Simulation environments with decision models

Minecraft agent where an LLM plans and Jev selects each player action, beating the game's dragon in under nine minutes in one run.

AI life-and-civilization simulation where Jev makes every person's next action as an auditable Choice and LLMs only plan.

Jev plays Atari Pong with one up/down/stay Choice per frame, receiving only digit-free relative descriptions computed by code.

Early-stage persistent multiplayer RPG where Jev makes every in-world NPC decision, Claude authors the world, and code owns rules.

Browser lane-racing demo where Jev, OpenAI Decisions and a local EmbeddingGemma model each choose a lane for the same obstacles.

Browser sandbox where Jev picks a small creature's control each step from a world-state JSON while code runs the world.

Open 4B System I driving model that scores behaviours like cruise, stop, yield and brake from three camera frames each decision.

Experimental robot loop where Jev chooses the next verified action from perception-generated options for a language goal.

MuJoCo PiPER arm controlled by a local decider-2b model choosing among ten skills via a Jev-style typed-choice interface while targets move.

Fully local grid tactics game where the open NanoJev model picks each move, attack, heal or dash from real candidate actions.

Factorio agent on FLE where Jev picks goals, next actions and stuck detection while code owns rules and actuation.

Simulation-only Payment Decision Lab testing whether Jev can beat rule-based routers at choosing payment service providers.

MuJoCo pilot where Jev, Claude Haiku and reactive rules choose pick-and-place actions; Jev matched the rules exactly.

Snake research environment where game rules stay in code and Jev picks the movement direction from structured state each tick.

StarCraft II research repo where Jev Choices pick macro actions and unit micromanagement, optionally constrained by a larger model's plan.

Simulated crypto trading loop that turns BTC and ETH tape features into words, asks Jev six judgments per tick and models costs and latency.

Evaluates Jev as a fixed policy in Gymnasium and Atari games, picking a legal action each step via one Choice question.

Mineflayer Minecraft bot where code lists feasible actions and Jev picks one in about 0.2 s; 15 of 40 runs reached the Nether.

Traffic signal controller where Jev picks each intersection's next phase from a SUMO snapshot, with local fallbacks.

Model Kombat: a 12,000-neuron fly connectome fights Jev in mk.js, with Jev picking one of seven moves about five times a second.

Camera-observed cooperative drone pursuit in a MuJoCo city where each UAV's tactical move is a /v1/systemone decision.

Pandu: tiny local policy networks (2.9K-5K parameters) with calibrated uncertainty that fall back to a teacher when unsure.

Two-stage Jev control of a MuJoCo Franka Panda: choose an intent, then X/Y/Z directions and gripper, with physics-based success checks.

Gym-style environment for offline Warcraft III with deterministic stepping and fog-filtered observations, plus an agent using Jev for micro.

Audience simulator where 10,000 computed personas read your post or listing and Jev decides who sees it and how each reacts.

Local Snake battle where four NanoJev AI snakes pick moves from a candidate distribution while you play the fifth.

Fixed-wing landing simulator and benchmark where Jev maps four Choice decisions to aircraft controls against humans, baselines and LLMs.

AI town simulation forked from a16z ai-town where Jev picks each agent's next legal move and an LLM handles dialogue and memory.

Browser driving simulator on real Canadian streets where you can replay every decision the AI driver made and why.

Three.js drone simulator flown by Jev: code computes the situation, Jev picks stick inputs, and safety limits stay in code.