GameGen-O is the first diffusion transformation model customized for generating open-world video games. By simulating various features of game engines, such as innovative characters, dynamic environments, complex actions, and diverse events, it enables high-quality, open-domain generation. Additionally, it offers interactive controllability, which allows for gameplay simulation. The development of GameGen-O involved extensive data collection and processing from the ground up, including the construction of the first open-world video game dataset (OGameData) and efficient sorting, scoring, filtering, and decoupling of titles through a proprietary data pipeline. This robust and comprehensive OGameData serves as the foundation for the model training process.

POKéLLMON is the first LLM-based agent to achieve human-level performance in a tactical combat game. It leverages three key strategies: 1) Contextual reinforcement learning, which uses text-based feedback from battles to iteratively optimize its generation strategy; 2) Knowledge-enhanced generation, which utilizes external knowledge to combat hallucinations and enable the agent to act accurately and timely; 3) Self-consistent action generation, which mitigates panicking switching behavior when facing strong opponents and avoiding combat. Battles against human players demonstrate POKéLLMON's human-level fighting ability and strategy, achieving a 49% win rate in tournament matches and a 56% win rate in invitational matches. Furthermore, it reveals vulnerabilities in human players' exhaustion strategies and deceptive tactics.

AI Town is a virtual town where AI characters live, chat, and socialize. It's a deployable starter kit that can be easily used to build and customize your own version of AI Town. It features a powerful backend engine that supports shared global state, transactions, and recording of all events, suitable for projects ranging from simple to scalable multiplayer games. It also provides a JS/TS framework for customization and extension.

GameGen-O is the first diffusion transformation model customized for generating open-world video games. By simulating various features of game engines, such as innovative characters, dynamic environments, complex actions, and diverse events, it enables high-quality, open-domain generation. Additionally, it offers interactive controllability, which allows for gameplay simulation. The development of GameGen-O involved extensive data collection and processing from the ground up, including the construction of the first open-world video game dataset (OGameData) and efficient sorting, scoring, filtering, and decoupling of titles through a proprietary data pipeline. This robust and comprehensive OGameData serves as the foundation for the model training process.

POKéLLMON is the first LLM-based agent to achieve human-level performance in a tactical combat game. It leverages three key strategies: 1) Contextual reinforcement learning, which uses text-based feedback from battles to iteratively optimize its generation strategy; 2) Knowledge-enhanced generation, which utilizes external knowledge to combat hallucinations and enable the agent to act accurately and timely; 3) Self-consistent action generation, which mitigates panicking switching behavior when facing strong opponents and avoiding combat. Battles against human players demonstrate POKéLLMON's human-level fighting ability and strategy, achieving a 49% win rate in tournament matches and a 56% win rate in invitational matches. Furthermore, it reveals vulnerabilities in human players' exhaustion strategies and deceptive tactics.

IndieHackers RPG is a personal weekend project that combines the charm of classic RPGs with the innovation of AI-driven dialogue. It is both a tribute to the RPGs I have played in the past and a humorous commentary on the indie hacker community.

ChatDev is an advanced AI game NPC research platform that supports complex NPC interaction operations through multiple large model interfaces. It generates visual effects in games through a custom prompt flow. You can explore the chat capabilities of multiple large models, create custom workflows to generate impressive game demos and results. Whether you want to engage in deep conversations with AI or quickly generate compelling content, we offer a rich set of features.

AI Town is a virtual town where AI characters live, chat, and socialize. It's a deployable starter kit that can be easily used to build and customize your own version of AI Town. It features a powerful backend engine that supports shared global state, transactions, and recording of all events, suitable for projects ranging from simple to scalable multiplayer games. It also provides a JS/TS framework for customization and extension.

The AI Tour Guide is an experimental AI tour guide plugin powered by IGN Guide. It can answer questions about "The Legend of Zelda: Tears of the Kingdom" and provide expert-level guide information to help you on your adventure in Hyrule. The AI Tour Guide is feature-rich, accurate, and affordable. Whether you're a newcomer or a seasoned player, the AI Tour Guide can provide comprehensive in-game guidance.

AI Roguelite is the world's first RPG where all entities are generated by AI and all game mechanics are guided by AI. Through AI technology, game elements such as characters, items, and maps will be generated in novel ways, providing players with unique and innovative gameplay experiences. This game is positioned as a revolutionary RPG, aiming to explore the application of AI in the gaming domain.

Ludo.ai is your game research and design assistant, helping you boost your productivity 10x through a single platform, providing you with all the resources you need to design your next hit game.