#game-ai
GitHub Topic「game-ai」がついているAI関連リポジトリの集計。Topicはリポジトリ作者が自己申告するメタタグで、AI関連の文脈で何が「game-ai」と分類されているかを可視化します。
REPOS #game-ai のRepo (TOP 18 / Stars降順)
Codex skill and Cities: Skylines 1 mod for API-driven AI city building
ihebjdey2/Machine-learning-agent-target-chaseUnity ML-Agents reinforcement learning experiment where an autonomous agent learns to chase a target and avoid obstacles.
BlackBearCC/vitricThe glass-box game engine for AI agents — every state visible, operable, and verifiable. AI builds, tests, and iterates games autonomously.
velle999/chiron-smacxChiron Rising — an Alpha Centauri (SMACX) mod pack: LLM-written faction diplomacy with leader memory, generated base names, Planetnet dispatches, probe protests, three new factions, and optional Future Society repricing. Built on Thinker.
raulEspaa/pax-agenticaGrand strategy game of Europe in 1500 used as an arena for AI rulers: a Gemini/LangGraph council, an ADK archivist with RAG and evals, playable in the browser.
Maddy824/RumourtownExplore a town of 36 people. Write a rumor, follow its journey, and build with local agent tools, deterministic replay and a dependency-free TypeScript belief engine.
111nathanlar/Agent-Worlds farjadhasnain/ollama-tictactoe-aiA C# console Tic-Tac-Toe game using Ollama and local LLMs for AI-driven NPC behaviour.
vladmaneata/AI-ApplicationsML and RL experiments in Python — spam classification, game AI, and reinforcement learning
rivendale/iocalc-agent-envSandbox protocol, adapters and MCP bridge that let people and AI agents play IOCALC
taoyun0303-star/AI-Animal-ChessPygame Animal Chess with Negamax, MCTS, RL agents, and an AI Thinking Panel.
Ziran-Ziran/gamescaling-agent-labIndependent GameScaling research: model training, multimodal observations, and low-latency game decisions; existing controller infrastructure.
hammadshakeelai/Candy-Crush-AISuperhuman Match-3 AI solving 23,355+ Candy Crush levels with 100% campaign mastery via 79.3M AlphaCandy Titan, AlphaZero beam search, and distributional RL.
ronakrajput8882/Flappy-Bird-DQNDeep Q-Network (DQN) agent trained to play Flappy Bird using PyTorch & Gymnasium — with experience replay, target network, and epsilon-greedy exploration.
HelloMInd-star/poker-egg-fullstack🌃 Texas Hold'em × MBTI Personality — Full-stack AI battle game with 16 unique decision-making opponents.
Otoru/geppettoStateless, deterministic Utility AI engine for game NPCs. Objects advertise what they offer; agents score them against current needs. Usable as a Go library or as a gRPC subprocess.
0mis/gpt6-astra-geometry-dashState-aware Geometry Dash experiment with a native bridge, Python controllers, and recording acknowledgements. Clubstep complete; other challenges unfinished.
daguix/tarot-botFour-player French Tarot with a Rust rules engine, self-play reinforcement learning agents, and a React interface
RELATED 他のTopicも見る · 全Topicランキング →
#claude-code
3,787#ai-agents
3,201#llm
2,090#mcp
1,866#claude
1,854#python
1,678#developer-tools
1,530#codex
1,376#ai
1,181集計対象: 各Repoの最新contentスナップショットの topics_json に小文字一致でマッチしたもの。 算出方法