robosuite
robosuite: A Modular Simulation Framework and Benchmark for Robot Learning
Decision gist · record as of 2026-08-14
Yes, if you are doing robot learning research or prototyping. robosuite is actively maintained, has low install friction, zero known vulnerabilities, and is widely used in academic robotics labs. The main caveat is that the license treatment is unclear—verify the license terms before use in proprietary projects. The 12 runtime dependencies are standard and well-maintained.AI-flagged interpretation of the facts on this page — verify before relying
Before you install
- Requires mujoco and mink system dependencies; rendering features need a display or headless rendering setup.
- Low install friction with a pure-Python wheel and active maintenance (last commit 2026-07-11, 233 days since latest release).
- Depends on 12 runtime packages including mujoco, numpy, and scipy—all widely available.
License · maintenance · safety
(unclear) — License treatment is unclear; the fact sheet does not specify an SPDX identifier or raw license text, so you should verify the license terms before use in proprietary or restricted contexts.
last release 2025-12-24 (233 days) · last repo commit 2026-07-11 · 2,557 stars
0 known vulnerabilities (OSV.dev, 2026-08-14) · 252,205 downloads/mo, #8,551 on PyPI
Alternatives
Verify before relying
pip install robosuite
import robosuite as suite
env = suite.make(env_name="Lift", robots="Panda", has_renderer=True)
obs = env.reset()
env.render()- Whether the license is open-source or proprietary (license_treatment is marked unclear)
- Whether mujoco and mink dependencies have their own license constraints that cascade to users
What it is and what it does
robosuite is a modular simulation framework built on the MuJoCo physics engine, designed for researchers and practitioners developing robot learning algorithms. It provides a standardized suite of manipulation tasks, procedural environment generation, multiple robot embodiments (including humanoids as of v1.5), and a range of control abstractions—from joint-space velocity control to whole-body controllers. The framework also integrates teleoperation devices, multi-modal sensors (RGB, depth, proprioception), and photorealistic rendering.
The package is actively maintained by researchers at Stanford, UT Austin, and NVIDIA, and is intended to lower barriers to entry for robot learning research by offering reproducible benchmarks, modular APIs for custom environment design, and utilities for collecting and replaying human demonstrations. It supports current Python versions and has no known security vulnerabilities.
Use it for
- Train reinforcement learning agents on standardized manipulation tasks with reproducible benchmark environments.
- Prototype custom robot environments by composing robot models, arenas, and parameterized objects procedurally.
- Collect and replay human teleoperation demonstrations for imitation learning workflows.
- Evaluate different robot embodiments and controller types on the same task for comparative research.
- Generate synthetic training data with multi-modal sensors (RGB, depth, state) for vision-based robot learning.
Worth the install?
AI-flagged interpretation of the facts on this page. Verify before relying on it.
Yes, if you are doing robot learning research or prototyping.
robosuite is actively maintained, has low install friction, zero known vulnerabilities, and is widely used in academic robotics labs. The main caveat is that the license treatment is unclear—verify the license terms before use in proprietary projects. The 12 runtime dependencies are standard and well-maintained.
Install
robosuite on PyPI
Before you install
Low install friction with a pure-Python wheel and active maintenance (last commit 2026-07-11, 233 days since latest release). Depends on 12 runtime packages including mujoco, numpy, and scipy—all widely available.
Requires mujoco and mink system dependencies; rendering features need a display or headless rendering setup.
License in practice
License treatment is unclear; the fact sheet does not specify an SPDX identifier or raw license text, so you should verify the license terms before use in proprietary or restricted contexts.
Quickstart
pip install robosuite
import robosuite as suite
env = suite.make(env_name="Lift", robots="Panda", has_renderer=True)
obs = env.reset()
env.render()Verify before relying
- Whether the license is open-source or proprietary (license_treatment is marked unclear)
- Whether mujoco and mink dependencies have their own license constraints that cascade to users
Package facts
| License | Not declared unclear |
| Python support | Supports the current Python release >=3 |
| Install friction | Low. Pure-Python wheel |
| Runtime dependencies | 12 packagesnumpynumbascipymujocominkqpsolversPillowopencv-pythonpynputtermcolorpytesttqdm |
| Maintenance | Actively maintained 233 days since the last release |
| Last repo commit | |
| First released | |
| Downloads | 252,205 / month, #8,551 on PyPI 30-day window, as of 2026-08-14 |
| Known vulnerabilities | None known OSV.dev, checked 2026-08-14 |
Evidence: robosuite-1.5.2-py3-none-any.whl
Tags
Let your AI agent find packages like this
Example. Real query, live index.
You found this page by searching. An agent finds it by wishing: SkillFed indexes 14,416 PyPI packages by what they can do, searchable in plain language.
wish › “robot simulation framework”
- robosuiterobosuite is a MuJoCo-powered simulation framework for building,…
- mjlabmjlab provides a GPU-accelerated reinforcement learning and robotics…
- lerobotLeRobot provides a unified PyTorch framework for training, deploying,…
Give your agent the search over MCP, or paste the wish link into any chat.
More Artificial Intelligence packages
LiteLLM provides a unified Python interface to call 100+ LLM providers (OpenAI, Anthropic, Gemini, Bedrock, Azure, and others) using OpenAI-compatible API format, available as both a Python SDK and a self-hosted AI Gateway proxy server.
Install it if you need to work with multiple LLM providers or want to centralize LLM routing in your organization.
Client library and CLI tool for downloading, uploading, and managing models, datasets, and repositories on the Hugging Face Hub platform.
Install it if you work with Hugging Face Hub models or datasets.
LangChain provides a framework for building agents and LLM-powered applications by composing language models, tools, and memory through a unified API that abstracts over multiple model providers.
hf-xet provides chunk-based deduplication and efficient file transfer for the Hugging Face Hub, enabling faster uploads and downloads of large files with local disk caching.
Tokenizers converts raw text into token sequences for NLP models, with support for training custom vocabularies and using pre-built tokenizers (BPE, WordPiece) optimized for speed via Rust.
Transformers provides a unified framework for loading, fine-tuning, and running state-of-the-art pretrained models across text, vision, audio, video, and multimodal tasks using PyTorch, JAX, or TensorFlow.
Install it if you need to run or train any transformer-based model for NLP, vision, audio, or multimodal tasks.
See also lerobot · mjlab · mujoco-warp · drake · mink · dm-control · skrl · dex-retargeting · rsl-rl-lib · pin-pink