questions: { next_action: boolean, danger: score, }
typesafe-mario
A TypeSafe/Jev agent that plays Super Mario Bros. from structured emulator state.

Every project here really calls Jev in its source · refreshed daily
questions: { next_action: boolean, danger: score, }
A TypeSafe/Jev agent that plays Super Mario Bros. from structured emulator state.
questions: { risk: score, }
Camera-only autonomous drone in MuJoCo with a small judgment model (TypeSafe Jev) in the loop at 2.5Hz
questions: { team: choice, human_requested: boolean, refund_requested: boolean, // +3 }
Interactive experiments with TypeSafe Jev, from support routing to 3D driving simulations with real AI decisions and visible sensor inputs.
questions: { lane_action: choice, speed_action: choice, hazard: score, // +1 }
2D autonomous car simulation in the browser, driven by TypeSafe's Jev decision model
questions: { throttle: choice, yaw: choice, pitch: choice, // +3 }
This demo uses Jev from TypeSafe AI to autonomously fly a drone in a random city from point A to point B, avoiding obstacles along the way. A trip costs $0.01.
questions: { line: choice, pace: choice, overtake: boolean, // +1 }
Uses jev to control race cars on a virtual track
questions: { next_move: choice, }
Chakravyuha — a polar ring-maze where every move is a Jev (TypeSafe System One) decision. A fun experiment: the model picks each move, the walk grades it green or red, and the history page asks whether its confidence score can be trusted. BYOK, no build step.
questions: { intent: choice, connection: choice, supported: boolean, }
A small detective escape room built with TypeSafe Jev, React, and Express.