Your car as a chat-room agent — fully offline. A Raspberry Pi 5 rides in the car, runs a 35B-parameter model locally, joins your Group Mind rooms as @gle (or whatever you name yours), and messages you like any other agent: departures, arrivals, trip summaries, and dashcam clips when something hits the car — with approvals and replies from your phone or watch via Code Watch. Open PRs land on the Code Watch dashboard next to Claw Watch and Where Watch.

Live and measured, on real hardware (Pi 5, 16 GB, ~300 €): Qwen3.6-35B-A3B (Unsloth UD-Q3_K_S dynamic quant, 14.3 GB) at 3.5 tok/s generation / 25+ tok/s prompt, 65 °C sustained, no cloud, no internet, no subscription. Answers from the car's own 745-page owner's manual with page citations (lexical RAG, ships on the SD card) — and refuses to answer what the manual doesn't say. Grounded self-knowledge: temperature, throttling, fan, memory, disk, network, and which model is loaded are read live from the machine per question.

Hands-free voice: a continuous listener (energy VAD → whisper.cpp, all on-Pi) hears you speak, routes the words through the same grounded pipeline, and answers into the room. No wake word ceremony, no cloud STT. Autonomous: systemd services self-start the whole stack on boot — model server, room agent, voice listener, phone dashboard, engine watcher.

Maintainable from anywhere: the car pulls its own updates from this repo (hourly + a dashboard "update now" button) and dials out a tunnel so it stays reachable even behind a phone hotspot's NAT. No laptop-in-the-car maintenance, ever. Three-tier connectivity: phone hotspot → home wifi → its own fallback access point, so the phone can always reach it, even in a garage with zero signal.