This is my submission for the Hacktoberfest Open-Source AI Challenge — Week 2: Side Hustle.
What I Built
Ledgerly is a Smart Invoice Organizer designed to help freelancers and small business owners manage invoices, receipts, and expenses more easily.
Manually organizing receipts and extracting expense details can be time-consuming. Ledgerly aims to simplify this process by allowing users to upload documents, extract information, organize expenses, and review their spending through a dashboard.
Features
- Invoice and receipt processing: Upload documents for text extraction.
- OCR integration: Use Tesseract.js to extract text from supported documents.
- AI-assisted extraction: Optional integration with a locally runnable Ollama model (Qwen), depending on configuration.
- Expense dashboard: Review and organize extracted expense information.
- CSV export: Export expense records for further analysis.
Tech Stack
- Frontend: React, Vite, CSS
- Backend: Node.js, Express.js
- OCR: Tesseract.js
- Open-weight AI: Ollama with Qwen (optional)
- Database: MongoDB, with an in-memory fallback
Why Open Innovation Matters
Invoices and receipts can contain sensitive financial information. Using a locally runnable open-weight model can help reduce reliance on external AI APIs and may improve privacy by keeping processing local when the application is configured accordingly.
Open-source tools also give developers more flexibility to inspect, customize, and adapt their software instead of depending entirely on a closed service's pricing and limitations.
My goal with Ledgerly is to explore how open-source AI can make everyday financial organization more accessible to freelancers and small businesses.
Who Could Benefit?
Freelancers, independent developers, and small business owners who want a simpler way to organize their receipts and expenses.
Links
GitHub repository: https://github.com/prakharsaraswat07/smart-invoice-organizer
Screenshots: Add screenshots of the working application.
Future Improvements
- Improve extraction accuracy for scanned invoices and complex PDFs.
- Add more reliable expense categorization.
- Improve validation and handling of missing or incorrect invoice details.
- Make the setup process easier for new users.
This project is part of my exploration of practical applications of open-source AI through the Hacktoberfest 2026 Week 2: Side Hustle challenge.
devchallenge #hf26challenge4
Top comments (0)