I’m happy to announce the release of Box3D, an open source 3D physics engine. It is now available on GitHub. Box3D repository You can think of Box3D as a fork of Box2D, extended with many features needed for 3D games. Some additions: Triangle mesh collision Height-field collision Baked compound collision The core architecture of Box3D remains almost identical to Box2D. C API All library source is C17 Sub-stepping solver Continuous collision Graph coloring for large islands Wide SIMD contact solver Multi-threading hooks Optional internal scheduler Large world support with doubles for position Recording and replay If you want to see Box3D in action, watch this video:
ed3dai/ed3d-plugins
Ed's repo of Claude Code plugins, centered around a research-plan-implement workflow. Only a tiny bit cursed. If you're lucky.
MolmoAct 2: An open foundation for robots that work in the real world | Ai2
MolmoAct 2 is a fully open robotics foundation model that brings faster, stronger 3D action reasoning to real-world robot tasks, alongside a major new bimanual manipulation dataset for researchers to study, reproduce, and build on.
WorldClaw: Agentic 3D Open-World Generation at Scale
From one open-ended prompt to an explicit, explorable, and editable 3D world.
Three.js From Zero — Creative Web 3D for Artists · MasterAllArts
Learn Three.js as part of the MasterAllArts creative 3D roadmap: turn drawings, models, shaders, and portfolio ideas into interactive Web 3D scenes. Free articles with live demos.
atmoprints - 3D Models on AT Protocol
A decentralized 3D model hosting platform built on AT Protocol. Share, discover, and download 3D printable models on the open social web.
Join the Hubs Discord Server!
We are a community of artists, developers, and other creatives that supports an immersive 3D web via our open-source, WebXR project. Our community builds good things. 🌐 | 21838 members
Mote: An Interactive Ecosystem Simulation — Peter Whidden
RoboScape: Physics-informed Embodied World Model
World models have become indispensable tools for embodied intelligence, serving as powerful simulators capable of generating realistic robotic videos while addressing critical data scarcity challenges. However, current embodied world models exhibit limited physical awareness, particularly in modeling 3D geometry and motion dynamics, resulting in unrealistic video generation for contact-rich robotic scenarios. In this paper, we present RoboScape, a unified physics-informed world model that jointly learns RGB video generation and physics knowledge within an integrated framework. We introduce two key physics-informed joint training tasks: temporal depth prediction that enhances 3D geometric consistency in video rendering, and keypoint dynamics learning that implicitly encodes physical properties (e.g., object shape and material characteristics) while improving complex motion modeling. Extensive experiments demonstrate that RoboScape generates videos with superior visual fidelity and physical plausibility across diverse robotic scenarios. We further validate its practical utility through downstream applications including robotic policy training with generated data and policy evaluation. Our work provides new insights for building efficient physics-informed world models to advance embodied intelligence research. The code is available at: https://github.com/tsinghua-fib-lab/RoboScape.
at3d.app — portable 3D identity for AT Protocol
An open standard for portable 3D and 2D avatars, virtual worlds, and game characters on the AT Protocol network.
heerich.js
Tiny engine for 3D voxel scenes rendered to SVG — boolean ops, oblique/perspective cameras, zero dependencies.
