Meshgen — AI skill for Claude Code

MeshGen

Use AI Agents to control Blender with natural language.


Features

• Focused on AI as a tool, not replacement
• Multiple backend options:
  • Local inference with llama.cpp or Ollama
  • Remote inference with Hugging Face, Anthropic, or OpenAI
• Optional LLaMA-Mesh integration for local mesh understanding and generation
• Optional Hyper3D integration for high-fidelity 3D mesh generation

Installation

1. Go to the Latest Release page
2. Download the addon ZIP file for your platform
3. In Blender, go to Edit -> Preferences -> Add-ons -> Top-Right Arrow -> Install from Disk...
4. Select the downloaded ZIP file

Setup

1. In blender, go to Edit -> Preferences -> Add-ons -> meshgen
2. Select either `Local` or `Remote` and follow instructions below

Local Backend


Run models free locally directly in Blender.

Only select this option if you:

1. Have a powerful NVIDIA GPU with at least 8GB of VRAM
2. Installed a cuda version of the addon during Installation
3. Prefer running the model directly in Blender instead of a local Ollama server

To set up the local backend, you can either:

1. Click Download Recommended Model to download Meta-Llama-3.1-8B-Instruct-GGUF
2. Manually download a .GGUF model and put it in the models folder (located by clicking the folder icon)

Remote Backend


MeshGen supports a variety of remote backends.

1. Ollama to run models in a free local server
2. Hugging Face, Anthropic, or OpenAI to run powerful models via API

[Hugging Face](#hugging-face) i