DEV Community: Yagna Vyas

Receipt Sorter Pro: A Private Expense Tracker Powered by Local Qwen3

Yagna Vyas — Fri, 16 Oct 2026 18:35:14 +0000

This is a submission for the Hacktoberfest Open-Source AI Challenge Week 2: Side Hustle

What I Built

Receipt Sorter Pro is a private expense tracker for freelancers and small business owners. You upload receipts (.txt or text-based PDF) or paste the text, and a local open-weight model extracts the vendor, date, currency, tax, total, payment method, category, and line items.

Who would pay for it: a freelancer or shop owner who dreads sorting receipts at tax time but doesn't want to upload financial records to a cloud service.

What it gives them:

A dashboard with spending by category and month, plus top vendors
An editable review table to fix mistakes
A ⚠️ flag when the extracted total doesn't appear in the receipt
Vendor rules (for example, "uber" is always travel)
Duplicate detection
CSV and Excel export with summary sheets

Demo

I kept it local on purpose, because its main selling point is that your data never leaves your computer.

Code

Yagya443 / receipt-sorter

Local Receipt Sorter

This small Python tool reads .txt receipts from receipts/, asks a local Ollama model to extract the vendor, date, total, and category, then writes the results to output.csv and prints spending totals for each category.

Requirements

Python 3.9 or newer
Ollama installed and running locally
The qwen3:4b model pulled into Ollama (or another model selected in sorter.py)

Install the Python dependency:

python -m pip install -r requirements.txt

Download the default model if needed:

ollama pull qwen3:4b

Ollama must be running locally when you execute the sorter. If its service is not already running, start it in a separate terminal:

ollama serve

Run

Put one plain-text receipt per .txt file in the receipts/ folder, then run:

python sorter.py

The script uses Ollama's JSON response format and disables model thinking. It removes any <think>...</think> block if one appears and retries once when the response is invalid. The…

View on GitHub

How I Built It

Model: Qwen3 4B, an open-weight model, running locally through Ollama. The app lets you switch to any model you have installed (I also have qwen3:8b).
Structured output: the model is given a JSON schema, so it can only return valid fields and allowed categories. Thinking mode is turned off and the temperature is 0, and there is one automatic retry on bad output.
Safety checks:each extracted total must appear in the original receipt text, otherwise the receipt is flagged for review. Dates are normalised to YYYY-MM-DD, and currency codes are cleaned up (Rs. becomes INR).
App: Python, Streamlit for the web interface, SQLite for saved history, and pandas for the dashboard and exports.
Tools: I started with GitHub Copilot, which generated the first command-line version (sorter.py) from one detailed prompt. I then extended it into the web app with a database, dashboard, and editing features.

I tested it on 10 receipts in different formats, including rupee bills with GST, a USD cloud invoice, and two deliberately messy receipts. The testing found a real bug: 5/10/26 was read as May instead of October. I fixed it by parsing ambiguous dates day-first, and I added the editable table because small models will always make some mistakes.

Why Does Open Innovation Matter?

-Privacy: receipts are financial records. Because Qwen3 runs on the user's own laptop, nothing goes to a third-party server. For this audience, that's the whole point.

Cost: there are no per-receipt API fees. Processing 10 receipts or 10,000 costs the same, which is what makes this viable as an affordable tool for a small business.
Offline: it works with no internet connection.
Control: I can swap models, change the prompt, add vendor rules, and tune the categories for a specific niche. With a closed API, I'd be tied to someone else's pricing, model changes, and data policies. Where it was weaker: a 4B model is slower than a cloud API and makes more mistakes, especially with ambiguous dates. I handled that with validation, a review flag, and manual editing, rather than hiding the problem.

My Agent Session

My First User

Prize Categories

Run Club: Find your pace, your people, and a reason to get outside

Yagna Vyas — Sat, 10 Oct 2026 18:13:55 +0000

This is a submission for the Hacktoberfest Open-Source AI Challenge Week 1: Touch Grass

What I Built

Run Club is a running app that helps people plan a route and find others to run with. Runners can explore route options, connect with nearby people who have shared their availability, and organize group runs. If no one is available, they can create a public run that other runners can discover and join

Demo

https://run-club-tau.vercel.app/home

Code

https://github.com/Yagya443/Run-Club

How I Built It

The app uses React and Vite for the frontend, Express for the backend, and MongoDB with Mongoose for storing app data. It uses map and routing services to help runners plan routes.
For AI features, I use the open-weight Qwen3:4b model through Ollama running locally. It can help describe route options, explain why runners may be a good match, and generate a post-run reflection or suggestion for the next run. The app’s code handles route generation and matching scores; the AI adds natural-language explanations and suggestions

Why Does Open Innovation Matter?

Using an open-weight model lets me run AI locally and experiment with how it fits into the app without relying on a paid hosted AI API for each request. It also makes it easier to inspect the model setup and try a different model later.
Open tools across the stack helped me build the mapping, backend, database, and AI features as parts I can adapt as the project grows.

My Agent Session

Ollama running Qwen3:4b

Prize Categories

Best Use of Render

ThinkTrace - AI-Powered Adaptive Interview Platform

Yagna Vyas — Sun, 04 Oct 2026 23:21:02 +0000

This is a submission for the Hacktoberfest Weekend Challenge: Build for a Friend

What I Built

Demo

Code

How I Built It

ThinkTrace is built as a full-stack application.

Frontend

React
Vite
Tailwind CSS
React Router
Axios
Monaco Editor

Backend

Node.js
Express

AI

Ollama
GPT-OSS 20B (Open-Weight Model)
Ollama Cloud API

The core of ThinkTrace is built around open-weight AI models through Ollama
The application uses Ollama's API to communicate with the AI model. The model can be changed through environment configuration rather than being hard-coded into the application.

Why Does Open Innovation Matter?