JohnHeibel/ClaudeAnimationBase

A starter kit for animating hand-painted cartoons with Claude: p5.js + p5.brush, the Clawd character, 31 acted emotions and a guide for the model

What it solves

This project provides a starter kit for creating character animations using AI coding agents (specifically Claude Opus 5.5). It simplifies the process of generating 2D animations with a "handmade" aesthetic—featuring boiling linework and watercolor fills—by providing a structured codebase and a set of animation guidelines for the AI to follow.

How it works

The kit uses p5.js and p5.brush to handle the visual rendering. A user provides a prompt to a coding agent (like Claude Code), which then reads a provided ANIMATION_GUIDE.md to understand the rules of the style and character. The AI storyboards the scene, builds it shot-by-shot, and uses a headless renderer (render.mjs) to produce frames and export a final MP4 video.

Who it’s for

It is designed for creators and developers who want to use LLMs to automate the creation of stylized 2D animations without manually coding every frame.

Highlights

  • AI-Driven Workflow: Designed to work with coding agents to storyboard and render animations from text prompts.
  • Stylized Aesthetic: Focuses on a "handmade" look with brush strokes and boiling linework.
  • Headless Rendering: Includes a script to render animations to MP4 via Node.js, Chrome, and ffmpeg.
  • Character Framework: Includes pre-defined assets and logic for character views, emotions, and costumes.

Related

  • Project
    glanderness/BeefTV

    An AI-native video creation workspace that uses a node-based canvas to integrate multimodal generation and editing into a single, high-performance desktop application.

  • Project
    Alibaba-NLP/VRAG

    A multi-turn multimodal RAG framework that uses agentic reinforcement learning to enable VLMs to reason and retrieve information across text, images, and videos.

  • Project
    apify/mcpc

    mcpc is a lightweight, cross‑platform CLI that gives shell access to any Model Context Protocol (MCP) server, supporting full MCP features, persistent sessions, OAuth 2.1 security, JSON scripting, dynamic tool discovery, and experimental x402 payments.

  • Project
    J3n5en/EnsoAI

    EnsoAI is an Electron‑based desktop workbench that couples Git worktree management with persistent AI‑agent sessions (Claude, Gemini, Codex, etc.). It provides a built‑in Monaco editor, visual Git UI, 3‑way merge tool, and one‑click IDE bridging, enabling developers to work on multiple branches in parallel while each branch enjoys its own dedicated LLM context.