# Tencent-Hunyuan/Hunyuan3D-WorldClaw

WorldClaw: Agentic 3D Open-world Generation at Scale

Repository: https://github.com/Tencent-Hunyuan/Hunyuan3D-WorldClaw
Canonical: https://ross.abutalabs.com/products/hunyuan3d-worldclaw
Homepage: https://tencent-hunyuan.github.io/Hunyuan3D-WorldClaw/
License Family: other
Last push: 2026-08-13T05:47:55+00:00

## Health v2 (maintenance only)
Score: 56/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 97, release rhythm 35, longevity 2
- inputs: {"age_days": 28, "days_push": 20, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, young, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1117, forks 70 (observed 2026-08-28T04:03:38.288036+00:00)

## What it is
WorldClaw is a research framework from Tencent Hunyuan for agentic, large-scale 3D open-world generation, released alongside an arXiv paper. It combines AI agents with generative 3D models to build expansive virtual worlds.

## Use cases
- generate 3d open worlds with ai agents
- procedurally create large-scale 3d scenes
- build virtual game worlds from text prompts
- research agentic 3d content generation
- scale up 3d world synthesis pipelines

## When to choose
- you need to generate large-scale 3D open worlds with agentic AI pipelines
- you are researching generative 3D world models
- you want to build on Tencent Hunyuan's 3D generation stack

## When to avoid
- you need a production-ready tool with stable APIs and support
- you lack GPU resources for large generative 3D models
- you need a polished game engine rather than a research codebase

## Facets
- artifact type: library
- maturity: experimental
- function: machine-learning, deep-learning, agent-framework, graphics, simulation, game-engine
- domain: artificial-intelligence, graphics, simulation, deep-learning
- platform: python, cross-platform
- tags: 3d-generation, open-world, hunyuan3d, generative-ai, research, world-models, scene-generation, ai-agents, game-development, gpu, linux

## Member repositories
- Tencent-Hunyuan/Hunyuan3D-WorldClaw (main) score 56

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:38.288036+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T06:41:52.070286+00:00, confidence not recorded.
  - readme: https://github.com/Tencent-Hunyuan/Hunyuan3D-WorldClaw (fetched 2026-08-28T04:03:38.288036+00:00, sha bb1cf02c01cc)
  - homepage: https://tencent-hunyuan.github.io/Hunyuan3D-WorldClaw/ (fetched 2026-08-29T12:45:45.036761+00:00, sha cb59768730a2)
- Data as of 2026-08-30T08:39:29.467469+00:00.