The mario-ai project offers a comprehensive pipeline for developing AI agents to master Super Mario Bros. using neuroevolution. By integrating a Python-based NEAT implementation with the OpenAI Gym SuperMario environment, it allows users to define custom fitness criteria, mutation rates, and network topologies. During training, the framework evaluates generations of neural networks, selects high-performing genomes, and provides real-time visualization of both gameplay and network evolution. Additionally, it supports saving and loading trained models, exporting champion genomes, and generating detailed performance logs. Researchers, educators, and hobbyists can extend the codebase to other game environments, experiment with evolutionary strategies, and benchmark AI learning progress across different levels.

My AskAI offers an AI agent designed to revolutionize customer support by automating responses and deflecting up to 75% of support requests. Integrated easily into existing live chat providers such as Intercom and Zendesk, it helps businesses improve efficiency and focus on more complex issues. The platform also supports educational purposes, allowing students to interact with material around the clock, providing insights into areas where they struggle.

AIpacman is an open-source Python project that simulates the Pac-Man game environment for AI experimentation. Users can choose from built-in agents or implement custom ones using search algorithms like DFS, BFS, A*, UCS; adversarial methods such as Minimax with Alpha-Beta pruning and Expectimax; or reinforcement learning techniques like Q-Learning. The framework provides configurable mazes, performance logging, visualization of agent decision-making, and a command-line interface for running matches and comparing scores. It is designed to facilitate educational lessons, research benchmarks, and hobbyist projects in AI and game development.

Vanilla Agents is a lightweight PyTorch-based framework that delivers modular and extensible implementations of core reinforcement learning agents. It supports algorithms like DQN, Double DQN, PPO, and A2C, with pluggable environment wrappers compatible with OpenAI Gym. Users can configure hyperparameters, log training metrics, save checkpoints, and visualize learning curves. The codebase is organized for clarity, making it ideal for research prototyping, educational use, and benchmarking new ideas in RL.