Skip to main content

MAGMA Scenarios

Official robotic task scenarios and the shared scenario registry for MAGMA-GEN and MAGMA-BENCH. The package provides simulation environments, task definitions, presets, skills, and functions for discovering and loading scenarios from installed Python packages.

You can add your own scenarios in a separate package without modifying this repository or the generation pipeline.

Installation

Python 3.12 is required. Simulation installation has been checked on Linux x86_64.

python -m pip install "magma_scenarios==2.1.0"

This installs magma_core[simulation] and the simulation dependencies, including ManiSkill, SAPIEN, and PyTorch. Version 2.1.0 is a stable release of this package; it accepts MAGMA Core starting at 2.0.0b1, including subsequent stable v2 releases. GPU rendering requires suitable system drivers.

To install the release directly from GitHub:

python -m pip install "magma_scenarios @ git+https://github.com/MAGMA-rob/magma-scenarios.git@v2.1.0"

This installs the scenario code from GitHub and resolves dependencies from PyPI. For development, clone this repository and run python -m pip install -e ..

Discover and load scenarios

magma-scenarios list
magma-scenarios show press_button

The same registry is available in Python:

from magma_scenarios import get_scenario, list_scenarios, load_definition, load_preset

print(list_scenarios())
manifest = get_scenario("press_button")
definition_type = load_definition("press_button.Definition")
preset_type = load_preset("press_button.ButtonPressOrdered")

Listing scenarios and reading manifests do not start a simulator or register simulation environments. Loading a definition, preset, or skill registers its scenario's environments and returns the component class; it does not create an environment. Benchmarks can register an environment by ID with register_environment("PressButtonBasic-v1").

Included scenarios cover button pressing, sorting, delivery, table cleaning, laundry, coffee preparation, and packaging. Use magma-scenarios list to see all installed scenario providers.

Add your own scenarios

Please refer to the official documentation site

Development and support

Use magma-scenarios --help for all commands. test-tools and test-requests provide interactive checks for scenario implementations; see their --help for configuration options.

Report bugs through GitHub Issues or contact Loan Bernat.

Authors and license

Loan Bernat, with contributions from Abdelbasset Houdass (internship). Licensed under the BSD 2-Clause License.

Metadata

Release files for magma-scenarios 2.1.0

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for magma-scenarios 2.1.0
File Size Uploaded
magma_scenarios-2.1.0.tar.gz 22.8 MB Details

Built distribution (wheel)

Table of built distributions (wheels) for magma-scenarios 2.1.0
File Interpreter ABI Platform
magma_scenarios-2.1.0-py3-none-any.whl Python 3 none any Details

Total release size: 46.2 MB

Release files / magma_scenarios-2.1.0.tar.gz

Download URL magma_scenarios-2.1.0.tar.gz
Size 22.8 MB
Tags Source
SHA-256 checksum
How to use checksums
1100d91315f3486078fa35052241e00290fcce42cdedd314a635df8677213f75
BLAKE2b-256 checksum
How to use checksums
509543f1c9f07d82d87e7ae0838fb472f2b6df6d42a577da54774759c7f61fe6
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.14

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Oct 2, 2026.

Transparency log

Release files / magma_scenarios-2.1.0-py3-none-any.whl

Download URL magma_scenarios-2.1.0-py3-none-any.whl
Size 23.4 MB
Tags Python 3
SHA-256 checksum
How to use checksums
68d7c7df10feb88e3842993486f53ff5b34200cf5844c877658e5518593c4bd9
BLAKE2b-256 checksum
How to use checksums
8925e1ef085fe0cfe474cd015f99f3e1bf2590fef41fb88932bd9005baf21d78
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.14

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Oct 2, 2026.

Transparency log

Release history Release notifications | RSS feed

2.1.1

2 release files

This release

2.1.0 This release

2 release files

2.0.2

2 release files

2.0.1

2 release files

2.0.0

2 release files

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page