Repo · Games & real time
Jev Goal Reflex
Three.js simulation where an OpenAI model turns each plain-language instruction into a plan and Jev makes every reflex decision: two Score questions…
Open github.com ↗From the repository
Steer a 3D box with plain-language goals: an LLM (System 2) plans each instruction, TypeSafe Jev (System 1) makes every move, turn and jump decision in real time. Three.js + TypeScript.
ai-agentsgame-aijevllmreal-timesystem-onesystem-twothreejstypesafetypesafe-jevtypescript
How builders describe it
Three.js simulation where an OpenAI model turns each plain-language instruction into a plan and Jev makes every reflex decision: two Score questions for move and turn plus one Noul for jump, with code acting only past a 0.33 dead zone and sending no Jev request while no step is active.
The decision Jev makes
Choose a legal move, a lane or an NPC reaction each turn.
Where it fits
Games are a stress test for decision speed. Jev picks the next move from the legal ones, fast enough for arcade games and deep enough for chess and strategy. All 256 games & real time projects →