AWARE
A solo Hack the 6ix build: an $80 Arduino that sees, hears and follows plain-English rules, with every model on the board.
Jul 2026Hack the 6ix 2026solo
AWARE device on an Arduino UNO Q. Open the full-size file 
AWARE web dashboard. Open the full-size file
tl;dr
- Every model runs on one $80 Arduino UNO Q. No cloud inference, but not offline: the camera and mic are processed on the board, and alerts go out over Telegram.
- You type a rule like "when glass breaks after 10pm alert me". An on-device LLM turns it into a deterministic rule.
- A rules engine checks every active rule each 500 ms. No LLM in that loop.
- YOLOv8n runs on the board's Adreno GPU through ONNX Runtime QNN.
Why I built it
My goal for the edge track: a device where you describe what to watch for in plain English, and every model, including the language model, runs on the board. Nothing goes to a cloud model.
What I built
I built it solo, so every part is mine: the perception pipeline, the LLM rule compiler and parser, the rules engine, memory digests, the dashboard, the bridge to the microcontroller, and deployment.
How it works
- Perception, always on. YOLOv8n object detection at 2 Hz, plus BlazeFace, MediaPipe pose and hands, and MiDaS depth. YAMNet sorts sounds into 521 classes at 4 Hz. The STM32 microcontroller reads temperature, distance and motion, with Edge Impulse anomaly detection.
- Reasoning, on demand. The LLM reads your command and calls create_rule() with "when" and "then" fields. A plain parser compiles those into triggers and actions.
- Rules, every 500 ms. The engine checks each rule against the latest perception data. The LLM is not involved.
- Action. Piper TTS on a Bluetooth speaker, LEDs, servo or relay control, Telegram alerts, video clips, and live dashboard updates.
- Memory. Every event goes into SQLite. Every 5 minutes the LLM compresses recent events into a short digest. Ask "what happened today?" and it answers from the log, on the device.
Models and cost
| Model | Job | Runtime |
|---|---|---|
| YOLOv8n | object detection | ONNX on the Adreno 702 GPU, via QNN |
| YAMNet | sound events, 521 classes | ONNX |
| Whisper-tiny | speech to text | on-device |
| Piper TTS | text to speech | on-device |
| MiniCPM5-1B (GGUF Q4_K_M) | commands to rules, memory | on-device |
The LLM only runs when you add a rule, ask a question, or a digest is due. The 500 ms checks are plain code. No API costs, and no camera or mic data goes to a cloud model.
Results
- Built at Hack the 6ix 2026, with all inference on one $80 board.
Stack
- Python 3.12
- YOLOv8n
- YAMNet
- Whisper-tiny
- MiniCPM5-1B (GGUF)
- Arduino UNO Q