Summary

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 rather than producing isolated assets only.

Key Features

Agentic 3D open-world generation.
Language-driven world construction.
Interactive scene editing.
3D asset and environment creation.
Spatial reasoning for agents.
Executable world environments.
Large-scale world generation research.
Public Tencent Hunyuan project resources.

About WorldClaw


The system connects language-driven planning with 3D world construction and interaction. Its research direction combines scene generation, asset creation, spatial reasoning, and agent control so that a world can be built at scale and then used as an executable environment.


WorldClaw is useful for game prototyping, embodied-agent research, simulation, virtual production, and procedural world design. The linked project page is accompanied by a public GitHub repository and research paper for developers who want to study or extend the approach.

Get more likes & reach the top of search results by adding this button on your site!

Embed button preview - Light theme
Embed button preview - Dark theme
TurboType Banner

Subscribe to the AI Search Newsletter

Get top updates in AI to your inbox every weekend. It's free!