Jev-Powered Red Alert 2 Agent

Geyzson Kristoffer wired TypeSafe’s Jev into Red Alert 2. The agent scouts with dogs, optimizes its economy and base placement, chooses when to expand, attack, defend, or use superweapons, and controls tanks and other units in combat.

View on X

Geyzson Kristoffer@GeyzsoN𝕏

This might be the craziest thing I’ve built with TypeSafe’s Jev yet. I wired it into Red Alert 2, and now it scouts with dogs, optimizes its economy and base placement, decides when to expand, attack, defend, or use superweapons—and somehow split-pushes tanks, micros its army during fights, and routes around enemy defenses. A lot of this behavior just emerged from Jev making decisions in real time

Sep 17, 2026X postsView on X

It can split-push tanks, micro its army during fights, and route around enemy defenses. Kristoffer says much of this behavior emerged from Jev making decisions in real time.

Also filed under Games & real time

Steer a 3D Box with Goals
The build steers a 3D box with plain-language goals. An LLM plans each instruction, while TypeSafe Jev makes move, turn, and jump decisions in 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.
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.
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.