# JARVIS-QVAC

Local-first Ubuntu GNOME voice assistant scaffold. The cognitive core is the
already-extracted `/home/raven/dev/agent-harness`, copied into
`vendor/agent-harness`; Jarvis does not copy or depend on `/home/raven/dev/dlinux`.

## Bootstrap

```bash
npm install
npm test
npm run cu-doctor
npm run gpu-doctor
npx qvac doctor
npx qvac serve --openai --host 127.0.0.1
```

The daemon bridge loads the harness in-process with `Agent.engine.load()` and
creates sessions with `Agent.create()`. The optional QVAC HTTP sibling is
configured for `127.0.0.1:11434`. The GNOME extension is an intentionally thin
ESM panel shell; inference, audio, portals, and computer-use actuation belong
in user services.

GPU inference is a hard requirement. `gpu-doctor` must report a QVAC-visible
GPU and `jarvisd` refuses to continue if the loaded model reports `device: cpu`.
This prevents a misleading CPU mode and competing QVAC workers.

Current repository scope is phase-0/phase-1 bootstrap plus the computer-use
grant boundary. Portal ScreenCast/RemoteDesktop, AT-SPI, PipeWire audio, the
full D-Bus adapter, GTK control-center pages, and the voice state machine are
the next implementation slices. See [docs/agent-harness-map.md](docs/agent-harness-map.md)
and [docs/cu-acceptance.md](docs/cu-acceptance.md).