FAQ

Can I connect my own model to wavecat?

Answer

Out of the box, wavecat runs entirely on the models bundled with it — all on your own machine. It should just work.

For advanced setups, there’s an optional (in development) path to route the heavier interactive work to a model server you provide. The rest of the local pipeline keeps running on-device exactly as before; you’re only pointing the most demanding tasks at infrastructure you control.

Hopefully this will be useful for users with local Mac Studio or DGX Spark servers, where they can run more powerful models and connect them securely and privately with wavecat. Still no cloud. The on-device pipeline that watches your screen and builds context stays local either way. I’ll perhaps work on improving that too, so that you can run wavecat on even less powerful laptops.

So the short answer is yes, but you almost certainly don’t have to. The default is designed to be great on its own, and your data stays private throughout.

Thank you for downloading wavecat!

Your download should begin automatically.

Getting started

  • Open the downloaded file and follow the prompts to finish setup.
  • On first launch, wavecat guides you through installing its vision and language models, which take up roughly 19 GB of disk space.
  • You'll then be asked to allow wavecat to watch your screen. Everything runs locally, so no personal data ever leaves your device.

Hardware requirements

  • Mac: Apple Silicon only, with 24 GB unified memory minimum and 32 GB+ recommended.
  • Windows / Linux: a dedicated GPU with 12 GB+ VRAM (Vulkan, plus CUDA on Windows), or a unified-memory device with 24 GB+ RAM.
  • Nothing is strictly enforced, but wavecat won't run smoothly unless your device meets these requirements.

Wrong OS? Download for macOSWindowsLinux.