Open Lakehouse Format for Multimodal AI. Convert from Parquet in 2 lines of code for 100x faster random access, vector index, and data versioning. Compatible with Pandas, DuckDB, Polars, Pyarrow, a…

HTTP Streaming of ROS Image Topics in Multiple Formats

A JavaScript client library for integrating multi-party communications powered by the Amazon Chime service.

RMW for ROS 2 using Zenoh as the middleware

FlatBuffers: Memory Efficient Serialization Library

An extremely fast Python linter and code formatter, written in Rust.

C/C++ WebRTC network library featuring Data Channels, Media Transport, and WebSockets

coturn TURN server project

Ready-to-use SRT / WebRTC / RTSP / RTMP / LL-HLS / MPEG-TS / RTP media server and media proxy that allows to read, publish, proxy, record and playback video and audio streams.

Vuer is a 3D visualization tool for robotics and VR applications.

Docker Containers of Raspberry Pi OS

ROS 2 node for libcamera supported cameras (V4L2, Raspberry Pi Camera Modules)

COLMAP - Structure-from-Motion and Multi-View Stereo

BEHAVIOR-1K: a platform for accelerating Embodied AI research. Join our Discord for support: https://discord.gg/bccR5vGFEx

ROS 2 Package for LeRobot SO-ARM101

An implementation of roslibjs's interfaces by using Foxglove WebSocket Protocol.

2025 - This is my deployment environment for real world AI robot policies, and a place to create training data for reinforcement learning and imitation learning.

LeIsaac provides teleoperation functionality in IsaacLab using the SO101Leader (LeRobot), including data collection, data conversion, and subsequent policy training.

ROS 2 Package for LeRobot SO-ARM101

An Open-Source Large-Scale Reinforcement Learning Project for Search Agents

A light-weight, pythonic ros2 package to connect the genesis simulator and ROS2

Lightweight interface for controlling ROS-based robotic arms using LeRobot

Octo is a transformer-based robot policy trained on a diverse mix of 800k robot trajectories.

End-to-end robot control based on generative diffusion model

Deep learned, NVIDIA-accelerated 3D object pose estimation

[CVPR 2024 Highlight] FoundationPose: Unified 6D Pose Estimation and Tracking of Novel Objects