Game Ai Python Packages

rlcard

Reinforcement Learning / AI Bots in Card (Poker) Games - Blackjack, Leduc, Texas, DouDizhu, Mahjong, UNO.

bitbully

Fast perfect-play Connect Four (Connect-4) solver for Python and C++ with bitboards, opening books, and MTD(f) search

game-learning-runtime

Agent-first, learner-neutral runtime for interface-driven game training and evaluation.

gym-super-mario-bros

Gymnasium environments for NES Mario games, with task metadata, reward instrumentation, and reproducible evaluation interfaces.

simthinkd

A tiny decision model (265k parameters) that picks one action in about 2 ms on one CPU core, inside real-time loops.

py-draughts

Fastest Python draughts/checkers library — bitboards, 8 variants, alpha-beta engine, web UI. ~200x faster than pydraughts.

agentdeck-ai

The game console for AI agents — open execution, recording, and replay infrastructure for AI systems in game worlds.

hexbot

Python framework for building Hex Connect-6 AI bots. AlphaZero self-play, MCTS, neural networks, C game engine, live training dashboard. Home of the Orca bot.

ensoul

Official Ensoul SDKs for AI NPCs and living personas. Memory and personality that evolve through real conversation, scale to thousands, and run simulations over time. Python, TypeScript, Kotlin, Swift, Unity C#, C++, and Godot.

god-code

Godot-aware AI coding agent for original game development, with scene editing, validation, review, playtest, and MCP tools.

trimcts

High-performance C++ implementation of Monte Carlo Tree Search (MCTS) with Python bindings. Supports AlphaZero and MuZero paradigms, featuring batched network evaluation and efficient tree reuse.

misty-chess

An open-source fog-of-war (dark) chess engine: exact belief enumeration + GT-CFR search

openrl

Unified Reinforcement Learning Framework

reinfors

High-throughput reinforcement-learning search and sampling in Rust, with caller-owned Python networks and training

marionette-mc

A NeoForge bridge that lets any external agent see and control a rendered Minecraft client

douzero

[ICML 2021] DouZero: Mastering DouDizhu with Self-Play Deep Reinforcement Learning | 斗地主AI

chessplainer

Explain chess positions with SHAP: which pieces make Stockfish think a position is winning, drawn or lost.

boidswarm

Advanced Boids with Graph-Laplacian leader election, ripple-based signaling, and role-driven flock dynamics.

balancelab

Economy balance analysis and exploit detection for AI game agents

sovereign-engine

Procedural Game Engine powered by IntentShield and LogicShield

agentcrdt

CRDTs for distributed AI agent state and conflict-free belief merging

affect-kernel

Deterministic affect-state kernel for long-lived AI characters, with injected adapters

normsync

Norm monitoring and violation detection for AI agent actions

puissance4

AI for the game "Connect Four". Available on PyPI.