The latest articles on DEV Community by Riya Rathi (@riyarathi2211). https://dev.to/riyarathi2211 https://media2.dev.to/dynamic/image/width=90,height=90,fit=cover,gravity=auto,format=auto/https:%2F%2Fdev-to-uploads.s3.us-east-2.amazonaws.com%2Fuploads%2Fuser%2Fprofile_image%2F4152151%2F93303e17-dd01-44ae-8269-6f92c782efc1.png https://dev.to/riyarathi2211 en Riya Rathi Sat, 17 Oct 2026 07:51:49 +0000 https://dev.to/riyarathi2211/billbuddy-4bc7 https://dev.to/riyarathi2211/billbuddy-4bc7 <p><em>This is a submission for the <a href="https://dev.to/challenges/hacktoberfest-week2-2026-10-12">Hacktoberfest Open-Source AI Challenge Week 2: Side Hustle</a></em></p> <h2> What I Built </h2> <p>Meet BillBuddy, a personal finance web app designed to make expense tracking and budgeting simpler.</p> <p>It is easy to lose track of small expenses throughout the month. BillBuddy brings transactions, budgets, and spending insights together in one place so users can understand where their money goes and make more informed financial decisions.</p> <h2> Demo </h2> <p><a href="https://bill-buddy-2jck0jz8l-riya-rathis-projects.vercel.app/" rel="noopener noreferrer">https://bill-buddy-2jck0jz8l-riya-rathis-projects.vercel.app/</a></p> <h2> Code </h2> <p><a href="https://github.com/riyarathi2211/billBuddy" rel="noopener noreferrer">https://github.com/riyarathi2211/billBuddy</a></p> <h2> How I Built It </h2> <p>I built BillBuddy using React and Vite, with a focus on a clean interface and a practical, responsive user experience.</p> <p>I organized the application into separate pages for the Dashboard, Documents, Budgets, Insights, Categories, and Export. This keeps the interface easy to navigate without overcrowding a single screen.</p> <p>Transactions are stored in IndexedDB, while budget settings are persisted in localStorage. Spending summaries, budget alerts, unusual-expense flags, and monthly forecasts are calculated from the available transaction history.</p> <p>Receipt scanning uses OCR to help extract text from uploaded receipts.</p> <p>AI and open-source model disclosure: The current Smart Insights functionality uses locally calculated rules and spending statistics. These features should not be described as generative AI unless an open-source AI model is actually integrated into the application.</p> <p>For this challenge, I would like to explore how open-weight models and local inference could further improve expense categorization, receipt understanding, and personalized financial recommendations without depending on a paid, closed AI API.</p> <h2> Why Does Open Innovation Matter? </h2> <h2> My Agent Session </h2> <p>Open innovation makes it easier for developers to experiment, learn from existing tools, and build useful applications without having to create every component from scratch.</p> <p>For a personal finance tool like BillBuddy, open-source libraries make features such as OCR, data visualization, and browser-side persistence more accessible.</p> <p>It also creates opportunities to experiment with open-weight AI models that can potentially run locally. This could reduce dependence on external services, improve user control over financial data, and make intelligent features more accessible to people with limited budgets.</p> <p>For me, open innovation is about making useful technology more accessible while giving developers the freedom to learn, customize, and improve it.</p> devchallenge hf26challenge Riya Rathi Sun, 11 Oct 2026 15:06:44 +0000 https://dev.to/riyarathi2211/campuswalk-28di https://dev.to/riyarathi2211/campuswalk-28di <p><em>This is a submission for the <a href="https://dev.to/challenges/hacktoberfest-week1-2026-10-05">Hacktoberfest Open-Source AI Challenge Week 1: Touch Grass</a></em></p> <h2> What I Built </h2> <h1> CampusWalk 🌿 — Touch Grass, One Quest at a Time! </h1> <p>CampusWalk turns ordinary outdoor time into meaningful mini-adventures.</p> <p>It is an AI-powered outdoor quest generator that helps students explore their campus, connect with nature, and take refreshing breaks from screens.</p> <h3> Features </h3> <ul> <li>🤖 AI-generated quests based on available time, activity, and difficulty</li> <li>🌱 Nature, walking, exploration, and photography challenges</li> <li>🏆 XP, achievements, and progress tracking</li> <li>📔 An adventure journal to save completed quests and reflections</li> </ul> <h3> Built With </h3> <p>React, Vite, JavaScript, Transformers.js, and an open-weight language model running in the browser.</p> <p><strong>Our goal:</strong> Make stepping outside feel like an adventure, one quest at a time!</p> <h2> Demo </h2> <p><a href="https://campus-walk-lk2mnd9rs-riya-rathis-projects.vercel.app/" rel="noopener noreferrer">https://campus-walk-lk2mnd9rs-riya-rathis-projects.vercel.app/</a></p> <h2> Code </h2> <p><a href="https://github.com/riyarathi2211/CampusWalk/tree/main/src" rel="noopener noreferrer">https://github.com/riyarathi2211/CampusWalk/tree/main/src</a></p> <h2> How I Built It </h2> <p>CampusWalk is an AI-powered outdoor quest generator designed to help students step away from their screens and explore the world around them.</p> <p>I built the frontend using React, Vite, and JavaScript, with a clean, nature-inspired interface. Users can choose an activity—Nature, Walking, Explore, or Photography—along with their available time and preferred difficulty.</p> <p>The AI component uses Transformers.js with the open-weight onnx-community/LFM2.5-350M-ONNX model. It runs inference directly in the browser using WebGPU, where supported, to generate personalized outdoor missions without relying on a hosted LLM API for each generation.</p> <p>I also built an achievement system with XP and unlockable badges, along with an Adventure Journal that stores completed quests and reflections locally on the user's device.</p> <h2> Why Does Open Innovation Matter? </h2> <p>Open innovation made it possible to build an AI-powered experience without depending entirely on a proprietary, closed-model API.</p> <p>Using an open-weight model with browser-based inference gives CampusWalk the potential to reduce dependence on external inference services, improve user privacy, and make experimentation more accessible. It also lets developers inspect the model's capabilities, explore different deployment options, and adapt the experience without being locked into a single hosted AI provider.</p> <p>For a project focused on encouraging people to engage with the real world, keeping the AI experience lightweight and accessible is an important part of the vision.</p> <h2> My Agent Session </h2> <p>CampusWalk uses browser-based model inference rather than a multi-step autonomous coding or tool-using agent. I don't have a DevRelay session link to share, so I'm leaving this section out.</p> devchallenge hf26challenge