Skip to content
Tech News
← Back to articles

Show HN: A desktop fly drawn to the scent of vibecode

read original more articles
Why This Matters

This innovative desktop fly simulation leverages real neural data and scent-based cues to create an immersive and biologically inspired interaction on macOS. It highlights advancements in neural modeling, sensory integration, and interactive visualization, offering new possibilities for research and entertainment in the tech industry. For consumers, it provides a novel, engaging way to explore neuroscience concepts through a playful and realistic virtual creature.

Key Takeaways

DesktopFly πŸͺ°

A 3D fruit fly that lives on your macOS desktop β€” driven by a live spiking simulation of the real FlyWire connectome. It walks across your windows, grooms, sleeps, and decides to flee your cursor with the same neurons a real fly uses.

Fork of DenisSergeevitch/desktop-fly β€” this one gives the fly a sense of smell for vibecode.

It scans your disk for agent markers ( AGENTS.md , CLAUDE.md , .cursor/rules , .kiro/steering and ~40 more) and turns anything on screen that leads to them into an odour source: an editor or terminal window with the project open, a row in the front Finder window, a folder icon on the desktop. An open project smells strongest, a closed icon weakest, and the reach of each grows with how much vibecode it holds β€” a hub of six marked repos is smelled across the whole screen, a single weak folder only from nearby. The steering neurons then walk the fly there, and when the smell is far the population wakes up enough to make it fly.

The fly's brain window: 23,210 real neuron soma positions from FlyWire v783, with live spikes flashing at real neuron locations. The two glowing yellow markers are the Giant Fibers β€” the escape command neurons. Click any region to stimulate it.

What's real

23,210 neuron soma positions (of 139,255 in FlyWire v783) render the rotating brain window, colored by super-class (FlyWire's coarse cell-type grouping).

(of 139,255 in FlyWire v783) render the rotating brain window, colored by super-class (FlyWire's coarse cell-type grouping). A 668-neuron circuit with ~19,000 real synaptic connections (synapse counts, signed by neurotransmitter prediction) runs as a 1 kHz leaky-integrate-and-fire (LIF) simulation: LC4 (104) + LPLC2 (210) looming-detector visual neurons DNp01 / Giant Fiber (GF) (2) β€” the escape command neuron DNa01 + DNa02 (4) steering neurons Β· DNp09 (2) forward walking DNg11 (6) grooming Β· MDN (4) backward walking ("moonwalker") DNp02/DNp04/DNp11 (6) escape-maneuver (wing) neurons their 330 strongest partners, including ascending (proprioceptive) and sensory (wind) neurons

(synapse counts, signed by neurotransmitter prediction) runs as a 1 kHz leaky-integrate-and-fire (LIF) simulation: Escape is not scripted. Your cursor's approach becomes looming input to the real LC4/LPLC2 cells; the fly takes off only when the Giant Fiber actually spikes through its real synapses β€” ~1,200 synapses of feedforward inhibition push back, which is why slow approaches are tolerated and fast lunges trigger escape in ~4 ms, just like the real animal.

The body itself is procedural (FlyWire is a brain connectome β€” no body geometry exists), with a tripod gait, visible wing-beat, altitude-scaled flight, grooming, and sleep postures.

... continue reading