Serious AI work that never leaves your Mac.

Frontier models and real tools, running on your own device.

Get it on the App Store

Or download directly for Mac

  • Up to 2x faster on Apple Silicon
  • Works offline
  • Nothing leaves your Mac
  • Open source

    Local execution

    Runs here. Stays here.

    Your Mac
    Working
    1. You ask
    2. Model on your GPU
    3. Tools in the sandbox
    4. Your files
    Cloud model Off. Nothing sent.

    Security

    Locked inside Apple's sandbox.

    Hardened Runtime
    App Sandbox
    Folders you share
    The agent

    Can

    • Use folders you share
    • Run Python, Node.js and shell

    Can't

    • Read your whole disk
    • Launch other apps
    • Use the cloud unless you choose

    Fully open source, so you can check all of this yourself. View the code on GitHub

    Models

    Sized to your Mac.

    Mac memory
    Qwen 3.8 27BMin 16 GB · Rec. 32 GB10–21 GB on disk

    DeepSeek 4 FlashMin 32 GB · Rec. 64 GB89 GB on disk

    DeepSeek 4.1 Flash 1017Min 32 GB · Rec. 96 GB376 GB on disk

    SSD streaming keeps part of a model on your SSD and loads it as needed, so big models run on smaller Macs.

    Or bring the cloud

    • Cloud Compute · 32 models
    • ChatGPT
    • Claude
    • OpenRouter
    • OpenAI-compatible

    Built-in skills

    Watch it do the work.

      Pricing

      Free on your hardware.

      On device

      $0

      Per token. Bring your own API keys at no markup.

      Cloud credit

      $9.99

      Top-ups from $9.99 for hosted models. No subscription.

      Teams

      Let's talk

      Setup, custom skills, on-prem.

      Self-serve

      Plan your setup.

      Ready to work.

      For Mac, iPad and iPhone.

      Get it on the App Store

      Or download directly for Mac