jev-plays-pokemon-red
PyBoy 游戏智能体,由代码处理路线和计算,Jev 在决策点选择操作。
PyBoy game agent where code handles routing and arithmetic and Jev selects among actions at decision points.
EXPLORE JEV
浏览游戏智能体、模拟环境和交互实验,观察结构化状态如何用于动作选择。
THE RESOURCE INDEX
项目、工具、教程与文章
原始链接,按用途整理。
支持中文与多关键词,例如:浏览器 DOM。
全部资源
PyBoy 游戏智能体,由代码处理路线和计算,Jev 在决策点选择操作。
PyBoy game agent where code handles routing and arithmetic and Jev selects among actions at decision points.
使用模拟器结构化状态的游戏智能体。
A TypeSafe/Jev agent that plays Super Mario Bros. from structured emulator state.
在 MuJoCo 中使用 Jev 的无人机模拟实验。
Camera-only autonomous drone in MuJoCo with a small judgment model (TypeSafe Jev) in the loop at 2.5Hz
Snake auto-played by TypeSafe's Jev model: one System One choice per tick, legal moves and facts generated in code
TypeSafe Jev controls original StarCraft shareware through keyboard and mouse with recorded action probabilities.
Python prototype that plays NES Super Mario Bros. from structured RAM observations, with Jev answering focused movement and jump questions.
Observable browser stealth game: Jev makes typed guard judgments while deterministic code owns the world.
A browser-native Doom agent experiment with structured spatial state, composable AI controls, live decision telemetry, and a Chocolate Doom WebAssembly runtime.
TypeSafe Jev plays original Civilization II in a browser, with live action probabilities. Experimental full-game harness.
A Next.js brick breaker whose paddle is controlled in real time by TypeSafe AI's Jev model. Built with Claude Code.
TypeSafe's Jev plays Atari Pong. One typed Choice question per frame, no coordinates sent to the model.
Cyber-Breach: The Jev Protocol - A tactical cyberpunk arena combat game powered by TypeSafe AI Jev System One decision model
A cyberpunk border encounter powered by TypeSafe Jev. Bluff the guard. Inspect the receipts.
USER + JEV: P(DOOM) PROTOCOL — co-op platform shooter where TypeSafe Jev plays alongside you
Minecraft mod where Jev tries to finish the game from scratch without a scripted route.
Jev plays browser table tennis in real time: structured telemetry, typed decisions, ordinary Chrome inputs, and auditable evidence.
3D chess powered by TypeSafe AI (Jev). AI vs AI by default, or play either side. Multiple difficulty levels.
100 AI NPCs live in a tiny town. Jev chooses the next action; the world writes the story.
Chess where both players are TypeSafe's Jev model: every move is a typed Choice decision
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.
Autonomous PlayStation 2 AI Agent with real-time visual telemetry HUD powered by TypeSafe Jev System One
Shady Town: social-deduction party game for the living room TV, moderated by TypeSafe Jev
A 3D planetary rover sandbox for experimenting with autonomous decisions using TypeSafe AI.
River shooter game in Python, inspired by Atari's River Raid, played by a TypeSafe AI pilot
A Minecraft Java player controlled by TypeSafe AI, with live decisions, Canadian flag building, and a side-by-side dashboard.
A sandbox where a TypeSafe System One model presses the controls of a small creature. Code runs the world.
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.
Interactive experiments from support routing to a 3D driving simulation: structured sensor state in, typed steer, brake, and overtake decisions out.
Village NPCs that judge you each tick, deciding what to do and how they feel, instead of chatting.
Krunker-style 1v1 FPS where Jev decides move, aim, ADS, fire, and jump at about 9 Hz.
Agent-first Haskell DSL for TypeSafe's Jev judgment model: typed packets, inferred types, answers under the same labels
Pi extension: verbatim context compaction with TypeSafe Jev decisions
Reversible context pruning for Pi, powered by TypeSafe Jev. Keep useful context without deleting session history.
Codex plugin: verbatim Jev-guided context restoration around session compaction. Port of tamaratran/fast-jev-compaction to Codex lifecycle hooks.
Community TypeSafe AI playground: 110 use cases, games, dilemmas and model challenges, with editable prompts, A/B comparisons and a mobile-friendly UI.
Runtime constraints for the pi coding agent: checks every side-effecting tool call against what you said, before it runs. Powered by TypeSafe Jev.
Verbatim context pruning for the pi coding agent, scored by TypeSafe Jev: stale tool calls and results are dropped or truncated, everything kept stays verbatim.
A VGI worker exposing TypeSafe System One questions (choice, noul, score) to DuckDB/SQL as LATERAL-joinable table functions
Options trading bot (backtest + Alpaca paper only) with TypeSafe Jev as the decision core
Jev-powered context compaction for Pi. Keep critical instructions and tool history, prune the noise, and fall back gracefully.
Sandbox & benchmark: optimize how you ask Jev (TypeSafe System One) to play falling-block puzzle games, head-to-head against LLMs
Real-vaxt taksi dispetçerlik simulyasiyası — TypeSafe JEV (System One) modeli ilə
Continuous, verbatim context compaction for LLM agents using TypeSafe's Jev model.
Experimental Pi extension using TypeSafe Jev for auditable tool-history compaction
Three.js robotaxi game where TypeSafe's Jev model makes the driving decisions
Jev-powered execution state for Pi coding agents. Track changes, checks, and blockers outside the main LLM, with evidence-backed updates and replay. Inspired by SKILL.state.
TypeSafe AI (Jev System One) plugin for OpenClaw - sub-100ms group triage, tool safety guardrails, compaction curation, and model routing
Three.js drone simulator with a Python backend and live TypeSafe Jev navigation
Natural-language PostgreSQL predicates with TypeSafe Jev. A simple search playground with randomly generated databases.
Latent reasoning for user-intent decomposition: does more continuous-space compute produce better goal extraction? With JEV (TypeSafe System One) as the calibrated decision layer.
Automatic Jev context clearing for Pi. Keep the conversation, prune stale tool output, retrieve originals without rerunning commands.
Cache-neutral context trimming for the pi coding agent, powered by TypeSafe Jev: long tool output cut to verbatim key lines before it enters context, with lossless recall. Measured, with pre-registered benchmarks.
试试项目英文名、相关用途,或重置筛选。
部分项目补充了中文用途说明,原始描述保留供对照。在 GitHub 阅读完整目录 ↗