- Home
- Skills
- Frontend & Web Apps
- nex-wobble-office-3d-agents
Works with the AI Agents you already use
Nex Wobble Office 3d Agents
Generate a production-ready 3D virtual office for AI agents using Next.js and React Three Fiber.
$39
nex-wobble-office-3d-agents
Example session with this skill installed
Build me a 3D virtual office for 4 agents with specific zones for 'Dev' and 'Testing', optimized for a Raspberry Pi deployment.
- Read your context and instructions
- Compiled the nex-wobble-office-3d-agents
I've generated a Next.js 3D office suite:
OfficeScene.tsx: 80x60 layout with 'Dev' and 'Testing' zones.BlobAgent.tsx: Support for independent GLB instances.lib/store.ts: Zustand store with Pi-mode enabled (reduced grid/shadows).Dockerfile: Optimized for ARM64.
Connects securely to your tools. The creator never sees your data.
About this skill
A Pro-Grade 3D Virtual Workspace for AI Agents
This skill provides a complete, production-ready React Three Fiber scene for visualizing multiple AI agents in a 3D office environment. Built for Next.js, it handles the complex boilerplate of 3D rendering, state management, and asset loading, allowing you to focus on your agent logic.
What it does
- OfficeScene: A modular 3D environment including floors, walls, and customizable zones with floating HTML labels.
- BlobAgent System: A high-performance agent renderer that supports GLB model loading, skeleton cloning (allowing multiple independent instances of the same model), and procedural "wobble" animations.
- AliceAnimator: A bone-level procedural animation engine that drives rigged characters based on agent status (idle, walking, celebrating).
- Zustand Store: Reactive state management for real-time updates to agent positions, roles, and statuses.
- Pi-Optimized: Includes a "Pi Mode" toggle and a multi-stage Dockerfile specifically tuned for ARM64/Raspberry Pi deployments.
Why use this skill?
Rendering multiple independent 3D characters in React Three Fiber is notoriously tricky due to skeleton sharing and performance bottlenecks. This skill solves those issues out-of-the-box using the SkeletonUtils.clone pattern and status-driven emissive materials. It provides a polished, stylized visual layer for your agents that is significantly more engaging than a text-based dashboard.
Technical Foundation
Built with Next.js, Three.js, React Three Fiber, @react-three/drei, and Zustand. It ships with a Docker configuration ready for self-hosting with local network security defaults.
Built by Nex AI. More skills and info at nex-ai.be and slopsome.com.
- Requires manual placement of GLB files in public folder.
- Performance may drop with 20+ rigged agents on low-end hardware.
- No built-in pathfinding logic.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before any payment.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed 3 months ago