Openrl alternatives for AI agents.

[CVPR 2025] RoboBrain: A Unified Brain Model for Robotic Manipulation from Abstract to Concrete. Official Repository.

Mosaico - The data platform for Physical AI

VoxPoser: Composable 3D Value Maps for Robotic Manipulation with Language Models

A modular high-level library to train embodied AI agents across a variety of tasks and environments.

Contrib package for Stable-Baselines3 - Experimental reinforcement learning (RL) code

SimWorld: An Open-ended Realistic Simulator for Autonomous Agents in Physical and Social Worlds

google-deepmind/gemini-robotics-sdk is a high-star GitHub project relevant to AI agent workflows.

A unified framework for robot learning

HoloMotion: A Foundation Model for Whole-Body Humanoid Control

Software for writing protocols and running them on the Opentrons Flex and Opentrons OT-2

UnrealCV: Connecting Computer Vision to Unreal Engine

A Comprehensive Framework for Visual SLAM Systems and Datasets

A modular, open and non-proprietary toolkit for core robotic functionalities by harnessing deep learning

Robot kinematics implemented in pytorch

Python inverse kinematics using Pinocchio and QP solvers

Evaluating and reproducing real-world robot manipulation policies (e.g., RT-1, RT-1-X, Octo) in simulation under common setups (e.g., Google Robot, WidowX+Bridge) (CoRL 2024)