wanhaoniuCommunity·9 Agent Skills Included

MomoAgent

Open-source robotic arm control with voice and vision

Controls a 5-DOF robotic arm through leader-follower teleoperation, voice commands, and camera-based vision. Eliminates complex ROS setup and manual joint programming with ready-made Python scripts, a desktop GUI, and web and mobile apps. Includes 3D-printable hardware files and calibration tools so makers and educators can build and run pick-and-place demos quickly.

41|2

↗

npx skills add wanhaoniu/MomoAgent --all -g -y

All Skills in This Repository (9)

Pure Emerald Level Indicators

📦 In Repo

wanhaoniu

magic-mirror-demo

Capture camera photos, score portraits, and generate queen videos via ArtsAPI.

artsapi-image-video

Generate images and videos via ArtsAPI CLI with prompt-driven requests and status checks.

macos-use-desktop-control

Automate macOS desktop UI interactions by locating elements via visible text.

dji-show-demo

Automates DJI Show Demo workflows for robotic arm and camera systems.

photo-booth-camera

Capture macOS Photo Booth photos and pass them to ArtsAPI for image-to-image or video generation.

sidecar-window-control

Move the frontmost macOS window to iPad Sidecar or an extended display.

soarmmoce-real-con

Control a real SoarmMoce robotic arm locally via Python scripts and SDK.

screen-pointer-tools

Track mouse coordinates and control the cursor across macOS multi-monitor setups.

photo-booth-macos-use

Capture a single still photo from a selected webcam via macOS Photo Booth.

Community

Advanced

Frequently Asked Questions

FAQPage Schema

How to install MomoAgent?▼

Run `npx skills add wanhaoniu/MomoAgent --all -g -y` in your terminal to install all skills in this suite globally.

What is MomoAgent used for?▼

It is an open-source 5-DOF robotic arm based on SOARM101 with higher payload and a larger workspace, controlled via Python and ROS for education, prototyping, and pick-and-place tasks.

How do I control the MomoAgent robotic arm?▼

Start the slave server on the follower device, then run the master client on your PC with the serial port and IP configured. You can also use the built-in GUI, voice commands, or the web and mobile apps.

Does MomoAgent support voice and vision control?▼

Yes. It includes speech recognition, face and gesture tracking, and camera streaming modules that let you operate the arm through natural interaction.

Can beginners build the MomoAgent arm?▼

Yes. The repository provides 3D-printable part files, assembly models, a beginner quick-start guide, and calibration tools to walk you through the full build.