--- title: CraftPilot emoji: ๐Ÿงถ colorFrom: yellow colorTo: red sdk: gradio sdk_version: 6.16.0 app_file: app.py python_version: "3.10" pinned: false license: mit tags: - build-small-hackathon - backyard-ai - off-the-grid - llama-champion - sharing-is-caring - field-notes - craft - vision - multi-agent - llama-cpp - minicpm - hackathon - track:backyard - sponsor:openbmb - achievement:offgrid - achievement:llama - achievement:sharing - achievement:fieldnotes datasets: - skamathramesh/craftpilot-traces --- # CraftPilot โ€” AI-Powered Craft Business Assistant Upload a photo of your handmade craft. Get a complete marketplace listing with catalog data, product descriptions, social captions, and fair pricing. **Built for someone I know** โ€” a creative introvert who does crochet, painting, embroidery, and sewing but struggles to write product listings and price her work fairly. ## Links - **Demo Video**: [Watch on Google Drive](https://drive.google.com/file/d/1RwCmAR6ozSrFYeIi6py8SGDR8j-sJ614/view) - **Social Post**: [LinkedIn](https://www.linkedin.com/posts/activity-7470209185532493824-sE5M) - **Blog (Field Notes)**: [CraftPilot Blog](https://huggingface.co/blog/build-small-hackathon/craftpilot) ## How it works 1. Upload a craft photo 2. Select craft type 3. (Optional) Add notes, material cost, time spent 4. Click "Analyze My Craft" The AI runs a multi-agent pipeline, all powered by a single model: - **Vision** โ€” describes your craft item in detail - **Cataloger** โ€” extracts structured metadata (category, materials, colors, tags) - **Copywriter** โ€” generates product title, descriptions, and Instagram captions - **Pricer** โ€” suggests fair pricing based on materials, labor, and market rates ## Technical Details - **Single model:** MiniCPM-V 2.6 (~8B) via llama.cpp โ€” handles both vision and text - **No cloud APIs** โ€” everything runs locally - **Streaming results** โ€” pipeline streams as each agent completes - **Agent traces** โ€” full pipeline transparency in the Agent Traces tab ## Badges - **Off the Grid** โ€” no cloud API calls - **Llama Champion** โ€” all inference via llama.cpp - **Sharing is Caring** โ€” agent traces uploaded to HF dataset - **Field Notes** โ€” blog post about the build Built for the Build Small Hackathon 2026 โ€” Backyard AI track.