pfft...yet another finance tracker? think again :)
This is a submission for the Hacktoberfest Weekend Challenge: Build for a Friend Why I Built Living in India, we heavily utilise UPI for payments. The introduction of UPI, and 10-minute delivery apps have made spending money so easy and comfortable that it has made spendings get a little out of hand. We don't realise how much money we're spending on a day-to-day basis. I noticed my dear…
This is a finance tracker designed specifically for iPhone users in India, created to help individuals keep track of their spending without manually logging expenses. The app utilizes text messages to automatically read bank transactions, making it a privacy-focused solution that never requests access to all messages. Using iOS Shortcuts app automation, the app processes only the permitted messages, ensuring users' financial data remains private.
The app categorizes transactions through AI using an open-weight model that runs on a Mac at home, keeping the data secure and not exposing it to any AI company. The demo video allows users to see the app in action, and the code repository for the project can be found on GitHub. Building this project involved several components, including message parsers, transaction categorization using an open-weight model, and an iOS app interface.
Privacy is a significant aspect of this project, as SMS transactions are sensitive data, and by keeping the processing local and using open-weight models, users maintain control over their financial information.
The author, Anmol, expressed concerns about logging his transactions in the app's database. However, the author assured him that the data will eventually be stored on-device for maximum privacy. The project originally aimed to be a web app but was adapted into a native iOS app due to Anmol's preference for the Apple ecosystem. The app's appearance follows a clean, liquid glass style design, appealing to Anmol's appreciation for visually appealing interfaces.
This project highlights the importance of privacy in financial tracking and showcases the potential of using open-weight models for local processing.
Written by urgent.news from Dev.to's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
