craftpilot / README.md
skamathramesh's picture
Upload README.md with huggingface_hub
35fa336 verified
|
Raw
History Blame Contribute Delete
2.35 kB
---
title: CraftPilot
emoji: 🧢
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 β€” 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** β€” 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** β€” describes your craft item in detail
- **Cataloger** β€” extracts structured metadata (category, materials, colors, tags)
- **Copywriter** β€” generates product title, descriptions, and Instagram captions
- **Pricer** β€” suggests fair pricing based on materials, labor, and market rates
## Technical Details
- **Single model:** MiniCPM-V 2.6 (~8B) via llama.cpp β€” handles both vision and text
- **No cloud APIs** β€” everything runs locally
- **Streaming results** β€” pipeline streams as each agent completes
- **Agent traces** β€” full pipeline transparency in the Agent Traces tab
## Badges
- **Off the Grid** β€” no cloud API calls
- **Llama Champion** β€” all inference via llama.cpp
- **Sharing is Caring** β€” agent traces uploaded to HF dataset
- **Field Notes** β€” blog post about the build
Built for the Build Small Hackathon 2026 β€” Backyard AI track.