Summary
Connects Claude to the Embassy of the Free Mind's collection of 15,000 rare pre-modern texts, all translated to English. The corpus spans philosophy, religion, science, and literature from before the modern era. Search operations hit the sourcelibrary.org API, which runs on a Next.js stack with MongoDB Atlas for storage and Google Gemini handling OCR and translation of the original manuscripts. Reach for this when you need primary sources from historical periods or want to query obscure philosophical and religious texts that aren't in standard training data. The underlying system processes images through a pipeline that splits two-page spreads, extracts text, translates, and summarizes.
Keep your Mac awake while Claude Code and 40+ AI agents run. Sleeps when they're idle.
One time payment $9 →
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
On Capafy, your Skill runs online 24/7 as an agent product, and you get paid every time someone uses it.
Start earning →
Source Library v2
A Next.js application for digitizing and translating historical texts. Built for the Embassy of the Free Mind.
Stack
- Framework: Next.js 14 (App Router)
- Database: MongoDB Atlas
- AI: Google Gemini for OCR and Translation
- Storage: Vercel Blob for images
- Deployment: Vercel
Getting Started
npm install
npm run dev
Architecture
Image System
All page images go through /api/image for consistent sizing and cropping:
| Tier | Size | Quality | Use Case |
|---|---|---|---|
| Thumbnail | 400px | 70% | Grid views, page navigation |
| Display | 1200px | 80% | Main reading view |
| Full | 2400px | 90% | Magnifier, fullscreen |
Split Pages
Books with two-page spreads can be split. Each page stores:
crop.xStartandcrop.xEnd(0-1000 scale)cropped_photo(optional pre-generated Vercel Blob URL)
Cropping happens on-demand via Sharp. OCR automatically crops inline and saves the result for future use.
Processing Pipeline
- Import - Upload images or import from Internet Archive
- Split - Detect and split two-page spreads (ML or manual)
- OCR - Extract text using Gemini Vision
- Translate - Translate to English using Gemini
- Summarize - Generate summaries and key themes
Key Directories
src/
├── app/ # All routes, pages, and API endpoints
│ ├── api/ # API routes
│ ├── book/ # Book pages (detail, read, pipeline)
│ └── page.tsx # Homepage
├── components/ # Reusable React components
├── hooks/ # Reusable React hooks for component logic
└── lib/ # Business Logic, Utilities (mongodb, ai, types), and Services
Featured
Keep your Mac awake while Claude Code and 40+ AI agents run. Sleeps when they're idle.
One time payment $9 →Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →On Capafy, your Skill runs online 24/7 as an agent product, and you get paid every time someone uses it.
Start earning →
