Coding agents & developer tools

Game development agents

984 agents · most starred first

Game development agents, page 2 of 10

craftium★ 215

A framework for creating rich, 3D, Minecraft-like single and multi-agent environments for AI research. (Accepted at ICML 2025).

SnakeAI★ 211
minecraft-agent-skills★ 210

Minecraft AI agent skills and dual-target plugin bundle for Codex and Claude Code.

quark_drive_skills★ 202

Quark Drive Skills: Pokemon Champions Agent Skills for dex and metagame facts, exact battle calculations, and audited team building. Companion interface: Quark Drive Web.

pokemon-agent★ 199

AI-powered Pokemon gameplay agent with headless emulation, REST API, and live dashboard. Works with any LLM.

stardew-together★ 196

同行 · Together — 面向自主经营、任务与全成就推进的 Stardew Valley AI Agent。原生工具、持续计划、游戏记忆与玩家辅助。

gd-agentic-skills★ 193

The official "Long-Term Memory" for Godot 4.5+ AI Agents. A high-density library of 95+ expert skills and 27 genre blueprints, providing audited, strictly typed GDScript patterns, automated persona orchestration (Analyst, Auditor, Builder), and production-grade game engineering.

blender-game-skills★ 191

Claude Code agent skills for game dev in Blender. Turn concept art into rigged, game-ready 3D assets, measured against your references.

csbrasil★ 189

FPS satírico de navegador: 5 facções brasileiras caricatas, 44 personagens, 5 mapas e 26 armas — rounds e Capture the Flag contra bots, direto na aba, sem instalar nada. Three.js + vanilla JS, zero build. Gerado em par com agentes de IA (Claude, Kimi, Codex/GPT, GLM) — AI generated & AI friendly.

VillagerAgent-Minecraft-multiagent-framework★ 187

(VillagerAgent ACL 2024) A Graph based Minecraft multi agents framework

Unity_ML_Agents★ 180

This is the code for "Unity AI" by Siraj Raval on Youtube

effekseer-vfx-skill★ 178

Agent skills that make real-time game VFX: procedural Effekseer effects, video-model flipbooks, or both, played in Godot and Unity (Claude Code, Codex and other Agent Skills hosts).

ygo-agent★ 177

AI-driven Yu-Gi-Oh! bot using deep reinforcement learning and LLMs

goldeneye-pc-port★ 175

A native PC port of GoldenEye 007 (N64) and a testbed for multi-agent AI porting a large decompiled C codebase.

RSIGame★ 175

RSIGame: Autonomous agentic game development with recursive self-improvement

CivAgent★ 168

CivAgent is an LLM-based Human-like Agent acting as a Digital Player within the Strategy Game Unciv.

coplay-unity-plugin★ 167

Unity plugin for Coplay

ritmo★ 167

The all-in-one toolkit for agent-first game development: ECS, assets, effects, sounds, music and more 🎮

LLM-PySC2★ 166

LLM-PySC2 is NKAI Decision Team and NUDT Decision Team's Python component of the StarCraft II LLM Decision Environment. It exposes Deepmind's PySC2 Learning Environment API as a Python LLM Environment.

BuilderGPT★ 164

A generative Minecraft structure tool for the Cynia Agents framework.

OpenRA-RL★ 164

Open Framework for AI Agents to play Red Alert through Reinforcement Learning

chess★ 163

耗时多年自研高性能golang棋牌AI智能平台,基于最新主流大模型LLM+多agent协同。严禁赌博,否则后果自负!!!

GPA-LM★ 161

This repo is a live list of papers on game playing and large multimodality model - "A Survey on Game Playing Agents and Large Models: Methods, Applications, and Challenges".

openai-autogen-dev-studio★ 161

OADS: Generate games and programs using OpenAI agents. Built on top of Microsoft Autogen.

agi-game-live★ 148

A React-based virtual avatar component for real-time gameplay analysis and emotional support. Integrate with screen capture to provide insights and companionship through advanced LLM integration.

LGUI★ 145

Game UI framework for AI agents, made by LumioGames. Build screens, logic and tests in the browser with no game engine, then export to Unity. 给 AI Agent 用的游戏 UI 框架,不依赖游戏引擎。

zephyr3d★ 143

TypeScript 3D rendering engine for the browser - one codebase targeting WebGL, WebGL2 and WebGPU, with a visual editor and node-graph materials

UniGPT★ 142

在Unity编辑器中使用ChatGPT、BingChat、GoogleBard来生成并执行代码。(Use ChatGPT, BingChat and GoogleBard to generate and execute code within the Unity editor.)

godot-agent★ 142

A lightweight Godot framework + agent skills for building and shipping games

mc_aiplayer★ 141

Autonomous AI agent that plays Minecraft on its own — a server-side Fabric mod (MC 1.21.3) where a DeepSeek / OpenAI-compatible LLM drives a real player to mine, build, farm, fight and survive from natural-language commands. LLM plans, deterministic tasks execute — no Python harness, no bot account.

awesome-ai-built-games★ 141

A curated list of vibe-coded games: playable games built with AI coding agents like Claude Code, Cursor, Codex, Gemini and Grok, with Three.js, Phaser, Godot and more.

Landing-Starships★ 138

Make autonomous landing rockets using Deep Reinforcement Learning (Unity ML-Agents)

MC-AI-Coding-Assistant-Tool★ 138

让 AI 编程助手(Cursor / Claude Code 等)能更好地编写 Minecraft 模组的完整工具包。

Afk-Bot★ 135

Funcional minecraft AFK bot for servers. Anti-AFK, Auto-Auth, Microsoft/Offline accounts support.

reality-engine★ 132

Top Dynamic AI World Simulation & Storytelling Tools 2026

UnrealClientProtocol★ 131

Lightweight UE5 plugin that exposes Unreal Engine's reflection system over TCP+JSON — let AI agents call UFunctions, read/write UProperties, and inspect any UObject in a running editor, zero engine modification required.

agent-office-3d★ 129

A low-poly 3D office that shows your AI coding agents' live status — idle agents sneak off to play Minecraft (no tokens used).

bomberland★ 128

Bomberland: a multi-agent AI competition based on Bomberman. This repository contains both starter / hello world kits + the engine source code

world-forge-ai★ 124

AI World Generator 2026: Create Self-Evolving Maps & Stories

roblox-skills★ 123

Open source list of roblox skills for AI agents

minecraft-openai★ 122

Controlling a Minecraft NPC using OpenAI 🤖

LLMGameHub★ 120

gradio agent-demo-track region:us

ML-Agents-SoccerTwos★ 114

static region:us

MineLand★ 113

Simulating Large-Scale Multi-Agent Interactions with Limited Multimodal Senses and Physical Needs

everything-game-dev-code★ 111

A universal scaffold for AI-assisted game development. 42 agents, 51 commands, 86 skills. Multi-engine (Unity, Unreal, Godot, HTML). Multi-harness (Claude Code, Codex, Cursor, OpenCode, Kiro).

godot-framework★ 109

A lightweight Godot framework + agent skills for building and shipping games

openclaw-unity-plugin★ 107

55 MCP tools to drive the Unity Editor from any MCP-compatible AI agent — scenes, GameObjects, prefabs, assets, tests, and builds. OpenClaw gateway included for remote and chat access.

agentcraft★ 103

AI Agent Simulation generates Minecraft Settlements

AIConnectors★ 102

Unity C# API connections to StableDiffusion (Automatic1111, Stability.ai SDXL, Replicate.com), Dall-E, ChatGPT/ GPT-4, and possibly others in the future.

poke.AI★ 101

A pre-LLM agent that plays the 3rd gen Pokemon games

FFramework★ 101

Unity + AI 解决Agent可靠性与可持续性,GameFramework + HybridCLR + YooAsset 开发的塔防游戏

Schola★ 101

Schola is a plugin for enabling Reinforcement Learning (RL) in Unreal Engine. It provides tools to help developers create environments, define agents, and connect to python-based RL frameworks such as OpenAI Gym, RLlib or Stable Baselines 3 for training agents with RL.

atari-agents★ 100

Code and links for over 25,000 trained Atari agents

hyperforge★ 100

MMORPG for humans and agents. In development. Powered by ElizaOS

ai-forge-mcp★ 100

565 AI-callable tools across 16 MCP servers. Full-pipeline AAA game asset production. Controls Blender, Substance Suite, Maya, Houdini, and Unreal Engine 5. 50 specialized AI agents. One prompt in, game-ready asset out.

OpenCodeGameStudios★ 100

Agentic game development taken to the next level: plan, build and test across major engines with any coding agent🤖

Maicraft★ 100

麦麦玩MC的AGENT项目

Spatial_AI_NPC★ 100

Multimodal embodied AI NPC system with spatial perception, voice, LLM agent, relationship memory, emotion, and Unity/VRM integration.

ultimate-volleyball★ 99

3D RL Volleyball environment built on Unity ML-Agents

vibecraft★ 99

AI-driven vibe based Minecraft building via MCP. Describe a build, watch your agent construct it in Minecraft.

AlphaAgent★ 99

为Godot引擎编辑器开发的Ai Agent插件

rpg-maker-agent★ 99

给 AI 一篇文章,自动生成一款可以玩的 RPG Maker MZ 游戏

OpenAI-GYM-CarRacing-DQN★ 98

Train a DQN Agent to play CarRacing 2d using TensorFlow and Keras.

game-dev-skills★ 98

My personal agent skill repository, primarily focused on game development.

Duo-Cai-You-Xi★ 97
mod-llm-chatter★ 97

AI-powered bot conversations for AzerothCore WotLK 3.3.5a - for mod-playerbots

Pacman-Game★ 96

In this project, the Pacman agent will find paths through his maze world, both to reach a particular location and to collect food efficiently. I implemented general search algorithms such as depth-first, breadth-first, uniform cost, and A* search algorithms which are used to solve navigation problems in the Pacman world.

defold-agent-config★ 96

An example configuration of AGENTS.md and a set of skills for AI-assisted game development with the https://defold.com engine.

ARC3-solution★ 96

My submission to the ARC-AGI-3 Developer Preview Agent Compitition.

kit-usd-agents★ 96

The base repository to build OmniverseKit USD agents.

summer★ 96

The game engine built for AI. Includes MCP server, CLI and skills that let any agent build, test, publish, and grow full games with Summer Engine.

roblox-dev-skill★ 96

An agent skill that turns AI coding assistants into Roblox development experts: Luau, engine APIs, architecture, anti-exploit security, and how to drive Studio's built-in MCP server safely. Version-stamped against a specific Studio/Luau release. Works with Claude Code, Antigravity, Codex, and any Skills-format assistant.

create-retro-game-kr-patch★ 96

레트로 게임 한글 패치 제작 전 파이프라인 에이전트 스킬 · Agent skill for end-to-end Korean (Hangul) fan-translation patches for retro games

rl-bot-football★ 95

An RL agent for the Google Football environment

godot_rl_agents_examples★ 95

Example Environments for the Godot RL Agents library

agent-wow★ 95

AzerothCore WoW client designed for autonomous AI agent players.

act-combat-design★ 94

二次元 / 动作游戏(ACT)战斗设计方法论 + 行业知识库,任意 AI agent(Claude、GPT、Cursor…)可用。设计玩家角色与 Boss → 审阅级 HTML + 落地资源表;招式集 / 视觉预警 / 配队等战斗约定由你的项目自定义,绝不强加。

game-client-to-server-reverse★ 94

从游戏客户端反推服务端协议并复现可部署服务端 (Agent Skill)。Unity/UE/Cocos, IL2CPP/Lua/JS…

dqn-atari★ 93

A TensorFlow based implementation of the DeepMind Atari playing "Deep Q Learning" agent that works reasonably well

NeuroMinecraftGenesis-NMG-★ 93

NeuroMinecraftGenesis (NMG): A revolutionary AI system that draws on the DiscoRL self-evolving algorithm, six-dimensional cognitive engine, and quantum-classical brain computing developed by DeepMind. It features multi-agent evolution, three-world integration, and AI toolkit capabilities.

fable-cities★ 93

A Cities: Skylines-class city builder running in the browser, built in Three.js by AI agents. Code ships when it's finished.

unity_ml_agents_course★ 92

Learn to create agents in Unity ML using Deep Reinforcement Learning with Tensorflow.

dino-reinforcement-learning★ 92

Evolutionary Reinforcement Learning for Dino Game: Train an AI agent to master Google Chrome's Dino Game using a genetic algorithm and reinforcement learning.

slitherin★ 91

AI research environment for the game of Snake 🐍 .

LiveDevAgents★ 91

Multi-Agent danmaku game engine. 2024.12 CAMEL-AI Hackathon 一等奖项目.

snake★ 91

Snake playing agents

generals-bots★ 91

Develop your agent for generals.io!

UnrealMLAgents★ 91

The Unreal ML Agents Toolkit is an open-source project that enables Unreal Engine games and simulations to serve as environments for training intelligent agents using deep reinforcement learning. This project is a port of Unity ML-Agents, adapted to work within Unreal Engine.

frida-game-hacking-mcp★ 91

A MCP implementation of Frida that seeks to emulate Cheat Engine functionally to allow for seamless Game Hacking by AI agents

OpenWar3AI★ 91

为 AI 打造的《魔兽争霸 III》1.27 开放接口:用任何语言写 AI · An open API for Warcraft III 1.27, built for AI agents — write bots in any language

MahjongMaster_AI★ 90

雀魂游戏实时 AI 指导 / Majsoul-AI-Assistant-MahjongMaster / MajsouI copilot / 雀魂助手 / 雀魂教练 / 雀魂AI分析

arc-skill★ 90

An agent skill that plays ARC-AGI-3. One rule: say what an action will do before you spend it. Claude Code on Opus 5 finished all 25 public games at 100.00 RHAE in 7,645 actions.

Unity_ML_Agents_2.0★ 89

Repository for implementing Unity ML-Agents 2.0

valo-strategic-tracker★ 89

Best Valorant Agent Overlay & Utility Mods 2026 | Pro Settings Optimizer

DegentCivil★ 88

A new AI Game Paradigm in Autonomous world. it includes configurations for agents, functional buildings, and equipment, as well as the logic for agents daily behavior and interactions with buildings, equipments...etc.

pirateAI★ 88

Pirate trainer (Deep Learning, Autonomous Agents, 3D, Unity, Hyperopt, Keras)

mj-unity-tutorial★ 88

Introductory set of tutorials for using the Unity plugin of MuJoCo with the ML-Agents framework.

Unity_ML_Agents★ 86

Unity ML-agents Project Repository of RLKorea

gpt-play-pokemon-firered★ 86

An autonomous AI agent that plays Pokemon FireRed in real time using OpenAI's LLM, with a live web dashboard for monitoring.

LittleJS-AI★ 86

AI-assisted toolkit for making HTML5 games with LittleJS: the engine, templates, and agent instructions that work with Claude Code, Codex, Cursor and Copilot, so the AI builds your game instead of rebuilding an engine. Installable as a Claude Code plugin.

More in Coding agents & developer tools