Plain-English Cellular Ecosystem Simulator

LifePot is a cellular automaton-inspired ecosystem that users describe in plain English. Jev turns those inputs into species, feeding relationships, reproduction strategies, and environmental conditions.

View on X

Tugrul Guner@Tugrul_Guner𝕏

Look what I've built with Jev @CompleteSkeptic and @typesafeai LifePot, a cellular automaton-inspired ecosystem you describe in plain English. Jev turns your inputs into species, feeding relationships, reproduction strategies and environmental conditions. Its orchestrator selects specialists to make scoped decisions about the world. As the simulation runs, population and resource changes can trigger new Jev decisions about ecological rules and environmental pressure. The simulation itself handles movement, feeding, reproduction, inheritance, mutation and death. Jev influences the conditio

Sep 25, 2026X postsView on X

Its orchestrator selects specialists to make scoped decisions about the world. The simulation handles movement, feeding, reproduction, inheritance, mutation, and death. Population and resource changes can trigger new Jev decisions about ecological rules and environmental pressure.

Also filed under Games & real time

Benchmarks Jev on Pokémon Red
The project benchmarks Jev, TypeSafe’s fast decision model, against Jev paired with a GPT-6 Sol planner for playing Pokémon Red.
Mapping Children's Behavioral Intent in Games
Mores Research used Jev to map children’s behavioral intent in games and examine how it correlates with real-world behavior. It reports mapping intents across 45+ real sessions involving 20 child users over a long horizon.
StarCraft Agent for Fast Tactical Decisions
Jev_Star is a StarCraft agent experiment that uses Jev for fast tactical decisions.
AI-Town Character Action Simulation
JevTown is an AI-town simulation where Jev selects character actions and responses.