Show HN: A 3D mesh playground for coding agents (three.js + manifold-3d)

Hacker News•Mon, Oct 26, 2026, 12:02 AM•2 min read

When GPT-6/Gemini launched recently, a lot of the 3D demos used blender-mcp ( https://github. com/ahujasid/blender-mcp ). It's cool, but you have to install blender locally and wire up plugins just to try a prompt or share a run.

Source: [Hacker News](https://sketchagent.dev/s/yfYU6LhT)

📰 Read Full Story

This is an aggregated headline summary. For the complete report, visit the original publisher.

Continue Reading at Hacker News ↗

#tech #mesh #blender #playground #coding #three #manifold #mcp #run

More Headlines

TechnologyDev.to• 6m ago

CartSpark — Autonomous E-Commerce Listing Studio Powered by Google Gemma 2

This is a submission for the Hacktoberfest Open-Source AI Challenge Week 3: Slow and Steady What I Built CartSpark is an autonomous e-commerce listing generator, unit economics price optimizer, and customer review copilot designed specifically for marketplace sellers and independent creators (Ets...

TechnologyDev.to• 7m ago

How Do You Show Two Training Runs Are Equal? A Paired Test on Unseen Text, Using an NPU vs GPU Case

Disclosure: the case study below is VIDRAFT's own result. VIDRAFT is a technology partner of QuantID. This post reviews the measurement design; it is not an independent verification.

TechnologyDev.to• 7m ago

Notice2Next: Turning Bureaucratic School Notices into Grounded Action Checklists with Gemma 2

This is a submission for the Hacktoberfest Open-Source AI Challenge Week 3: Slow and Steady . What I Built As a teacher, I know how easily important instructions get buried in long educational notices. A single circular may contain an examination deadline, a fee requirement, a list of documents...

TechnologyDev.to• 7m ago

An AI Recruiting Agent Should Schedule, Not Select: A 14-Case SME Release Test

An AI Recruiting Agent Should Schedule, Not Select: A 14-Case SME Release Test For a small employer, a useful first recruiting agent can acknowledge an application, answer approved process questions, and offer interview times. It should not rank, reject, infer suitability, interpret an accommoda...

TechnologyDev.to• 7m ago

Ending a 14-Day Team Trial Is Harder Than Starting One

Liquid syntax error: Unknown tag 'endraw'

TechnologyDev.to• 8m ago

¿Puede una NPU solo-inferencia preentrenar un LLM? 325M de parámetros desde cero, con la misma calidad que una B200

Resumen Sí, siempre que exista una pila de entrenamiento hecha para ello. En VIDRAFT preentrenamos VKORE-325M-NPU-Base (325,6 millones de parámetros) desde una inicialización aleatoria en la Rebellions ATOM-Max , una NPU comercial coreana lanzada en 2025 y diseñada para inferencia. Entrenamos e...