Skip to content
store
img2threejs

Self-hosted alternatives to img2threejs

5 self-hosted AI Skills apps to use instead, best rated first.

Top picks

  1. C

    claude-to-deerflow

    Get

    claude-to-deerflow is an agent skill that lets an assistant send messages and questions to a running DeerFlow instance through its HTTP API. DeerFlow is an AI agent platform built on LangGraph that orchestrates sub-agents for research, code

    Self-hosted

  2. O

    open-notebook

    Get

    open-notebook is an agent skill for organising research with Open Notebook, a self-hosted alternative to NotebookLM. It arranges sources, notes and AI conversations into research notebooks. Sources can be PDFs, web pages, audio, video and O

    Self-hosted

  3. R

    Reactive Resume

    Get

    Reactive Resume is a free and open-source resume builder for writing resumes and cover letters, checking the work, and tracking job applications. You create a free account, import an existing resume or start from scratch, and see the finish

    Open sourceSelf-hosted

  4. S

    self-hosted-funnel-launch

    Get

    Self-hosted funnel launch is an agent skill that takes a funnel from an empty install to published on infrastructure you control, using the Autonnel funnel builder, which is licensed Apache-2.0. The result covers a landing page, checkout, a

    Self-hosted

  5. G

    get-convex/convex-backend

    Get

    Convex is an open-source reactive database for web app developers. It combines a database, a place to write server functions in pure TypeScript, and client libraries that keep the app's data live, so screens update as the data changes. Beca

    Self-hosted

About img2threejs

I

img2threejs

Turn an object or character reference image into a quality-gated

img2threejs is an agent skill that rebuilds an object or character from a reference image as a procedural Three.js model written in code. The skill calls this reconstruction by code. The model is built through a staged sculpting pipeline, and each stage is gated by quality checks and an AI-vision self-correction loop that compares the result with the reference. The skill says plainly that it is not photogrammetry, mesh extraction or the use of downloaded art packs, so the model is authored in code rather than scanned or copied. It works under Claude Code, Codex or OpenCode. Where the instructions mention agent vision or a browser tool, the agent uses whatever the host offers, such as native image reading, a browser MCP like Playwright or Chrome DevTools, the project preview, or a screenshot from the user. Exporting is a separate step. An explicitly chosen emission target, given with a --target option, transforms the finished model as a whole into another output kind, and it does not change how the model was built. The skill is installed with npx skills from the img2threejs repository, and its security audits show Gen Agent Trust Hub and Snyk passing, with Socket showing a warning.

View img2threejsAll AI Skills apps
Price
Free
Made by
img2threejs
Category
AI Skills
Website
github.com/img2threejs/img2threejs/img2threejs