Robots, liquids, cloth and sand in one scene: an open-source engine for robot learning The Alloy project released an open-source (Apache-2.0) physics engine for robot learning that simulates rigid bodies, cloth, granular materials and liquids in a single scene, built on MuJoCo Warp and Newton. Each object is routed to a solver by material — MuJoCo Warp for robots and rigid bodies, Newton's VBD for cloth, Newton's implicit MPM for sand and pastes, and Alloy's own DFSPH solver for liquids — with cross-solver contact in one world. The engine ships an MCP server so agents like Claude Code can build and run scenes, and is installable via pip for Python 3.11 or 3.12. Many of the tasks we want robots to learn mix materials: pouring water into a glass, folding a towel, scooping sand, routing a cable. In simulation those materials usually live in different tools, so a policy that has to pour and grasp ends up stitched across engines, or the liquid gets left out. Alloy https://github.com/argonrobotics-ai/alloy is an open-source Apache-2.0 physics engine for robot learning that puts them in one scene. The paper is on arXiv: Alloy: A Multi-Material Physics Engine for Robot Learning https://arxiv.org/abs/2611.16312 . Alloy is built on MuJoCo Warp and Newton and picks a solver for each object from its material: | Object | Solver | |---|---| | Robots and rigid bodies | MuJoCo Warp MuJoCo C on the CPU | | Cloth and soft bodies | Newton's VBD solver | | Sand, granular material and pastes | Newton's implicit MPM solver | | Liquids | Alloy's own DFSPH solver | Objects from different solvers touch each other in the same scene. sim.routes tells you which solver each object got. Here an MJCF arm sits beside a tub of water and a tray of sand: python import alloy ARM = """