gaming-ai

PixelVisionAI is an embodied AI system that learns to play games using screen pixels and OS-level input only. No game APIs, no memory access, no cheats — just vision, decision-making, and interaction, like a human player.

• Updated Feb 7, 2026
• Python

An advanced AI co-pilot and strategy automation engine for Slay the Spire. It utilizes out-of-core streaming pipelines and act-specialized multi-class LightGBM ensembles to calculate and recommend optimal card selections or explicit skips in real-time.

• Updated Jul 2, 2026
• Python

A high-performance AI assistant for real-time gameplay analysis. Features tactical strategy suggestions, skill-gap detection, and personalized training loops to level up your rank.

• Updated Jun 24, 2026

A python library that provides a simulation environment for the traditional Nepali board game "Baghchal" using Gymnasium

• Updated Jul 23, 2025
• Python

End-to-end YOLO11 computer vision for Arena Breakout: high-speed Windows capture, AI-assisted annotation, dataset QA, training, evaluation, and real-time inference.

• Updated Aug 5, 2026
• Python

Reference architecture for multimodal gaming AI using NVIDIA Triton Inference Server and Kubernetes

• Updated Mar 4, 2026
• Python

A reinforcement learning project featuring an intelligent agent trained to navigate and complete levels in Super Mario Bros. using deep Q-learning and computer vision techniques.

• Updated Dec 13, 2025
• Python

This repository provides an AI-powered player engagement system with personalized recommendations, in-game rewards, and generative content for gaming scenarios.

• Updated Jan 28, 2025
• Python

Machine learning agent and coaching system for Super Auto Pets using reinforcement learning and computer vision

• Updated May 21, 2025
• Python

Gameplay-Review-AI — A high-performance analytical tool using AI to evaluate gaming sessions. Provides data-driven insights on mechanics, strategy, and performance to help players optimize skills.

• Updated Jun 24, 2026