Case Study · Flagship

The Smart Van

An edge-AI brain for a campervan. Talk to it, and it controls the lights, reads the batteries, and finds itself on a map — all running locally on a Jetson Orin Nano, with no cloud in the loop.

Try the live demo Source on GitHub


The idea

Why build it

Van life means unreliable power and patchy 4G. A system that depends on the cloud is dark exactly when you need it. So the whole stack runs on the edge: voice recognition, the language model, and text-to-speech all live on one low-power module in the van.

How it works

The stack

VOICE

Local agent

A Qwen LLM via Ollama runs an agent loop with tools, fed by on-device ASR and answered through on-device TTS. No transcript ever leaves the van.

POWER

Victron telemetry

SmartShunt, SmartSolar, and an Orion DC-DC charger read out over BLE — live state-of-charge, solar yield, and load, parsed from the raw instant-readout frames.

CONTROL

Lights & devices

12V spotlights on a Shelly dimmer, driven through a clean device contract so new hardware drops in behind the same interface.

PLACE

Location & camera

GPS from the 4G router puts the van on a map; a webcam feed streams over the local network for a quick look outside.

Engineering

Built for testing

Every layer has a test seam: device drivers run against a contract suite, the agent against a stub model, Victron parsing against golden BLE dumps, and the web API against an in-memory bus. The laptop runs the full suite green with no van attached — the hardware adapters stay thin on purpose.

Python FastAPI PipeWire BLE Ollama Jetson Orin Nano


See it running

The demo is the real dashboard UI on simulated telemetry — toggle the lights, watch the batteries tick.

Open the live demo