# Add on-device AI





Recipes for running AI inference **on the user's own machine** instead of calling out to a hosted API—no API key, no network round-trip, and it keeps working offline.

<Cards>
  <Card href="/bare/how-to/add-on-device-ai/build-a-local-ai-chat-tui-with-qvac" title="Build a local AI chat TUI with QVAC" description="Add a second worker for on-device inference and a bare-tui interface on top of the hello-pear-bare template—streamed answers, model/context flags, and a protocol you can repurpose beyond chat." />
</Cards>