AI tools for Game

StreamRender-H3 turns a code-controlled game world into a continuously generated visual experience. A code game engine maintains state and rules while a two-step streaming diffu

Matrix-Game 4.0 combines executable game logic with streaming neural rendering for playable interactive worlds. A game engine owns state and rules, a coding agent handles new in

PlayTrain turns single-file JavaScript games into environments for reinforcement learning. Researchers can use language models to generate or modify a game, play it in a browser

GLM-5.3-Flash is Z.ai multimodal model for coding, tool-driven agents, and professional work. It combines visual understanding with lower-cost inference, enabling agents to insp

MiniMax Music 3.0 is a music generation model that turns a creative concept and optional lyrics into a complete song. It composes, arranges, performs, and produces the result in

WorldClaw is an agentic 3D open-world generation project from Tencent Hunyuan. It explores how an AI agent can create, edit, and operate inside large interactive 3D environments

Evoke is a 14B, three-step, CFG-free autoregressive world model for persistent interactive world generation. It creates a world that can remember camera movement, respond to cha

Wonder is an interactive video world model for image- and video-conditioned world generation. It builds persistent environments that users can navigate with camera movement whil

Open-Dreamer is an open project from Next State about training a frontier-level world model. It provides a practical account of model design, training lessons, failures, fixes,

ARDY is an interactive human motion generation system from NVIDIA and ETH Zurich for producing realistic 3D motions in real time. The project targets applications such as game a

Fish Audio S2.1 Pro is a production-grade neural text-to-speech model available through the Fish Audio API with the model string s2.1-pro-free. It is designed for developers who

DreamX-World is a general-purpose interactive world model for creating diverse, high-fidelity worlds that can be explored, controlled, and transformed through actions and event

AnchorWorld is an embodied egocentric world-simulation framework with view-based evolution customization. It uses human-motion action control and pose-associated anchor views so

ReactiveGWM is a reactive game world model designed for steering non-player characters in generated game worlds with high-level strategies. It focuses on making this workflow mo

Gamma-World is a generative multi-agent world model designed for interactive simulation beyond two controllable players while preserving shared-world consistency. It focuses on

CubePart is an open-vocabulary part-controllable 3D generator designed for creating multi-part 3D mesh objects from text prompts and part schemas. It focuses on making this work

PhysForge is a framework for generating physics-grounded 3D assets for interactive virtual worlds and embodied AI environments. It addresses a limitation of many 3D generation s

Scenema Audio is an expressive audio generation model for zero-shot voice cloning, emotional speech, singing, and performance-driven speech synthesis. It is designed to generate

Dramabox is Resemble AI's expressive text-to-speech model with prompt-driven voice cloning and performance control. It is designed for generating acted speech where the prompt c

Articraft is an agentic system for generating articulated 3D assets that are structured for simulation and interaction. It targets objects with moving parts, such as ovens, draw