ANV-Gyro is a desk AI appliance — a cluster of Raspberry Pi 5 boards inside a translucent blue acrylic enclosure, running Ministral 3B entirely on-device. No cloud. No subscriptions. No data leaving the room.
The device sits on your desk. It has spinning spheres that physically show CPU load — fans push air through turbine vanes, spinning two Ø80 mm piano-black aluminium spheres. Idle: ~2 RPM. Full AI load: ~25 RPM. No dashboard needed — you see the AI working.
Inference runs inside the box. Your queries, documents and outputs never touch an external server. Works on a disconnected network. GDPR compliance is structural — not contractual — because the data never moves.
Run Ministral 3B locally, or route queries to Claude or OpenAI when you need more power. Use MixMatch to send the same prompt to multiple providers simultaneously and compare responses side-by-side — with AI-judged evaluation.
The ANV-Gyro console is a tab-based web application served from the device itself. Every tab is a live module — role-gated, real-time, and accessible from any browser on your local network.
Multi-provider streaming chat with persistent history, system prompt control, temperature/top-p tuning, and per-message provider switching.
Live Linux shell on the Raspberry Pi cluster. Full bash access for system management, model reloading, and diagnostics.
Preview, download or email full conversation transcripts. Supports formatted text export for documentation and compliance.
Live table editor connected to the PostgreSQL backend. Browse, filter and modify records directly from the console.
Usage metrics per user, global prompt counts, daily activity graphs, and real-time cluster health indicators.
Structured application event log. Timestamped entries for all system events, auth actions, and AI requests.
Device inventory view showing all connected hardware, component status, temperatures, and firmware versions.
KRaft-mode Kafka cluster monitoring. Topic list, consumer group status, lag metrics, and broker health in real time.
The console routes each conversation to whichever provider you choose. API keys never touch the browser — all proxy calls are server-side.
Default provider. Ministral 3B running via llama.cpp on the RPi 5 cluster. OpenAI-compatible API. No internet, no key, no cost.
Full Claude model suite available via server-side key management. Streamed responses via SSE, same UI as local mode.
GPT model family, proxied server-side. Same system prompt and parameter controls as local mode.
Connects directly to Mistral AI's cloud API. Same model family as the on-device version — useful for comparison.
The hardware is the product. Spinning spheres, a flip-up display, a pico projector, round status gauges — all inside a blue acrylic enclosure you can see through.
300 × 240 × 80 mm · translucent sapphire PMMA · RGB underglow · boards visible inside
Cluster compute for distributed llama.cpp inference · PWM fan control via GPIO temperature sensors
Ø80 mm aluminium · turbine vanes spin from fan exhaust · idle 2 RPM → full load 25 RPM
IPS · 1920×1200 · hinged at rear edge · 70° friction-lock · closed = silent slab
GC9A01 · 1.28" · 240×240 · front-face · CPU load + clock always visible
DLP2000 · rear-mounted · projects upward onto wall behind device · no second screen needed
OV5647 · magnetic mount · MEMS mic on pogo-pin connector · both detachable
Log in and start a conversation — local, private, no internet required.