Politiche e giudici per agenti di gioco
157 progetti · Tutti i progetti →
Risponde a domande di scelta, booleane e con punteggi ordinati da stati e candidati, senza decodificare token di risposta. È un modello locale distinto ispirato a Jev; le registrazioni confrontano Jev e Qwen non adattato sulle stesse interfacce di gioco.
Il progetto controlla un giocatore di Minecraft Java 1.16.5 tramite Mineflayer, separando il modello di pianificazione dalla scelta delle azioni con Jev. Configura il relay dei modelli e i percorsi locali, installa le dipendenze, avvia il server vanilla e segui il flusso nether-agent documentato.
La raccolta offre competenze per smistare record, verificare prove, valutare secondo criteri e scegliere azioni consentite. Segui la guida e scegli Jev reale tramite TypeSafe o OpenRouter, oppure una simulazione dell’agente esplicitamente segnalata.
TypeSafe Mario è un controller NES sperimentale che usa telemetria dell’emulatore e osservazioni ricavate dalla RAM. Con Python 3.13, chiave TypeSafe e gioco locale, controlla state-demo prima di eseguire 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
Descrizione del progetto non disponibile.
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.