Coding agents & developer tools
Game development agents
984 agents · most starred first
Game development agents, page 3 of 10
AI4U is a plugin that allows you use the Godot Game Engine to specify agents with reinforcement learning. Non-Player Characters (NPCs) of games can be designed using ready-made components.
Let AI agents see and control Unity Editor through plain files. 25 commands, lens system, screenshots, texture catalog.
chasm — a local-first, game-agnostic AI backend for agentic NPCs. Connect any game with a mod (or build one on it); chasm provides the LLM, cloned voices, memory, and in-world actions.
Describe a factory in one line. Claude builds it as a live 3D simulation you can run. Open source agent skill: real discrete event simulation, tilt-shift miniature.
AI Play Minecraft
Automated Hyperparameter Search for Unity ML-Agents
A Settlers of Catan framework built in Python with AI agents
Disk images (intended for emulators) containing code and tools for building Soft Dorothy Software games. Primarily vintage Pascal and C calling the vintage Macintosh Toolbox.
Codex-native CLI for AI-assisted game development, scaffolding local projects with studio roles, bounded prompts, and hard-failing validation.
Generate materials from text prompts in Unity
This is a repo for studying the application of LLM Agents on Games
Active Ragdoll Training with Unity ML-Agents
Roblox game boilerplate for AI agents: Rojo, Wally, typed Packet networking, ProfileStore data, strict Luau and an AGENTS.md
Embodied AI companion for Minecraft — persistent memory, vision, learning, multi-agent. Built on Hermes Agent.
Best Open-Source Roblox Studio AI Workflow for Claude Code 2026
更新、移植、提取碧蓝档案/蔚蓝档案mod的工具 | Updating&Porting&Extracting Mods for Blue Archive | Steam&Android
Let Your AI Play Detroit:Become Human
RobloxForge Docs 2026: Official MCP Vertical Slice Verification Layer for Studio
Nature of Code - Autonomous Agents examples in 3D
Byte Arena: Digital Playground for Intelligent Agents (star the repo to vote for us)
Virtual human (avatar and agent) procedural animation toolkit for Unity. https://www.youtube.com/watch?v=mstLuzTw790
Roblox Luau AI Agent Standards and Static Checker Toolkit 2026
Real-Time Synchronized AI Agentic Assistant for Roblox Studio Automation and Scripting 2026
Code accompanying the paper "TiZero: Mastering Multi-Agent Football with Curriculum Learning and Self-Play" (AAMAS 2023) 足球游戏智能体
Build, inspect, test, and debug Godot games from your terminal. Automate repetitive work with scripts, or let an agent use the same commands. No agent, model, or AI account is required. MCP is an optional interface.
Autonomous LLM-driven Among Us simulation with memory, social reasoning, pathfinding, sabotage, emergent behavior, and real-time React/PixiJS visualization.
AI Agent for Chinese Chess - CS 221 Project
Game Codebase Analysis AI Agentic Tool
LLM-agnostic tabletop RPG Game Master framework. Runs on OpenCode, LM Studio, or any LLM service. D&D 5e included as reference system — add any TTRPG via a system module.
This project implements a supervised deep learning system that learns to autonomously control a vehicle in the Countryside level of Hill Climb Racing. Using computer vision and a convolutional neural network (CNN), the model observes raw gameplay frames and predicts the correct driving action in real time — mimicking human input.
A kart racing game in the browser with zero art assets — every texture, mesh, material and sound is generated in code. Built by a fleet of Claude agents in four days.
Best Open-Source AI Roblox Studio Copilot 2026: Chat-Driven Script Editing & Luau Automation
Connect Luau Games to 100+ DataGrout Logic Cells and Batteries 2026
An autonomous multi-agent IDE for screenplays🎮 & novels📖. One-click to share web performances or drive Unity dialogue systems. Empowering vibe game dev with AI!
An LLM that plays RimWorld and rewrites its own playbook between colonies. RimBridge mod + self-improving agent.
AI-Powered Roblox Luau Code Execution Server for Live Game Testing 2026
BloxAgent 2026: AI-Powered Luau Reverse Engineering and Roblox Script Automation Framework
Using tensorflow, this agent can autonomously train itself to play Out Run and potentially be modified to play other games or perform tasks other than gaming
🎮 Tencent Game-Creation-Agents (GCA) is an end-to-end pipeline that turns a natural-language idea into a playable, verified browser game.
An open-source command-line tool for developing Unity games with Claude Code
Native C++ AI assistant module for the Godot 4.7 editor - multi-provider LLM chat, GDScript code generation & execution, scene-aware context, on-demand API docs and gotchas injection
An autonomous multi-agent IDE for screenplays🎮 & novels📖. One-click to share web performances or drive Unity dialogue systems. Empowering vibe game dev with AI!
Hierarchical Expert Prompt for Large-Language-Models: An Approch Defeat Elite AI in TextStarCraft-II for the First Time
34 Claude Code AI skills for Roblox game development: ideas, Luau architecture, gameplay systems, UX, economy, monetization, security, QA, publishing, and live ops.
A Complete Open Source Agent AI Framework For Unity
Idea-to-store autonomous harness for Flutter/Flame games across Claude Code, Antigravity, and Codex. Automates research, planning, design, generator-evaluator loops, AdMob, and store submission.
MIT-licensed TypeScript runtime for AI-native game characters and worlds, with durable state, reliable actions, memory, tools, and Unity, Godot, and Unreal Engine integrations.
一个在Unity中实现的生成式人工智能代理规划框架。A planning framework for generative artificial intelligence agents implemented in Unity.
SketchUp meets AI Agents
DSH (DeepSeek Harness) plugin that launches and drives a running Godot 4.x game through its in-game TCP interaction server — replaces the godot-mcp MCP server with native agent tools.
GoAgent · 围棋智能体: AI-editor-style KataGo + multimodal LLM desktop Go agent
Godot automation for AI agents to build and verify projects through a CLI, Agent Skill, or MCP server, with structured results, headless operations, and live runtime control.
The game engine for AI agents. Give your AI superpowers for game dev + A skills framework that just works + easy install and setup ☀️
AI Assistant for Godot
A curated list of tools, models, research, and resources for generating games with AI
LLM-based autonomous world
An AI benchmark for Pokémon VGC with agent implementations using multi-agent reinforcement learning, behavior cloning, LLMs, and heuristics
An Agent-Based Modelling (ABM) Framework for Unity3D
Claude Code, natively inside Unity Editor. A dockable chat window with full project awareness, 60+ MCP tools, and zero alt-tabbing.
Open-Ended Long-Horizon Text Game Generation for Test-Time Continual Learning Agents
🎮 34 production-grade Claude Code skills for indie game development — studio agents, workflow skills, engine specialists, genre packs, and CI validation. From concept to launch.
Arcade kart racer in the spirit of Mario Kart, built entirely with Three.js. 100% procedural assets, no build step. Built by five Claude Opus 5.5 sub-agents from one prompt.
Top Elden Ring Gameplay Enhancement Suite 2026: ESP & No Recoil
AI assistant for trading in Old School Runescape.
static region:us
Agent-ready toolkit for isometric games: ComfyUI art pipelines, seamless terrain, sprites, grid math, Canvas2D rendering, pathfinding, and asset automation.
A reinforcement learning environment for PCB autorouting, built on KiCad's push-and-shove router. Includes a decoder-only PPO/GRPO agent, LLM tool-calling and rule-based baselines, and a uniform 3-stage evaluation pipeline. The routing engine ships separately as the PCBWorld-Engine submodule (GPLv3).
A reinforcement learning agent for tic-tac-toe. Implements the example from Chapter 1 of Sutton and Barto.
Unity project showcasing A* pathfinding, fully jobified & burst compiled. It also contains examples of RaycastCommand and BoxcastCommand that are used to build the grid, as well as another example of the usage of IJobParallelForTransform, used to move the agents.
A Reinforcement Learning agent for Clash Royale created using Proximal Policy Optimization
This repository contains a Godot skill for Codex-compatible & ClaudeCode-compatible agents, providing workflows and bundled scripts for inspecting, editing, running, and debugging Godot projects.
Give your AI coding agent a Roblox brain. Skill collection for Roblox Studio game development.
Frontier ARC-AGI-3 agent: 99.86% RHAE, all 183 levels solved for $654
The package manager for Minecraft servers.
Game development plugin for Hermes Agent: sound effects, music, NPC voices, pixel art, 3D models, Godot/Unity/Blender/Unreal, a playtester that actually plays the build, and one-click export.
Towards Generalist Game Agents: A Survey of Foundation Models in Virtual Worlds
007 Agent Under Fire recomp from Xbox to PC Port.
A tutorial showing how to train RL agents for webgames, in this case, Chrome Dino
Train reinforcement learning agent using ML-Agents with Google Colab.
LLM integration into Crusader Kings 3
A library for Hnefatafl (Viking Chess, or Tafl) that is used for move generation/validation, piece placement/movement, and game over detection. You can use it to simulate games between AI agents - although you need to write the agents yourself :)
适用于 AI Agent 全自动为 Minecraft 服务器插件、mod自动化测试
Bridge connecting Hermes Agent to Miniverse pixel worlds
0 config AI agent skill for Unity — AI-driven unity control, automate workflow. For UnityEditor/UnityPlayer
RL agent for Slay the Spire 2 — headless simulator + trained model + real game bridge
Agent-run decompilation: per-CPU translators write C, an emulator-backed judge proves each function behaves exactly like the original, and a port kit builds native games. Dreamcast, Saturn, GameCube, Xbox 360.
基于OPENAI辅助UE开发,接入openai-api,使用DALL.E自动生成模型,Chat-GPT自动设计蓝图.
NAIL is an agent that plays text-based interactive fiction games.
AI-driven peds for GTA V/FiveM using GPT, enhancing gameplay with realistic, engaging autonomous agents on .NET.
A customizable MCTS planner with advanced featured tailored to multi-agent simulations and emergent narratives.
Local-first, AI-assisted circuit design tool. Wire components in a 3D view, describe what you want to build, and the AI agent writes the firmware and simulates it all before you touch a chip.
Repo for Paper "OpenHA: A Series of Open-Source Hierarchical Agentic Models in Minecraft"
A plugin for DeepSeek Harness, allowing your agent to play in Minecraft Java Edition servers.
The game snake (for playing by yourself run snake_env.py). Deep Reinforcement Learning agent learns to play the game (run agent_1.py)..
Train a reinforcement learning agent to play a variation of Pong®
A lightweight node.js framework to facilitate writing agents (or 'bots') for Starcraft II in JavaScript.
AI-first Unity 6.2+ game development workflow — rules, agents, skills, and slash commands for Claude Code and Antigravity
Arcade kart racer in the spirit of Mario Kart, built entirely with Three.js. 100% procedural assets. Built by five Claude Fable 5.1 sub-agents from one prompt.