Robot Learning Python Packages

robosuite

robosuite: A Modular Simulation Framework and Benchmark for Robot Learning

mani-skill

Manipulation Skill Framework, an open source GPU parallelized robotics simulator and benchmark

hflow

SDK for robotics teams to verify the quality of their data used for AI model training.

kalanos

Audit Robotics data before you train on it. Scores LeRobot, HDF5, MCAP, ROS 2, CSV and JSON recordings for timing, signal integrity and motion quality.

gauntlet-robotics

Robustness evaluation harness for robot manipulation policies (VLA): perturbation sweeps, failure clustering, reproducible reports.

provael

Provael — red-team open Vision-Language-Action (VLA) robot policies in simulation and report an Attack Success Rate (ASR). Prove it. Prevail.

orbit-eval

You have a robot. orbit tells you what to do next, and how you will know it worked. Zero-dependency CLI for LeRobot datasets and evaluations: what the recording got wrong, what it never covered, whether a change survived the noise.

fieldtrial

Statistically rigorous real-world evaluation for robot policies. Plan how many rollouts you need, run them randomized and blinded from a phone at the robot, let fieldtrial switch LeRobot or openpi policies itself, and get a report that only says "better" when a pre-registered test does.

ml-dash

Scalable Training Telemetry and Metrics Visualization

mani-skill-nightly

Manipulation Skill Framework, an open source GPU parallelized robotics simulator and benchmark

embodichain

An end-to-end, GPU-accelerated, and modular platform for building generalized Embodied Intelligence.

calibra-robotics

Dataset observability and coreset selection for robotics imitation learning

openwam

Official code for "OpenWAM: An Open Framework for Composable World-Action Models" (Stanford University)

rofunc

🤖 The Full Process Python Package for Robot Learning from Demonstration and Robot Manipulation

openwam-sdk

Official code for "OpenWAM: An Open Framework for Composable World-Action Models" (Stanford University)

pyroboframes

High-performance ML dataloader for robotics. LeRobot format, hardware-accelerated video decode, MLX arrays. Zero-copy pipeline for Apple Silicon.

mlx-smolvla

SmolVLA on Apple Silicon: native MLX inference, LeRobot-protocol serving, and preview on-device training, with verified parity gates

robotrace-dev

Python SDK for RoboTrace: observability and evals for AI-powered robots. Log episodes (synchronized video + sensors + actions) from rosbag2 or Hugging Face LeRobot datasets, version them, and re-roll new policy versions against historical observations.

robohive

A unified framework for robot learning

robometrics

RoboMetrics is a pip-installable Python library for computing robotics trajectory, prediction, temporal drift, safety, comfort, coverage, calibration, physics, and diversity metrics from NumPy arrays and simple CSV/JSON trajectory files.

adduct

Finds the defects in your robot demonstration data that will break your policy — before you spend GPU-hours training. Static analysis for LeRobot, RLDS, robomimic, and Zarr datasets.

unienv

Framework unifying robot environments and data APIs

flexiv-control

Unified real-time control and safety layer for the Flexiv Rizon — teleop, MPC, RL, sim2real, with a MuJoCo sim.

pyrobovision

Perception stack for autonomous robots & vehicles. Real-time multi-object tracking, 3D perception fusion, safety-constrained learning. Track, detect, and understand the world.