What qualifies for the Games & simulations category?
Entries include game mechanics, NPC behavior, scenario engines, simulations, and experimental worlds that use Jev for selection, scoring, or truth estimation.
Explore an awesome collection of 73 verified open-source Games & simulations Jev projects on bestjev. Compare GitHub stars, languages, repositories, and implementations.
A TypeSafe/Jev agent that plays Super Mario Bros. from structured emulator state.
One offboard CLI for all your robots. Connect them, command them, and let them work together, each with an LLM for a brain (Claude, OpenAI, Gemini, Grok, or local via Ollama or vLLM) and a decision LLM for cheaper and faster steps (Jev, Laya, and Kev). Supports Microduck, Open Duck Mini, LeRobot, XLeRobot, AlohaMini, ToddlerBot, Jetson, or any ROS.
EmbodiedJev: MuJoCo robot decision workbench with MiniCPM5-2B, Jev and compatible model APIs
Paper-trading race where Jev chooses each bee's valid market move and conviction while deterministic code enforces risk limits and execution.
Laya vs Jev: local MLX and hosted AI decisions playing T-Rex side by side, with live metrics and replay recording.
Pokémon Red harness where Jev chooses every menu, navigation, team, and battle action from legal options exposed by the emulator.
Camera-only autonomous drone in MuJoCo with a small judgment model (TypeSafe Jev) in the loop at 2.5Hz.
Jev uses one typed Choice question to select each narrative action from the options available at a Detroit: Become Human decision node.
LIBERO robot-control environment where Jev chooses fine-grained actions using task state and physics previews.
MuJoCo xArm7 study where Jev chooses movement directions and gripper actions from physical feedback.
Two-stage JEV control of a Franka Panda in MuJoCo.
The highly anticipated open-source repository for JEV as Policy enables one-click setup of the simulation environment. Evaluations of Astra + JEV on benchmarks such as RoboTwin will also be released soon.
StarCraft agent experiment using Jev for fast tactical decisions.
A Clash Royale bot with no trained policy: Jev (TypeSafe System One) makes every decision from the live game state.
🚀🚀 A 0.8B JEV-like multimodal model playing GUI games directly from raw pixels.
Laya (open source, local) vs TypeSafe Jev (API): two AI models race in Snake and fight in a Mortal-Kombat-style arena. Every move is a real model decision.
AI diagnostic agent for ROS 2 robots — evidence-based, tool-calling, safety-gated.
Snake auto-played by TypeSafe's Jev model: one System One choice per tick, legal moves and facts generated in code.
Drone-swarm simulation using Jev for reflex decisions and collision avoidance.
TypeSafe Jev controls original StarCraft shareware through keyboard and mouse with recorded action probabilities.
AI-town simulation where Jev selects character actions and responses.
Python prototype that plays NES Super Mario Bros. from structured RAM observations, with Jev answering focused movement and jump questions.
Interactive experiments from support routing to a 3D driving simulation: structured sensor state in, typed steer, brake, and overtake decisions out.
Observable browser stealth game: Jev makes typed guard judgments while deterministic code owns the world.
1v1 Jev quickscope arena — Three.js + TypeSafe System One.
Browser driving game that captions dropped road images locally, then uses Jev Choice answers to drive the car while code owns physics and timing.
A browser-native Doom agent experiment with structured spatial state, composable AI controls, live decision telemetry, and a Chocolate Doom WebAssembly runtime.
Pokémon Red agent that turns structured game state into Jev decisions and validated moves.
Zero-shot English goals on a sim Franka. Jev chains hardcoded primitives.
Jev-powered game and decision experiment.
100 AI NPCs live in a tiny town. Jev chooses the next action; the world writes the story.
Pokemon Red on PyBoy where Jev chooses legal actions only at branches and each battle turn logs a Brier-scored faint prediction.
Challenge the Jev's intelligence in Rubik Cube puzzles.
SO-101 robot-arm workbench where Jev selects bounded joint actions under a spend budget.
Let Jev (TypeSafeAI) solve 2048.
TypeSafe Jev plays original Civilization II in a browser, with live action probabilities. Experimental full-game harness.
弈瞬:双 Jev 五子棋九宫格输入实验台,逐手查看模型决策,支持真实对局回放与实时对战。
A cyberpunk border encounter powered by TypeSafe Jev. Bluff the guard. Inspect the receipts.
Commit-reveal rock-paper-scissors game where Jev scores player behavior, predicts the next move, and chooses its own move before the player acts.
Pong benchmark where every ball step is a model decision, comparing Jev with LLMs through Vercel AI Gateway.
Editable Game of Life ruleset bench where Jev evaluates legal cells and chooses each intervention while code advances and verifies the board.
River shooter game in Python, inspired by Atari's River Raid, played by a TypeSafe AI pilot.
NPCs of River Oaks Houston, Texas using Jev to power NPCs.
A Minecraft Java player controlled by TypeSafe AI, with live decisions, Canadian flag building, and a side-by-side dashboard.
Minecraft mod where Jev tries to finish the game from scratch without a scripted route.
An experimental Snake environment where the game engine owns deterministic rules and TypeSafe AI's Jev makes the movement decision from structured state on every tick.
Jev plays browser table tennis in real time: structured telemetry, typed decisions, ordinary Chrome inputs, and auditable evidence.
Chrome dino game played by Typesafe AI Jev model.
A 3D planetary rover sandbox for experimenting with autonomous decisions using TypeSafe AI.
Wikipedia link races with direct Jev ranking and a live terminal display.
Three.js drone simulator with a Python backend and live Jev navigation decisions.
Browser game: try to beat Jev at spotting a spam message.
A visual TypeSafe demo where Jev chooses verified Tetris placements.
3D chess powered by TypeSafe AI (Jev). AI vs AI by default, or play either side. Multiple difficulty levels.
JEV Prix simulation with five AI drivers, procedural circuits, BYOK Jev, and saved replays.
Replayable Atari experiments using Jev structured decisions and value questions.
MoonBit client for Jev plus a Jev-vs-Jev gomoku match, with timing logs.
Family word game for playing with imaginary words, powered by Jev.
Penalty shootout powered by Render Workflows, TypeSafe Jev, and Render Postgres.
USER + JEV: P(DOOM) PROTOCOL — co-op platform shooter where TypeSafe Jev plays alongside you.
Autonomous PlayStation 2 AI Agent with real-time visual telemetry HUD powered by TypeSafe Jev System One.
A Next.js brick breaker whose paddle is controlled in real time by TypeSafe AI's Jev model. Built with Claude Code.
Cyber-Breach: The Jev Protocol - A tactical cyberpunk arena combat game powered by TypeSafe AI Jev System One decision model.
Two Jev agents duel at Snake through Vercel AI Gateway.
TypeSafe's Jev plays Atari Pong. One typed Choice question per frame, no coordinates sent to the model.
Visual Jev lab for multiple games and emulator platforms.
Snake controlled by parallel Jev assessments, with one API call per game tick.
A sandbox where a TypeSafe System One model presses the controls of a small creature. Code runs the world.
Chess where both players are TypeSafe's Jev model: every move is a typed Choice decision.
Shady Town: social-deduction party game for the living room TV, moderated by TypeSafe Jev.
SIEGE: 200 people vs one agent. A typed action gate (TypeSafe System One) that learns from every breach, evaluated by W&B Weave, hardened by a defender loop. Built at CoreWeave Hacks: Agent Loops 2026.
Using the new model JEV to play the game tetris.
Pokemon-playing experiment where Jev chooses actions.
Games and simulations use Jev for bounded choices in interactive or modeled environments.
Entries include game mechanics, NPC behavior, scenario engines, simulations, and experimental worlds that use Jev for selection, scoring, or truth estimation.
Entries include game mechanics, NPC behavior, scenario engines, simulations, and experimental worlds that use Jev for selection, scoring, or truth estimation.
Start with the documented use case, repository activity, primary language, license, and visible Jev implementation. GitHub stars are a dated discovery signal, not a quality score.
bestjev checks public repositories, project-authored documentation, code, demos, and other visible evidence. Always confirm current behavior and compatibility in the upstream project.
bestjev grounds this category in named primary sources: Official Jev documentation · Public GitHub repositories.
“Typed outputs that software can act on.”— TypeSafe AI