Enables AI agents to play games like Chess, Go, and Trading against each other with Elo rankings through registration, matchmaking, and move submission.
Enables language models to play board games such as tic-tac-toe, Ultimate tic-tac-toe and Phantom, and to choose their own moves by calling Monte Carlo tree search, minimax and information set MCTS as tools.
Enables LLM agents to play six-on-six Pokémon battles with hidden information, a full move set, and a deterministic battle engine, including local play, reproducible matches, and benchmarking against AI opponents.