VIT Intercore is the assistant we built for our own daily work. Instead of windows and menus it has one object on screen — a planet made of 76,000 fragments of light. When it wakes, its memory unfolds around it as a graph: people, the company, systems, skills, music.

It is controlled the way you would address a person: by name and by hand. The camera follows both hands, the microphone waits for the word “Vit”, and the assistant answers aloud in a human voice.

The hand works as a pointer. An open palm wakes the core, a pinch grabs and turns the view, two pinches zoom, and a short pinch presses a node. Hand tracking runs locally with MediaPipe; no camera frame is stored.

Voice goes through a single brain: it understands the request, calls tools — open a section, find a node, play music, assemble a kit — and speaks the answer. When music is playing and the name is heard, the track steps back so the assistant can listen and reply.

The workbench is a second scene with real depth: parts, wires, a soldering iron and a bin. Smart glasses and a watch are assembled step by step, by hand or by voice, and six drills train the hand: grab and throw, press, sort, stack, zoom and turn.

The trailer runs 1 minute 4 seconds and is filmed frame by frame from the real interface: wake, memory, gestures, voice search, music, the workbench and hand training. The music is an original score written for the film.

The planet, the graph, the table and every part are procedural — drawn in code, with no 3D model files. The filmed build holds 387 memory nodes and 656 links.