CalibratedDecisions.

Repo · Games & real time

hundred

Local lab of Jev use cases: Hundred (100 NPCs in a tiny town) and Jev Shogi (human Sente, Jev/rules Gote).

Open github.com ↗

From the repository

100 AI NPCs live in a tiny town. Jev chooses the next action; the world writes the story.

How builders describe it

100 AI NPCs live in a tiny town. Jev chooses the next action; the world writes the story.
Local lab of Jev use cases: Hundred (100 NPCs in a tiny town) and Jev Shogi (human Sente, Jev/rules Gote). Engines keep legality; Jev only picks the next closed-set action when enabled.
Two TypeScript monorepo products that keep the rules in the engine and ask Jev exactly one question: what should this person or this shogi side do next. Hundred runs a hundred NPCs with hunger, money, jobs, relationships and memories; Jev Shogi picks Gote's reply from engine-legal USI moves.

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 →

Related projects