Políticas y jueces para agentes de juego
157 proyectos · Todos los proyectos →
Responde preguntas de elección, booleanas y de puntuación ordenada a partir de estados y candidatos, sin decodificar tokens de respuesta. Es un modelo local independiente inspirado en Jev; las grabaciones comparan Jev y Qwen sin ajustar con las mismas interfaces de juego.
El proyecto controla un jugador de Minecraft Java 1.16.5 mediante Mineflayer, separando el modelo planificador de la selección de acciones con Jev. Configura el relé de modelos y las rutas locales, instala dependencias, inicia el servidor vanilla y sigue el flujo documentado de nether-agent.
La colección ofrece habilidades para triaje de registros, comprobación de pruebas, evaluación por rúbrica y selección de acciones permitidas. Sigue la guía y elige Jev real mediante TypeSafe u OpenRouter, o una simulación del agente identificada expresamente.
TypeSafe Mario es un controlador NES experimental basado en telemetría del emulador y observaciones derivadas de RAM. Con Python 3.13, clave TypeSafe y juego local, inspecciona state-demo antes de ejecutar play.
JEV-inspired parallel decisions for CUDA LLMs. One context, many decisions. vLLM API, game-agent examples, and reproducible benchmarks.
A Clash Royale bot with no trained policy: Jev (TypeSafe System One) makes every decision from the live game state
2D autonomous car simulation in the browser, driven by TypeSafe's Jev decision model
Real-time drone swarm autonomy simulation using Jev for fast System 1 reflex decisions and collision avoidance, with optional System 2 reasoning for strategic guidance
No hay descripción disponible.
Python prototype that plays NES Super Mario Bros. from structured RAM observations, with Jev answering focused movement and jump questions.
Hermes Agent plans, Jev (TypeSafe) picks bounded actions, Mineflayer executes: Minecraft with no screenshots or keypresses from a model. Includes the reproduction of rmalde/minecraft-agent's Ender Dragon run.
Pokemon Red on PyBoy: code owns the route and the arithmetic, Jev picks at branches in about 100 ms, calibration measured instead of assumed
Chess where both players are TypeSafe's Jev model: every move is a typed Choice decision
Observable browser stealth game: Jev makes typed guard judgments while deterministic code owns the world.
Chrome dino game played by Typesafe AI Jev model
An F1 racing game where TypeSafe's Jev picks the racing line and the pedals, and learns each corner's limit between laps
Playing Pokemon Red using TypeSafe Jev
Benchmarks and a playground for TypeSafe's Jev (System One) model: chess, and who-is-the-player-talking-to for speech-to-text game NPCs
Browser driving game that captions dropped road images locally, then uses Jev Choice answers to drive the car while code owns physics and timing.
Jev, TypeSafe's System One model, plays chess against any OpenRouter LLM, Stockfish and you. One-page web app with live moves, Jev's move probabilities, saved games and win rates.
GPT teacher consults for DSH: stateless one-shot codex teachers behind a hard per-task consult budget, a read-only sandbox and a deterministic prefilter.
Chess against Jev, TypeSafe AI's System One model, through OpenRouter. Built with the pico framework.
A Minecraft survival bot that thinks with Jev — TypeSafe's System One AI model
AI life-and-civilization simulation: TypeSafe Jev makes every decision (typed, probabilistic, auditable); LLMs plan — OpenAI-compatible APIs, local models (Ollama, LM Studio), Claude Code, Codex.