quackd
CLI that puts Jev on a LeRobot SO-101 arm. Discrete steps go to Jev, angles stay with the LLM.
Feature a build or sponsor the directory. DM @pranavmore69
Arms, humanoids, fleet software and the data engines behind them. Physical AI, not robot clip accounts. 22 builds on this page, each with the original post.
CLI that puts Jev on a LeRobot SO-101 arm. Discrete steps go to Jev, angles stay with the LLM.
One video of a human hand becomes a real2sim pipeline. Tracking, IK to a 44-DoF hand, grasp refine. First-party, OSS.
World action model that lets robot policy scale with in-the-wild human video. CoRL 2026. Code and data are public.
The open-source duck robot, ported to NVIDIA Isaac Lab so it can run a different physics stack.
ROBOTIS OMY arm: Gemini reasoning, GraspNet 6-DoF poses, collision-free pick-and-place on ROS 2.
25 cm open-source biped you train in sim and run on the real robot. $399, ships before Christmas.
Decoupled humanoid whole-body controller. Train on one GPU, drive it in the browser, zero-shot onto the robot.
NVIDIA SRL's robot control stack, rebuilt so the hardware is actually easy to set up. pi0.5 doing the hello-world task.
85-line finger-tracking toy for Physical AI video cleanup. Claude Code plus MediaPipe.
Can a VLM act through a body? Open-source benchmark for action intelligence, decoupled from motor control.
Basement-built autonomous rover: custom BMS PCB, STM32, Raspberry Pi, and a neural net trained to push objects into a goal zone.
Human-in-the-loop teleoperation infrastructure aimed at creating an open, distributed learning network for robots.
Connect Claude-style agent workflow directly to physical robots. Describe the task and the system writes the code to execute it in ~20 minutes.
Physical robot you can program directly with Claude Code or Codex to help with real-world tasks like working on cars.
Fully open-source robot vacuum you build for about $200: Raspberry Pi, 2D LiDAR mapping, ROS2 navigation and native Home Assistant integration. No cloud.
Fully open-source framework that turns an $8 ESP32 into a real-time autonomous voice assistant with local wake-word detection.
7-foot teleoperated centaur robot with a humanoid torso, quadruped base and quick-swap tool wrists, built for wildfires and disaster zones by a garage startup.
Full Physical AI data collection and processing platform for training robots from simulation and egocentric video.
Custom local AI running on an $8 ESP-32 that tracks humans with zero computational delay.
Open-source tool that turns plain English descriptions into production-ready CAD files (STEP, STL, URDF, etc.) for robotics and mechanical design.
7+1 DOF fully 3D-printable robot arm that costs around $220, complete with CAD and build guide.
Fully open-source expressive robot with object tracking and support for multiple AI models. STL + code released.
If you have a LeRobot SO-101 at home, you can put Jev on it with quackd CLI. The "--jev on" parameter sits in front of the model and takes the discrete steps (read state, gripper, stop). Angles stay with the LLM. On the steps Jev can take, each call is about 54× faster and Show more
Video in → physics out. 🤖 I gave GPT-6 Astra one video of a human hand. It wrote this entire real2sim pipeline itself — hand tracking, IK retargeting to a 44-DOF dexterous hand, grasp refinement. Zero code from me. Open-sourcing everything 👇 github.com/Hu-xiao-max/de…
EgoWAM has been accepted to #CoRL2026 @corl_conf 🥳🥳 See you all in Austin!!!! We’ve also open-sourced all the data and code: 📊 Data: partners.mecka.ai/egoverse?task=… 💻 Code: github.com/GaTech-RL2/Ego… If you run into any problems, please submit an issue on GitHub. We’ll do our best to Show more
Egocentric human data is abundant, but human motion is not always positive supervision for robot policy due to embodiment gaps. Naive BC co-training can HURT performance ☹️. 🌟Our key finding in **EgoWAM**: the state-prediction branch of a World Action Model effectively bridges
finally gave in to the urge and ported microduck to isaac lab!! opening the door to a whole new physics stack and lots of new experiments github.com/5usu/IsaacLab/… do give a star if you find it useful.
Smart pick-and-place with OMY, Gemini, and GraspNet! We integrated VLM reasoning, GraspNet 6-DoF pose synthesis, and Cyclo Control for collision-free manipulation on ROS 2. 🎬 Video: youtu.be/OxMBVGkFJHM 🤖 Code: github.com/ROBOTIS-GIT/cy… 📝 Docs: docs.robotis.com/docs/systems/o…
We built a small biped robot you can teach new tricks to. Train it in simulation, run it on the real thing. Meet Microduck 🦆 $399, shipping before Christmas. pollen-robotics.com/microduck github.com/pollen-robotic…
We open-sourced all components of the HTD whole-body controller (WBC): github.com/chrisyrniu/Isa… -Play our WBC on your browser: humanoid-touch-dream.github.io/wbc_mujoco/liv… -Main HTD codebase entry: github.com/chrisyrniu/hum… (data collection and HTD policy soon!) Highlighted features: -Lightweight Show more
A touch-aware humanoid manipulation policy that cleans the lab for you🧹🧪 Introducing Humanoid Touch Dream: a real-world system for dexterous, contact-rich humanoid loco-manipulation. Our key idea is simple: the policy predicts future hand forces and tactile latents alongside
We released DROID+, a new and improved DROID control stack from SRL. We believe robots (and hardware) should be easy to setup and easy to use, and so we updated the DROID stack to be the same. @HugoHadfield1 github.com/nvlabs/droidpl… Here's pi0.5 doing our "hello world" task:
Make your fingers dancing. a little toy I made , just 85 lines made by claude code and me . This is actually part of the video data cleaning and filtering process for Physical AI data collection. github.com/fat1/handMedia…
🔥 HumanCLAW is now fully open-sourced! github.com/Human-CLAW/Hum…
🦾HumanCLAW: Can Vision-Language Models Act Through a Body? A VLM can spot the sofa in a second. But can it get a body there and sit down? We call it Action Intelligence, and our work decouples it from motor control so it can finally be measured. Today’s best models turn out to
1/ I built an autonomous rover in my mom's basement completely from scratch. chassis, drivetrain, PCBs, STM32 firmware, controls, inference, all of it. In this demonstration, it’s controlled by a neural network, trained to push objects into a goal zone (like Ronaldo on wheels). Show more
Why Robotics Is Entering Its “Open Source” Moment Linux changed software by proving that a powerful system could be built through contributions from a global community rather than controlled entirely by one organization. Wikipedia showed that knowledge could grow through Show more
CLAUDE CODE JUST GOT A REAL BODY a startup called Waddle Labs plugged the same agent workflow straight into robots you connect their API to your robot and type what you want it to do then their agents write all the code to pull it off in about 20 minutes no rigging up motion Show more
An AI assistant just got its own phone number and email address. It makes your calls, waits on hold, and books the follow-ups. And it is one of 7 things that dropped this week most people slept on. Me and @AndrewWarner broke them all down in the video below. Here's what you Show more
There's an open-source home robot vacuum you can actually build yourself. It's called OOMWOO. Runs on a Raspberry Pi with 2D LiDAR mapping, ROS2 navigation, and native Home Assistant integration. No cloud dependency, no vendor lock-in. The team spent real time researching Show more
btw this robot runs on a fully open source AI framework called Xiaozhi it turns a $8 ESP32 chip into a fully autonomous voice assistant NO expensive cloud servers or high latency wake-word detection and audio streaming happen locally on the chip: > requires only an ESP32-S3, Show more
meet WALL-E no, not the one from the cartoon :) this is a fully 3D-printed, autonomous desk companion running on an ESP32. it uses a local AI voice assistant to process commands in real-time and control its own motors building intelligent robotics just dropped to zero cost...
NEW: California startup Satyress unveils a 2 meter tall centaur robot designed to enter disaster zones too dangerous for humans.
So what are we actually building at Axis Robotics? Four products, one compounding loop: 1. Task Generation Engine (live) Give it a prompt like: “A study desk with a pour-over kettle, a hand-crank coffee grinder, a coffee mug, a notebook, and a pen.” The engine turns that Show more
At Axis Robotics, our vision is to build a compounding data engine—one that connects large-scale pretraining data, corrective post-training data, model deployment, and failure feedback in a continuously improving loop. Over the next 6–12 months, we will advance this vision
this creator just built a zero-delay auto-aim system on an $8 microcontroller he deployed a custom local AI algorithm on a cheap ESP-32 to track human movement with absolute 0-pixel accuracy. the system completely eliminates standard computation delay. it processes the bounding Show more
finally! local AI is accessible to everyone. we replaced our massive smart home server with a single $8 ESP32-S3 chip processing voice commands entirely on-device. now anyone can build this. here is the full guide: x.com/i/article/2081…
One of the coolest open-source projects I have seen is text-to-cad. Describe a part in plain English, and AI helps generate production-ready CAD artifacts. It supports: - STEP, STL, 3MF, DXF & GLB export - URDF, SRDF & SDF generation for robotics - CAD model editing through AI Show more
text-to-cad just crossed 10,000 stars you can use it to generate: - STEP files - URDF, SDF and other sim artifacts - 3D mesh files like STL, 3MF and GLB - gcode for 3D printing - DFM checks for popular services like sendcutsend 100% free and open source ✌️
Robotics is getting its Raspberry Pi moment. This solves one of the biggest frictions in Physical AI: Everything has been fragmented. Different tools for control. Sensors. Calibration. Learning. Now it’s one unified stack: • motor control to VLA models in one system • Show more
A GUY PUT GPT-LEVEL AI INSIDE A 3D PRINTED ROBOT AND RELEASED THE ENTIRE THING FOR FREE Most people look at a 3D printer and see plastic toys This guy printed a robot with expressive eyes, object tracking, image recognition, support for ChatGPT, Qwen and offline models, then Show more