robomimic
ARISE Initiativerobomimic is a framework for robot learning from demonstration. It pairs released datasets of human and machine-generated manipulation demonstrations with imitation-learning and offline reinforcement learning algorithms, including BC-RNN, BC-Transformer, IQL and Diffusion Policy, and with tools for configuring, sweeping and reproducing training runs. It is part of the ARISE Initiative and uses robosuite as its simulator.
Openness
5 high confidence- license
- MIT (OSI, released datasets also MIT on the Hub)
- source
- public
- core features withheld
- no — an academic project with no paid offering
The framework is MIT-licensed and builds in full from its public repository, and the demonstration datasets it distributes carry the same license. It is an academic project begun at Stanford and maintained across several labs, with no paid edition.
- https://huggingface.co/api/datasets/amandlek/robomimic recorded 2026-11-12
Hub API for the robomimic datasets: tag "license:mit", "gated":false.
- https://raw.githubusercontent.com/ARISE-Initiative/robomimic/master/LICENSE recorded 2026-11-12
LICENSE is the MIT License text: "MIT License", "Copyright (c) 2021 Stanford Vision and Learning Lab".
- https://raw.githubusercontent.com/ARISE-Initiative/robomimic/master/README.md recorded 2026-11-12
README: "This project is part of the broader ... (ARISE) Initiative"; "The project originally began development in late 2018 by researchers in the Stanford Vision and Learning Lab (SVL). Now it is actively maintained and used for robotics research projects across multiple labs." No paid tier is mentioned.
- https://ungh.cc/repos/ARISE-Initiative/robomimic/files/master recorded 2026-11-12
Full listing of the master branch, 201 paths; no ee, enterprise, commercial or proprietary path.
- https://ungh.cc/repos/ARISE-Initiative/robomimic/releases/latest recorded 2026-11-12
Latest release v0.5.0 (v0.5), published 2025-06-27.
Adoption
2 medium confidencePyPI downloads of the robomimic package. The newest release on PyPI is older than the newest GitHub release, and the documentation recommends installing from source, so the count misses users of the current version.
- https://pypi.org/pypi/robomimic/json recorded 2026-11-12
PyPI metadata for robomimic: latest version 0.3.0, uploaded 2023-07-04; homepage https://github.com/ARISE-Initiative/robomimic.
- https://pypistats.org/api/packages/robomimic/recent recorded 2026-11-12
pypistats: last_month 47,295 downloads for robomimic.
- https://robomimic.github.io/docs/introduction/installation.html recorded 2026-11-12
Installation page: "Option 1: Install from source (recommended)" and "Option 2: Install via pip $ pip install robomimic".
Capability
not assessedThe software in this category is compared on how fast and how faithfully it simulates robots. robomimic trains policies from recorded demonstrations and relies on robosuite for any simulation, so it has no place on that comparison and none is claimed.
- https://raw.githubusercontent.com/ARISE-Initiative/robomimic/master/README.md recorded 2026-11-12
README: "robomimic is a framework for robot learning from demonstration. It offers a broad set of demonstration datasets collected on robot manipulation domains and offline learning algorithms to learn from these datasets"; v0.5.0 "Diffusion Policy, multi-dataset training, language-conditioned policies"; v0.3.0 "BC-Transformer and IQL".
- https://robomimic.github.io/docs/introduction/installation.html recorded 2026-11-12
Installation page, "Install simulators": "robosuite Required for running most robomimic examples and released datasets."
Verified 2026-11-12