Agentic system where a coding agent writes SDK programs to generate simulation-ready articulated 3D assets from text.
Updated EU status checked Last shown
Sources: the vendor's own pages (linked above) and creator videos at the linked timestamps. EU status is information, not legal advice; see how we check.
Articraft is a research system for generating articulated 3D assets, meaning objects with separate parts and joints. Instead of generating meshes directly, a coding agent writes programs against an LLM-friendly SDK, and those programs build the object. The project describes the output as simulation-ready.
According to the project site and a creator review, the work ships with the Articraft-10K dataset, which has over 10,000 assets across 245 categories. The code is reported as released and agent-agnostic, so different coding agents (a creator mentioned GPT-5.5) can drive it.
It is aimed at researchers and developers who need articulated assets for simulation, robotics or embodied-AI work. Details on licensing, the vendor or authors, and exact release timing were not available in the material provided.
Watch the moment: the exact second top creators show it. Videos load only when you press play, via youtube-nocookie.com.
Generates articulated 3D assets with parts and joints by having a coding agent such as GPT-5.5 write a program that builds the object. Comes with the Articraft-10K dataset of over 10,000 assets in 245 categories; code released and agent-agnostic.
Closest neighbours by meaning, not just by category.
Model
Roblox research model that generates text-to-3D objects as separate part meshes from a user-defined part list.
Model · Nvidia
Nvidia platform for generating character animations from text prompts, used as a source of reference motion.
Research
Agentic framework that reconstructs sim-ready 3D scenes with rigid, articulated and deformable objects from multi-view RGB.
Model
Text-prompted motion generation model that animates rigged 3D assets with arbitrary skeleton topologies, no retraining.
Model
Research text-to-3D method using block-wise diffusion over shape tokens, about 5x faster than autoregressive baselines.
Model
Image-to-3D generator from Tsinghua and Tencent ARC Lab that builds meshes pixel-aligned to the input view.
