JevBall: 22 football players with inspectable decisions

A 3D football match in which Jev selects each player's intent from locally generated candidates. Geometry, physics and reflexes stay in code; a tactics board and JSON inspector expose the options, probabilities, chosen actions and fallback policy.

Notes

The author reports 70 live requests with no invalid answers in a seeded 30-match-second sample, 366 ms mean latency and $0.0051 total cost. All 22 players can also run on the local policy without a key.

source-backed — Public repository, docs or live artifact. About this label

Destinations

Filed under

• #games
• #threejs
• #decision-making
• #observability

In collections

• Games & simulations →