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

A developer released a browser-based 3D mesh playground built on three.js and manifold-3d that lets coding agents connect over MCP or run in-browser to build and edit geometry without a local Blender install. The playground gives agents a render_preview tool that captures multi-view screenshots — front, right, top, iso, custom camera angles and clay mode — so the agent can inspect its output and correct the mesh. The linked trace shows Gemini reconstructing a Copenhagen canal scene from a photo, hitting a script error on the first pass, fixing the bug, then iterating through several rounds of 4-view and close-up render_preview checks to adjust the geometry.

When GPT-6/Gemini launched recently, a lot of the 3D demos used blender-mcp https://github.com/ahujasid/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. I built a browser-based 3D mesh playground so you can hook up your own coding agent over MCP or run in-browser directly in a tab. It runs on three.js + manifold-3d for blender-like boolean/mesh editing in JS, and gives the agent a render preview tool to take multi-view screenshots front/right/top/iso + custom camera angles + clay mode . That way the agent can look at what it built and fix the geometry, similar to how it iterates when building a website. The submitted link is a trace of Gemini reconstructing a Copenhagen canal scene from a photo: it hits a script error on the first pass, fixes the bug, and then goes through several rounds of checking 4-view and close-up render preview screenshots to tweak the geometry. Comments URL: https://news.ycombinator.com/item?id=50237291 https://news.ycombinator.com/item?id=50237291 Points: 1 Comments: 0