Genpark Lens

An open-source Visual Agent that turns any image into a structured curiosity engine, featuring 4 dimensions of insight. Distilled from the core concepts of Chance AI.

GenPark Lens proves that advanced visual agents and multi-modal "lenses" don't require millions of dollars in VC funding or a proprietary app. With the right prompt engineering and an open agent framework, you can instantly analyze any image across four dimensions: Identifier, Utility, Insight, and Vibe.

Features: The 4 Lenses

1. 🔍 The Identifier Lens: What exactly is in this image? (Objects, text, scene, art style).
2. 🛠 The Utility Lens: If it's a menu, translate it. If it's code, extract it. If it's a math problem, solve it.
3. 💡 The Insight Lens: OOTD fashion breakdown, nutritional estimation for food, architectural history, etc.
4. ✨ The Vibe Lens: A tiny, creative poem or witty observation about the mood of the image.

Installation for OpenClaw

Just clone this repository into your skills directory and invoke it:

openclaw use genpark-lens --image "/path/to/my-photo.jpg"

Built by the GenPark open-source community.