BAM provides high-fidelity servo actuator models and an identification pipeline to improve the accuracy of robotic simulations, specifically for better sim-to-real transfer in Reinforcement Learning.

An open-source robotic arm project providing complete hardware blueprints and software stacks to lower the barrier for learning and deploying Embodied AI.

A customizable operating system for robots that integrates agentic reasoning engines and a modular skill system to enable true physical autonomy.

OpenEnv is a Python framework that defines a Gymnasium‑style API for isolated, containerised agentic environments. It provides a server (FastAPI + Docker), an async client (with sync wrapper), a CLI for scaffolding, building, and deploying to Hugging Face Spaces, and a optional web UI for debugging. The library targets RL and LLM‑agent research, offering example environments (Echo, Coding, Chess, Atari, FinRL) and integrations with TRL, torchforge, SkyRL, and others. Early‑stage but actively governed and open‑source under BSD‑3.

A pragmatic Vision-Language-Action (VLA) foundation model pre-trained on 20,000 hours of real-world robot data to enable high-performance robotic control across multiple platforms.

A modular AI runtime for creating and deploying multimodal agents across digital environments and physical robots, supporting diverse sensors and AI models.

A large-scale simulation framework for training and benchmarking generalist robots to perform everyday kitchen tasks using diverse scenes, objects, and extensive demonstration data.

A portable operating harness and Python API that enables AI agents to control Android and iOS devices locally or in the cloud.

A continuously‑updated, open‑source handbook that curates VLA (vision‑language‑action) research, engineering tricks, community notes, and industry intel, providing reproducible scripts, hardware guides, RSS feeds, and an AI‑assistant skill—all under a CC‑BY‑4.0 license.

A lightweight reinforcement learning framework for training motion controllers to imitate reference motions across multiple simulator backends.

An open-source, build-it-yourself scaled version of the JPL Mars rover designed for education and research using consumer off-the-shelf parts.

A unified framework for evaluating Vision-Language-Action (VLA) models across various robot simulation benchmarks using Dockerized environments and batched GPU inference.

A scalable behavior cloning framework for robotics that provides training pipelines and evaluation tools for Diffusion Transformer (DiT) and Vision-Language-Action (VLA) models.

A cross-platform Arduino library that simplifies Field Oriented Control (FOC) for BLDC and stepper motors, enabling precise motion control across various hardware combinations.

A task-based evaluation benchmark for robot manipulation policies built on NVIDIA Isaac Lab, featuring 120+ tasks with automated success detection.

An open-source simulator for autonomous driving research used to develop, train, and validate autonomous driving systems in simulated urban environments.

TurboVLA is a lightweight Vision-Language-Action model that enables real-time robotic control at 32 Hz using less than 1 GB of VRAM by replacing LLM-centric architectures with a direct vision-language to action mapping.

A unified embodied-agent framework for general-purpose robots that integrates 3D spatial memory and closed-loop execution for long-horizon real-world tasks.

A versatile 3D mapping framework that uses factor graphs and GPU acceleration to provide accurate, sensor-agnostic range-based mapping and localization.

Nav2 is the official ROS 2 navigation stack, offering localisation, path planning, obstacle avoidance, and docking for mobile robots. It’s modular, supports multiple ROS 2 releases, and is backed by a strong community and industry sponsors.

XLeRobot is a low-cost, open-source dual-arm mobile robot platform designed for embodied AI and household manipulation tasks, starting at $660.

An open-source humanoid robot project providing the CAD, simulation models, and software needed to build and customize a 1.2m bipedal robot.

An AR diffusion framework for robot control that unifies visual world modeling and action inference to improve long-horizon performance and generalization.

SuperMew is a self‑hosted, audit‑first RAG/agent platform. It persists threads, runs, events and document versions, offers hybrid Milvus+BM25 retrieval, supports HITL checkpoints, versioned skills/tools, a frozen model control plane, and a built‑in evaluation framework. The stack uses FastAPI, PostgreSQL, Redis, Milvus, and a Vue 3 frontend, and can be run locally with Docker‑Compose or deployed in production with systemd/K8s.

Botpress Cloud is an open‑source platform for building AI‑powered chatbots. The repo contains the CLI, SDK, client libraries, example bots, and a collection of public integrations that can be deployed to Botpress Cloud workspaces. Developers use `bp init` to scaffold a bot or integration, write TypeScript with the SDK, and deploy with `bp deploy`. The system is designed for developers who want programmatic control over chatbot creation, with optional publishing of integrations to the Botpress Hub. All code is MIT‑licensed.

A generative 3D world engine that converts text and images into simulation-ready 3D assets and environments for embodied AI, deployable across multiple robotics simulators.

A Python library for photorealistic embodied AI research that provides deep programmatic control over Unreal Engine applications with high-speed rendering and extensive API access.

Warp is an NVIDIA‑backed Python library that JIT‑compiles regular Python functions into fast CPU/GPU kernels for physics simulation, robotics, and differentiable computing. It works with PyTorch/JAX, provides a simple `@wp.kernel` decorator and `wp.launch` API, and ships as the `warp-lang` PyPI package.

A high-performance data platform for robotics and Physical AI that transforms monolithic sensor logs into structured, queryable archives for model training.

An open-source robot simulator providing a complete development environment to model, program, and simulate robots, vehicles, and mechanical systems.

An open-source autonomous driving framework providing a production-ready software stack for the commercial deployment of autonomous vehicles.

Pinocchio is a high‑performance C++ library (with Python bindings) for rigid‑body dynamics, offering analytical derivatives, contact solvers, closed‑loop handling, and AD support. It powers many robotics and simulation tools and can be installed via Conda or pip.

A comprehensive reinforcement learning platform for fluid dynamics that provides a Gymnasium-compatible interface to over 60 CFD environments across six different solver backends.

An open-source, JavaScript-driven desktop robot platform based on M5Stack that allows users to create and customize robot behaviors via browser-based tools and MODs.

The Open Motion Planning Library (OMPL) is an open-source library providing over 40 sampling-based motion planning algorithms for robots to navigate state spaces and avoid obstacles.

An open-source auto-aiming and fire-control system for combat robots that uses neural network detection and trajectory planning to maximize hit rates and minimize kill times.

A 3D mobile robot navigation stack that enables mapping, localization, and autonomous navigation in complex multi-level environments, overcoming the limitations of 2D navigation frameworks.

A CUDA-accelerated library for robot motion generation that provides GPU-parallel algorithms for kinematics, collision checking, and trajectory optimization for high-DoF robots.

A Python API for interfacing with cars via the CAN bus, enabling the reading of vehicle state and control of steering, gas, and brakes for ADAS development.

A Python-based API and MCP server that allows users to control Xiaomi Mijia smart home devices via code, CLI, or AI agents.

A framework for sim-to-real transfer in legged robots that uses data-driven system identification and evolutionary optimization to align simulation dynamics with real-world hardware.

A Gymnasium‑compatible PyBullet simulator for single‑ and multi‑drone control, with examples for PID, downwash, and PPO reinforcement learning, plus optional Betaflight SITL integration.

MoveIt 2 is an open-source motion planning framework for ROS 2 used to develop robotic manipulation applications and benchmark planning algorithms.

A C++ plugin for Godot 4 that provides Behavior Trees and Hierarchical State Machines to help developers create complex, modular AI behaviors for game agents.

Psi0 is an open vision-language-action (VLA) foundation model for humanoid robots that enables dexterous loco-manipulation by combining a VLM backbone with a diffusion-based action expert.

TorchRL is a PyTorch‑native, modular reinforcement‑learning library that provides a unified TensorDict data model and interchangeable components (environments, collectors, replay buffers, loss modules, trainers, etc.) for building, scaling, and experimenting with RL, multi‑agent, model‑based, and LLM post‑training pipelines.

A multi-physics simulation package for modeling and simulating rigid and deformable bodies, granular dynamics, and fluid-solid interactions, specifically supporting robotics and embodied AI.

A GPU-accelerated, lightweight learning library for robotics research that enables rapid prototyping of robot learning algorithms.