cd /news/robotics/alloy-physics-engine-for-robot-learn… · home › topics › robotics › article
[ARTICLE · art-171378] src=alloy.argonrobotics.ai ↗ pub= topic=robotics verified=true sentiment=↑ positive

Alloy physics engine for robot learning

Argon Robotics released Alloy, an open-source multi-material, parallel physics engine for robot learning built on Newton and MuJoCo Warp and licensed under Apache-2.0, installable via `pip install alloy-engine` on Python 3.11 or 3.12. Alloy steps robots, cloth, cables, liquids, sand and soft bodies together in one scene, runs the same script on an NVIDIA GPU or CPU, and ships with 5,423 library objects, 9 ready-made tasks and quadruped walking, plus a sim.health() check that distinguishes physics failures from policy failures. The engine is aimed at AI agents building training tasks from in-package docs, which Argon Robotics says agents used to build new tasks in minutes.

read1 min views2 publishedNov 17, 2026
Alloy physics engine for robot learning
Image: source

Built on Newton and MuJoCo Warp. Open source under Apache-2.0. You

pip install alloy-engine Your agent Build and train

*<your task>*with Alloy

see prompt #

Install alloy-engine with pip (Python 3.11 or 3.12, in a virtual environment). Read its docs: run python -m alloy.docs, or fetch https://alloy.argonrobotics.ai/llms.txt. Then build <your task> in many parallel worlds: start from the closest ready-made environment in the docs and change it step by step. Train a policy until it succeeds, check sim.health() after every run, and report the success rate.

Built for agents. #

  • Docs in the packagepython -m alloy.docs shows them on your machine.
  • Build a new task in minutes Agents built new training tasks from the docs in minutes.
  • Health in every world Tells a physics failure from a policy failure.
  • Settings choose themselves Solvers and steps are picked;sim.routes() says why.

Key features. #

  • Many materials, one scene Robots, cloth, cables, liquids, sand and soft bodies, stepped together. Cloth and a cable beside a robot run slowly.
  • GPU or CPU The same script, renderer included, runs on an NVIDIA GPU or the CPU.
  • A camera for every world Colour, depth and segmentation of every world at once.
  • Robots ready to go Arms, a hand, a quadruped and two humanoids, with RL and demo recording.
  • Assets and tasks included 5,423 library objects, 9 ready-made tasks (pick-and-place, pouring, drawers, cloth folding) and quadruped walking.
── more in #robotics 4 stories · sorted by recency
── more on @alloy 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
→ Live at https://your-agent.zahid.host ✓
Get free account → Pricing
from €0/mo · no card required
LIVE [news/alloy-physics-engine…] indexed:0 read:1min 2026-11-17 · —