FAQ

Where does the model for wavecat run?

Answer

Every model that wavecat uses runs locally, on your own computer, through llama.cpp. There is no cloud inference anywhere in the loop. From the moment you launch wavecat, the models that read your screen and power the chat all execute on-device.

Because nothing is sent to a remote server for inference, wavecat keeps working even with your Wi-Fi turned off. Your screen — and everything wavecat learns from it — stays on your machine.

If you’d prefer, you can also connect your own model for the heavier interactive work. But that’s an advanced and in-developemtn option — the default experience is fully local and needs no setup.

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.