浏览器三维沙盒让智能体看图修模型

ryannz2 2026-10-26T03:12:33 I created https://sketchagent.dev/s/Y23McoC4 with my codex — out of curiosity, how does this compare to Luma / Meshy? The results seem to have much lower detail. wsxiaoys 2026-10-26T04:07:34 Luma/Meshy are generative models that output a high-fidelity mesh in one shot. This is more about testing an LLM’s spatial and visual understanding: the agent writes the geometry code and has to reason about the 3D result from what it sees, then iterate.

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. 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.