negotiation_agent provides a modular toolkit for building autonomous negotiation bots powered by GPT-like models. Developers can specify negotiation scenarios by defining items, preferences, and utility functions to model agent objectives. The framework includes pre-defined agent templates and allows integration of custom strategies, enabling offer generation, counteroffer evaluation, acceptance decisions, and deal closure. It manages dialogue flows using standardized protocols, supports batch simulations for tournament-style experiments, and calculates performance metrics such as agreement rate, utility gains, and fairness scores. The open architecture facilitates swapping underlying LLM backends and extending agent logic through plugins. With negotiation_agent, teams can quickly prototype and evaluate automated bargaining solutions in e-commerce, research, and educational settings.

TexasHoldemAgent provides a modular environment built on Python to train, evaluate, and deploy an AI-powered poker player for heads-up limit Texas Hold’em. It integrates a custom simulation engine with deep reinforcement learning algorithms, including DQN, for iterative policy improvement. Key capabilities include hand state encoding, action space definition (fold, call, raise), reward shaping, and real-time decision evaluation. Users can customize learning parameters, leverage CPU/GPU acceleration, monitor training progress, and load or save trained models. The framework supports batch simulation to test various strategies, generate performance metrics, and visualize win rates, empowering researchers, developers, and poker enthusiasts to experiment with AI-driven gameplay strategies.

Azul Game AI Agent is a specialized AI solution for the Azul board game competition. Implemented in Python, it models game state, applies Minimax search for deterministic pruning, and leverages Monte Carlo Tree Search to explore stochastic outcomes. The agent uses custom heuristics to evaluate board positions, prioritizing tile placement patterns that yield high points. It supports head-to-head tournament mode, batch simulations, and result logging for performance analysis. Users can tweak algorithm parameters, integrate with custom game environments, and visualize decision trees to understand move selection.