01Open source
Repos
Open-source repos worth knowing, by the problem they take on.
Robotics
GenZ-LIO
Implements the IEEE T-FR 2026 paper GenZ-LIO for robust, computationally efficient LiDAR-inertial odometry across confined and open environments.
portal
Rust transport layer that closes the robot teleoperation and inference control loop over WebRTC through NAT without VPNs or forwarded ports.
Spotter
Official codebase for Spotter, which adds an intervention layer between a frozen embodied model and a VLM to improve manipulation tasks.
FlashDexRetarget
Official implementation of FlashDexRetarget, which accelerates dexterous manipulation data generation via multi-motion retargeting.
Calibrex
Command-line tool that checks whether a robot's sensor calibration remains valid from ROS bags with per-axis verdicts for LiDAR, IMU, camera, and GNSS.
GazeVLA
Official CoRL 2026 code for a Python framework that learns human intention to improve robotic manipulation through explicit causal behavior modeling.
GRABETTE
A Python toolkit for collecting robot manipulation demonstrations via camera and IMU streams to export training-ready datasets for policy learning.
OpenWAM
A Stanford Python framework for composable world-action models that developers can use to unify causal video pretraining and robot dynamics evaluation.
ros2_pulse
This C++ ROS 2 probe measures topic frequency and node liveness with near-zero overhead for diagnosing communication in live robotic graphs.
SO-ARM 102
This open-source hardware kit provides a 5-DOF leader-follower robot arm design with CAD files and assembly guides for building teleoperation systems.
FlashSAC RSL-RL
This repository provides an implementation of the FlashSAC reinforcement learning algorithm for IsaacLab environments. It enables fast and stable off-policy learning for high-dimensional robot control tasks, such as rough-terrain locomotion.
Jumper Crab Robot
Jumper is an open-source, 22-DoF crab robot hardware platform designed for educational purposes and motion training. It features extensive documentation and AI-assistant integration to help users design appearances and behaviors.
BAGEL ROS Bag Visualizer
BAGEL is a browser-based visualizer for ROS1 and ROS2 bag files, point clouds, and Gaussian Splats. It operates as a fully static web application requiring no installation, offering a convenient debugging tool for robotics engineers.
Calibra Dataset Observability
Calibra offers dataset observability and coreset selection tools for robotics imitation learning. It audits data integrity to optimize training sets, significantly reducing data volume while maintaining or improving model performance.
LeRobot Android Controller
This project enables an Android phone to function as the controller for a LeRobot mobile robot, replacing a Raspberry Pi. It is a cost-effective solution that leverages built-in phone hardware like cameras, 5G, and NPUs without requiring root access.
Graph as Policy
Graph-as-Policy (GaP) is a robotics framework that compiles natural-language instructions into typed, verified skill graphs for execution on real robots. It targets 'Variational Automation' to ensure persistent reliability across varying tasks, offering a transparent alternative to black-box policies.
BICMap Robotics SDK
BICMap is a WebGL-based SDK for visualizing robotics data, including SLAM maps, point clouds, and navigation paths. Built on MapLibre and Three.js, it provides developers with pre-packaged tools for creating integrated indoor-outdoor robotic scenes.
Cadence Learning System
Cadence is a brain-inspired AI framework that learns continuously from live experience, combining perception, memory, plasticity, and action. It models a simulated human-like brain from simplified biological mechanisms rather than using feed-forward deep neural networks.
Metriplane Robotics Observability
Metriplane provides deterministic replay and verifiable incident evidence for recorded robotics workcell runs. It generates human-readable reports and regression tests from timestamped object positions and process rules, enabling engineers to rerun cases after software changes.
RL Token Pipeline
RL-Token-Pi05-open provides a pipeline for fine-tuning the ฯ0.5 VLA, training an RL Token, and deploying online reinforcement learning on the SO-101 robot arm. It includes a critical-phase classifier and step-by-step hardware, recording, training, and inference workflows.
FLUX Action Model
FLUX 3 Action is an open-weights 7B world action model from Black Forest Labs. It takes camera frames, robot state, and text instructions to predict actions and future video frames for robots, simulators, and games.
HOI-Retarget System
HOI-Retarget retargets human-object interaction clips into humanoid robot trajectories that reproduce the interaction, not just poses. It uses contact-centric trajectory optimization to ensure the robot grasps the same object locations at any scale.
XGO-Duck Robot
XGO-Duck is a 3D-printable bipedal robot duck built around an Arduino UNO Q and 15 serial servos, adapted from Pollen Robotics' Microduck. It includes mechanical models, PCB designs, a BOM, and an assembly guide for building and exploring biped motion.
Open Reality AI
Open Reality converts phone video into persistent, AI-queryable 3D scenes with measurement, path planning, and robot-training exports. It provides MCP tools for Claude, Codex, and Cursor, plus a self-hostable broker and the VGGT-SLAM library.
Robotics Coding Simulator
An open-source robotics simulator designed for AI coding agents, offering HTTP/JSON and MCP control, Newton physics, wgpu rendering, ROS 2 support, and reproducible benchmarks. Useful for agent-driven robot development.
Tactile Data Annotation
TLabel is a sensor-agnostic tactile data annotation toolkit that loads any tactile sensor and exports a unified 14-dimensional semantic schema. Fills a genuine gap in cross-sensor tactile annotation for manipulation data.
LiDAR Inertial SLAM
ROS2 LiDAR-inertial SLAM with multi-session alignment, built on rko_lio odometry or custom odometry. Provides multi-session alignment for LiDAR-inertial systems from a credible lab.
Agentic 3D Modeling
Procedura turns text prompts into editable parametric CAD programs with named parts, typed mates, and optional PBR materials and articulation exports. Novel LLM-to-parametric-CAD approach with robotics potential.
Humanoid Soccer Shooting
Official codebase for RoboNaldo, training Unitree G1 humanoid soccer-shooting policies in Isaac Lab using motion-guided curriculum reinforcement learning. Academic work focused on accurate, stable, powerful free-kick policies.
Camera Only Drone
An autonomous quadrotor flying a MuJoCo obstacle course using only an onboard camera, with a small judgment model (TypeSafe Jev) at 2.5Hz for situational decisions. Novel camera-only approach with a small model in the loop.
Autonomous Drone Navigation
A ROS 2 workspace for PX4/Gazebo UAV navigation in GNSS-denied spaces using VIO, LIO, 3D occupancy mapping, D* Lite planning, and GPU MPPI obstacle avoidance. Targets DARPA SubT Urban; substantial GNSS-denied stack.
ROS 2 Frontier Exploration
Modern C++ frontier exploration package for autonomous mobile robots with ROS 2 Jazzy and Humble support. Notable for its standalone C++ core library and Nav2 integration for custom applications.
Altara Telemetry Dashboards
React component library for real-time telemetry dashboards targeting robotics, aerospace, and industrial IoT. Notable for canvas-rendered flight displays, time-series, and ROS2/MQTT adapters at 60fps.
Franka Control Stack
No-ROS Python toolkit for Franka Research 3 control, teleoperation, trajectory planning, IK, and LeRobot data collection. Notable for its lightweight ZMQ streaming, Gymnasium environment, and LeRobot v3 integration for embodied AI research.
Microduck RL Playground
Reproducible reinforcement learning experiments, policies, and printable hardware add-ons for Pollen Robotics' Microduck. Notable as an independent experimental continuation of the official Microduck RL repository.
OpenETA Embodied Agent
Embodied task agent that connects perception, action, verification, and learning in a continuous physical-world loop. Notable for proposing an agentic paradigm shift from digital to physical intelligence.
SolidWorks URDF Exporter
Cross-platform SolidWorks to URDF converter with a browser-based editor. Notable for automatically inferring joints from mates and providing free prebuilt binaries for Windows, macOS, and Linux.
FlyDrones Connectome Pilot
Uses the fruit fly connectome as a spiking neural network to pilot drones from visual input, with a live 3D browser demo. Notable as a bio-inspired control experiment built on the published MaleCNS connectome.
Flybrain Robot Bridge
An experimental camera-to-robot bridge inspired by Drosophila vision, using optical flow and IMU feedback with a mock neural backend to send left/right UDP motor commands. It includes a local synthetic demo, with MaleCNS connectome integration planned.
MMBench2 World Models
Official code for 'Hallucination in World Models is Predictable and Preventable,' providing training/evaluation of generative world models plus hallucination predictors, targeted data collection, browser interaction, and 350M-parameter checkpoints.