DEDUPED Hot AI repos, turned into use cases Get 5 a day

How to let Claude Code or Codex make and tweak 3D assets with Image to 3dlab

Connect AssetFurnace as an MCP tool so your coding agent makes, checks and adjusts 3D assets locally.

Who it is forA developer who already works in Claude Code or Codex and wants an agent to produce game assets on their own machine.

The problemAsset work usually breaks the flow of a coding session, and sending art to hosted tools raises upload concerns.

The outcomeAn agent session that generates a character or model, checks the run, tries another setting and opens the result in the studio.

What you need first

  • An Apple Silicon Mac or an NVIDIA PC (Linux or Windows per the README), or a Linux AMD card with ROCm for the Pixal3D route
  • Terminal access to run the install line
  • Free disk space for model weights, for example 8.4 GB for Pixal3D and 6.6 GB for Front + back
  • Full Xcode on a Mac if you build Pixal3D locally

Steps

  1. Install with curl -fsSL https://assetfurnace.com/install.sh | bash, or ask your agent to install it from assetfurnace.com.
  2. For Claude Code, run claude mcp add assetfurnace -- ~/image-to-3dlab/lab mcp.
  3. For Codex, run codex mcp add assetfurnace -- ~/image-to-3dlab/lab mcp.
  4. Start a new agent session.
  5. Ask the agent to make a character, for example 'Make me a Pixar-style gator warrior and show me.'

Prompt for your agent

Using the AssetFurnace MCP server in the repo at <install folder>, make a 3D model of <subject>, check the run status, and open the result in the studio. Verify that the agent asks before downloading any model weights and that the output file exists on disk.

Caveat. The README says Mac and Linux are supported for agent use and Windows is not tested yet, and agents cannot delete or rename your assets.

Share: X LinkedIn Hacker News Email Copy link

Disclaimer

Deduped lists open-source repositories that belong to other people. We do not own, maintain, audit, or vouch for any of them, and a repo appearing here is not an endorsement or a safety check. The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong. Where a use case is marked "Seen in the wild", we link to public posts where someone described something similar, but we have not verified those posts and the use case itself is still our AI's own write-up. Use all of this at your own risk. Only run code, commands, or agents on systems and accounts you are authorized to use, and read the code and every command before you run it, especially anything that touches credentials, files, or the network. Nothing here is professional, security, legal, or financial advice. All trademarks and project names belong to their respective owners, and their use here does not imply affiliation. Content is provided as is, without warranties of any kind. Found a mistake, a safety problem, or something you want removed? Email [email protected] and we will look at it promptly. Full disclaimer page