# Jiggle Wiggle

- **Event:** [Built with Opus 4.6: a Claude Code hackathon](https://cerebralvalley.ai/e/claude-code-hackathon)
- **When:** Feb 10 at 12:00 PM – Feb 17 at 10:00 AM (EST)
- **Where:** Location TBA
- **Team:** [Aryan Keluskar](https://cerebralvalley.ai/u/aryankeluskar)
- **GitHub:** https://github.com/cindyzli/jigglewiggle
- **Demo video:** https://www.youtube.com/watch?v=kL3udtWY1EE
- **Gallery:** https://cerebralvalley.ai/e/claude-code-hackathon/hackathon/gallery
- **Page:** https://cerebralvalley.ai/e/claude-code-hackathon/hackathon/gallery/57

Jiggle Wiggle is a real-time AI movement coach that works with three input modes: YouTube videos, live Zoom calls, and AI-generated references. Paste any dance or fitness video URL and the app downloads it, extracts reference poses frame-by-frame, and compares your webcam feed against the dancer in real-time with split-screen skeleton overlays and per-body-part scoring (arms, legs, torso). In Zoom mode, it captures an instructor's video feed and runs pose detection on both streams simultaneously, coaching you through matching their moves. An LLM-powered voice coach provides adaptive spoken feedback in real-time with specific limb-level corrections. Hand gesture controls let you interact without touching the keyboard. All pose detection runs entirely in-browser via MediaPipe WASM with no server-side GPU needed for the core experience, while SAM2 runs on Modal's A100 GPUs for video segmentation. Built with Next.js 16, React 19, TypeScript, OpenAI GPT-4o-mini, Groq, Zoom Meeting SDK.

---

Markdown version of https://cerebralvalley.ai/e/claude-code-hackathon/hackathon/gallery/57. Site index for agents: https://cerebralvalley.ai/llms.txt · full text: https://cerebralvalley.ai/llms-full.txt