ReceiptFlow AI: The Zero-Cloud, Local-First Receipt Sorter for Freelancers
This is a submission for the Hacktoberfest Open-Source AI Challenge Week 2: Side Hustle What I Built Every tax season or quarterly review, I found myself facing the same chaotic chore: a desktop folder cluttered with scattered PDF invoices, train ticket receipts, cloud subscription receipts, and equipment purchases. When I looked for tools to automate this, I ran into two big dealbreakers:…
This submission entered the Hacktoberfest Open-Source AI Challenge Week 2: Side Hustle. The project is ReceiptFlow AI, a zero-cloud, local-first receipt sorter for freelancers. When tax season or quarterly reviews arrive, the user faces a chaotic desktop filled with scattered PDF invoices, train ticket receipts, cloud subscriptions, and equipment purchases.
The tool aims to automate this chore. Mainstream tools like Expensify, QuickBooks, or Dext charge $15 to $35 a month for scanning basic receipts, which the builder deems absurd for a freelancer. ReceiptFlow AI solves this problem by processing documents locally on-device, powered by open-weight models like Ollama, Gemma 2 2b for embedded text, and LLaVA 7B for images.
All metadata remains inside the browser's IndexedDB, with clean CSV exports generated client-side. No cloud databases, API bills, or data leaving the machine. The tool caters to freelancers under NDAs, indie builders tired of subscription charges, and frequent travelers who need to process receipts on the go. The data flow operates completely offline, with uploaded documents sent only to localhost FastAPI, not a hosted service.
The JSON data extracted by the model is stored in the browser's IndexedDB database. The complete codebase is open-source on GitHub.
Written by urgent.news from Dev.to's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
