your camera (e.g. C270, RealSense D455, Basler ace). Position the twin to match where it’s mounted in the real world.
2

Pair the hardware

On any device the camera is plugged into — your laptop, a Raspberry Pi or Jetson on a robot, an NVR — or on the same network as an IP camera, install the CLI and pair:
curl -fsSL https://cyberwave.com/install.sh | bash
sudo cyberwave pair
The CLI auto-detects the camera (USB, V4L2, RTSP, GigE Vision, RealSense, …), installs the right driver, and links it to the digital twin. If you are unsure how the camera you picked may connect, check out its dedicated page on the catalog — it details everything you need, plus troubleshooting and FAQs. Example: Logitech C270.
3

Stream sensors automatically

Cyberwave already knows what’s on your camera. As soon as sudo cyberwave pair completes, the dashboard lights up with the live RGB feed, plus depth, infrared, stereo, or any other modality the sensor exposes — no per-sensor configuration required.
The camera streams RGB (and depth / IR where available) into Cyberwave in real time, ready for recording, teleoperation, and workflows.

​
Capture frames from Python

Once the twin is paired, the Python SDK gives you the same API for any camera in the catalog. Run this from your laptop or any cloud machine — Cyberwave handles the networking and orchestration end-to-end: 
from cyberwave import Cyberwave

cw = Cyberwave()
camera = cw.twin("logitech/c275")              # swap for any other camera slug

with cw.affect("live"):
    frame = camera.capture_frame("numpy")      # latest RGB frame
    depth = camera.capture_frame("depth")      # depth map (RealSense, ZED, …)
Switching to a different camera is a one-line change — the rest of your automation stays exactly the same.

​
Build video workflows

Workflows turn a camera stream into a video-understanding pipeline. You compose them low-code in the dashboard or directly in Python, and Cyberwave decides whether each step runs on the edge next to the camera, in a cloud node, or as a mix of both — your automation and your hardware don’t change. A typical privacy-preserving security pipeline:
  1. Anonymize faces on the edge so the video leaving the device is already redacted.
  2. Run a local model like YOLO to detect doors in the scene (pick from hundreds of models at cyberwave.com/models).
  3. When a door is open, call a powerful cloud VLM (Gemini Robotics, GPT, …) to reason about whether it’s a security hazard.
  4. Send an alert with the frame attached.
Full walkthroughs live in the zone-based intrusion detection and edge-to-cloud VLM tutorials.
Because Cyberwave also speaks to robotic dogs, drones, and arms, you can mix and match hardware in the same workflow — for example, a fixed ceiling camera that triggers a dog patrol, or a wrist camera that hands off to a cloud VLA model when it sees an unfamiliar object.

​
Record, replay, review

Cyberwave automatically handles the recording, storage, and indexing of every paired camera. Open any environment in Replay to scrub through the video timeline alongside the twin’s pose, joint states, and point clouds — straight from the web app or pulled down via the SDK / REST API for offline analysis, dataset curation, or model training.

​
Where to go next

Perception Capability

The full picture of what cameras and vision models can do on Cyberwave.

Browse the camera catalog

Per-camera setup, BOM, and troubleshooting for every supported sensor.

Intrusion Detection Tutorial

End-to-end edge-only video pipeline with YOLO, anonymize, and alerts.