# Game & Simulation Use this category for decisions inside games, simulations, or interactive environments. ## Submission format ```md - [Name](URL) - Industry: one-sentence description of the Jev use case. ``` ## Entries - [typesafe-mario](https://github.com/fhshaik/typesafe-mario) - Gaming: TypeSafe/Jev agent that plays Super Mario Bros. from structured emulator state, choosing each action from emulator-derived features. - [jev-drone](https://github.com/RomanSlack/jev-drone) - Robotics simulation: camera-only autonomous drone in MuJoCo that puts a Jev judgment model in the control loop at 2.5 Hz. - [tsai-sc](https://github.com/phyous/tsai-sc) - Gaming: drives original StarCraft shareware through keyboard and mouse with Jev action probabilities recorded per decision. - [jev-plays-pokemon](https://github.com/milanboers/jev-plays-pokemon) - Gaming: reads Pokémon Red game state as text, answers typed questions each turn, and lets deterministic code turn the answers into moves. - [typesafe-jev-drone-demo](https://github.com/kxzk/typesafe-jev-drone-demo) - Simulation: Three.js drone simulator with a Python backend where Jev drives the navigation decisions. - [typesafe-playground](https://github.com/kavehmz/typesafe-playground) - Interactive playground: small Jev experiments that put the decision on screen, from routing a support message to steering a car in a 3D world. - [PlayJev](https://github.com/OmniJev/PlayJev) - Gaming: open 0.8B vision-language model that reads one 448 px game frame, returns a probability over the moves the game lists in a single forward pass with no generated text, and hands its low-confidence steps to a search program, across ten browser games. - [jev-plays-pokemon-red](https://github.com/valentynkit/jev-plays-pokemon-red) - Gaming: Pokemon Red on PyBoy where deterministic code owns the route and arithmetic, Jev picks only at branches, and every battle turn's faint prediction is scored by Brier against RAM state. - [jev-reflex-autonomy-lab](https://github.com/khordoo/jev-reflex-autonomy-lab) - Drone autonomy: a multi-drone lab where Jev supplies the reflex decisions, with an optional slower strategy layer guiding them. - [Soupbase](https://github.com/spoonnotfound/soupbase) - Gaming: uses Jev `Choice` judgments to answer lateral-thinking puzzle questions and assess proposed solutions, with application code requiring supported facts, a coherent explanation, and sufficient confidence before marking a puzzle solved. - [jev-torneo-animales](https://github.com/hectorlcastro09/jev-torneo-animales) - Gaming: winner-stays-on tournament of up to 2,569 animals where each fight is one Jev `Choice` between two names under land, water or air rules held in `state`, asking the champion against the next K challengers in a single request and discarding the speculative answers once the champion falls — 1,999 fights in about 16 s at roughly US$0.01. - [2048 × Jev](https://github.com/ARCJ137442/jev-2048) - Gaming: a 2048 board where every move is a Jev `Choice` over four directions with no heuristic fallback, gated by a user-set confidence threshold that pauses play for human review, with editable prompts and board rules, bring-your-own-key backends, and archive import/export. - [Jevtown](https://github.com/gaborishka/jevtown) - Audience simulation: a town of 10,000 personas computed from their id reads a post, listing, product or headline; one request asks Jev about 60 `Score` questions on who would care plus seven `Noul` moderation checks (0.5 keeps the text out of the public feed, 0.85 blocks it), batched `Choice` questions then return each persona's reaction in waves of 600, 1,500 and 3,000, and code sends the text to the next wave only while glad reactions outweigh sorry ones by at least 0.1 of the wave. - [RoboJEV](https://github.com/lykycy123/RoboJEV) - Robotics simulation: uses two-stage Jev `Choice` decisions over structured state to select intent and Cartesian motion/gripper commands for a Franka Panda in MuJoCo, rejecting malformed responses and checking task success independently through physics. - [Jev Chess](https://jevchess.com) - Gaming: one shared board where the internet collectively plays against Jev; every legal move is an option of a single `Choice` question so an illegal move is impossible, returned probabilities shade the pieces on the board, and a live calibration panel scores each claimed confidence against a one-ply material check. - [Life Chess × Jev](https://github.com/ARCJ137442/jev-life) - Experimental game design: a turn-based Conway board where each side's move is one Jev `Boolean` per legal cell in a single request, with no heuristic fallback and a user-set confidence threshold flagging unsure turns; the game is new, so there is no established play to copy, and its rules are not self-evident — they render from editable templates with auto-filled placeholders, so a designer can rewrite a rule and re-ask. - [kNES](https://github.com/ArturSkowronski/kNES) - Gaming: a Kotlin NES emulator whose agent plays Super Mario Bros. and Final Fantasy through SemIf, the open implementation of the Jev interface, on a local Qwen3.5-4B reading the screen itself; the goals that apply this turn become the declared options of one typed `Choice`, so a button the game does not offer is impossible rather than unlikely, and 900 logged decisions at ~400 ms each on an M5 Pro never once answered off the menu. - [Laya vs Jev arena](https://github.com/PromptEngineer48/laya-vs-jev-arena) - Model comparison: races an open local model against Jev through Snake and a Mortal-Kombat-style arena, the same game code driving both. - [JEV-Star](https://github.com/sc2musa/Jev_Star) - Gaming: uses Jev `Choice` decisions for StarCraft II macro control and micromanagement on 35 SMAC-Hard maps, validates selections against available actions, and follows optional GPT-6 plans to separate frequent action selection from longer-term strategy. - [THE HUNDRED EYES](https://github.com/mintannn/THE-HUNDRED-EYES) - Interactive media art: asks Jev one `Choice` and four `Score` questions per fictional observer to animate 100 eyes from a shared post, revealing four amplified voices before equal-count analytics expose the full distribution of reactions. - [jev-pilot-reflex](https://github.com/manhua-man/jev-pilot-reflex) - Autonomous vehicle simulation: Three.js autonomous driving reflex and AI safety brake simulator using Jev System 1/2 dual-brain architecture for fast emergency intervention. - [Magic Jev Ball](https://github.com/mikecann/magic-jev-ball) - Gaming: a 3D Magic 8 Ball you hold, shake and let go, where one Convex action asks Jev a `Choice` over the 20 classic answers for the user's question and the page shows Jev's probability for every answer, displaying the highest-probability one because the rounded probabilities occasionally disagree with the reported choice. - [Jev-mice](https://mice.jev.carsonsweet.com/) - Simulation: a mouse colony whose behaviour runs through Jev decisions on top of a deterministic engine.