Dev
GitHub repos gaining traction - what high-signal users are starring and what's climbing the board, captured daily and enriched from GitHub. Raw material for spotting new tech and patterns worth building on.
2,991
repos tracked
117
surfaced this week
232
created < 30d
Python
top language
56 repos
-
The first exam for code agents in the physical world: frozen robot tasks from many benchmark suites, each answered with a program and verified in a separate sandbox. Runs on Harbor.
-
Home robot ++
-
GTSAM is a library of C++ classes that implement smoothing and mapping (SAM) in robotics and vision, using factor graphs and Bayes networks as the underlying computing paradigm rather than sparse matrices.
-
OpenTac: open tools to design, fabricate, read and simulate flex-PCB tactile skins that sense normal and shear force, for any robot surface.
-
Exact convex collision geometry for MuJoCo assemblies: pegs and holes from any outline, threads, and gears.
-
OpenTac: open tools to design, fabricate, read and simulate flex-PCB tactile skins that sense normal and shear force, for any robot surface.
-
Isaac Lab API, powered by MuJoCo-Warp, for RL and robotics research
-
Hexapod walker: STS3215 prototype, RL training orchestrator (CoreWeave), MuJoCo sim, robot control
-
An open interactive toolkit that accelerates human and agentic physics-based Real2Sim of Robot Manipulation Tasks
-
RAX harness: coding agents that learn robot tasks by online exploration
-
🦀 Jumper — an crab robot.
-
[ICML 2026] A Framework for Benchmarking and Improving Coding Agents for Robot Manipulation
-
Official code for the SEAR benchmark
-
A controllable benchmark for robotic manipulation
-
Official repository for "RoboDojo: A Unified Sim-and-Real Benchmark for Comprehensive Evaluation of Generalist Robot Manipulation Policies".
-
Full kinodynamics constraints for arbitrary robot configurations with factor graphs.
-
Adaptive robot execution: direct and hybrid controller ports, interaction memory, and EmbodiedSWE/FLUX adapters. CPU validated; GPU qualification pending.
-
RL training environments for Microduck (mjlab)
-
State-of-the-art method for model-based dexterous manipulation
-
The ultimate harness for coding agents and beyond. All your agents. All your machines. One command center. Start with code, then follow your curiosity and build across disciplines: CAD, circuits, robots, games and music.
-
Evidence-backed, model-agnostic runtime contracts for physical agents
-
GTSAM is a library of C++ classes that implement smoothing and mapping (SAM) in robotics and vision, using factor graphs and Bayes networks as the underlying computing paradigm rather than sparse matrices.
-
GPT-6 Astra for embodied AI and robotics.
-
An mjlab integration for the Booster K1
-
A collection of high-quality models for the MuJoCo physics engine, curated by Google DeepMind.
-
A library of experiments using frontier LLMs/VLMs for robotics tasks, currently focusing on GPT-6 Astra.
-
A curated collection of papers, research blogs, open-source tools, benchmarks, and community demos for robot-use agents, including demos powered by GPT-6 Astra. —— Explore our searchable website.
-
Reproducible Microduck RL experiments, policies, simulation assets, and hardware add-ons
-
Notebook-based book "Introduction to Robotics and Perception" by Frank Dellaert and Seth Hutchinson
-
ENPIRE is an agentic framework that allows AI coding agents to autonomously self-improve real-world robot policies through closed-loop physical trial, error, and evolution
-
SuperDex brings together a purpose-built physics engine, robotics authoring tools, and a scalable reinforcement learning interface in a unified simulation platform, with VR-based teleoperation and additional capabilities planned for future releases.
-
A Tiny biped duck robot 🦆
-
A curated list of software, simulators, policies, agent tools and coverage for the Pollen Robotics / Hugging Face Microduck robot
-
A Simple Transport Layer For Teleoperation And Inference
-
🤗 LeRobot: Making AI for Robotics more accessible with end-to-end learning
-
Reinforcement Learning (RL) environments for the Microban platform, a 30cm open-source and affordable humanoid robot.
-
Code for GOAG: Generative and Object-Agnostic Grasp Planner for Dexterous Robotic Manipulation
-
Microban is an affordable, fully 3D-printable, and 100% open-source humanoid robot. Powered by a Raspberry Pi Zero 2W and 19 Dynamixel servomotors, it serves as an accessible DIY platform for learning, experimentation, and research in robotics.
-
★ 183 Toyota/yubi-hwYUBI - Yielding Universal Bidigital Interface - Open source hardware design for a finger-driven teleoperation glove and robot gripper, including CAD, BOM, and assembly instructions.
-
Automation foundation model for tiny devices: 2-bit, 8-29 MB, tool calls, ASR, structured extraction and embeddings on phones, wearables, smart homes, robots, cars and microcontrollers.
-
Python-first native robotics simulation and reinforcement-learning environments
-
Quantization, kernels, runtime and inference engine for mobiles, wearables, smart home and robots.
-
DART: Dynamic Animation and Robotics Toolkit
-
Official code repository for the paper "Hallucination in World Models is Predictable and Preventable".
-
[CoRL 2026] Official Repository for: Scaling Self-Play for End-to-End Driving
-
One policy. Any motion. Train universal whole-body tracking in mjlab—swap clips, not checkpoints.
-
★ 12.1k NVIDIA/cosmosNVIDIA Cosmos is an open platform of world models, datasets, and tools that enables developers to build Physical AI for robots, autonomous vehicles, smart infrastructure, and more.
-
ABC: Scalable Behavior Cloning with Open Data, Training, and Evaluation