DEV Community: Sandip Sahoo

Virtual Ofrenda Web App

Sandip Sahoo — Tue, 27 Oct 2026 14:16:27 +0000

Ghost in the Machine: Virtual Ofrenda 🕯️💀

This is a submission for the https://dev.to/challenges/hacktoberfest-week4-2026-10-26

What I Built

Virtual Ofrenda is an AI-powered digital memorial space inspired by the Mexican tradition of Day of the Dead (Día de los Muertos). The project allows users to create a personalized virtual altar for loved ones by uploading memories, stories, photos, and messages.

The theme "Ghost in the Machine" immediately made me think about how technology can preserve the stories, emotions, and memories of people long after they are gone. Instead of a ghost haunting a machine, I imagined memories living within the digital world, where AI helps transform personal stories into meaningful tributes.

Virtual Ofrenda serves as a bridge between remembrance and technology. Users can create beautiful digital offerings that keep stories alive and accessible for future generations.

Demo

🌐 Live Demo:
https://sandipsam2025.github.io/Virtual-Ofrenda/

🎥 Project Repository:
https://github.com/SandipSAM2025/Virtual-Ofrenda

👨‍💻 GitHub Profile:
https://github.com/SandipSAM2025

Code

The complete source code is available on GitHub:

Plain Text
https://github.com/SandipSAM2025/Virtual-Ofrenda

The project is fully open source and welcomes feedback, ideas, and community contributions.

How I Built It

The project was built using modern web technologies combined with open-source AI concepts to create an interactive memorial experience.

Technology Stack
HTML5
CSS3
JavaScript
GitHub Pages for deployment
Open-source AI-assisted development workflow
GitHub for version control and collaboration
Development Process
Designed a virtual altar interface inspired by traditional ofrendas.
Created interactive sections for stories, messages, and memory preservation.
Implemented a responsive and accessible web experience.
Used open-source AI tools during ideation, content generation, and feature refinement.
Deployed the final application through GitHub Pages.

The project focuses on demonstrating how open AI and web technologies can be used to preserve human memories in meaningful ways rather than simply automating tasks.

Why Does Open Innovation Matter?

Open innovation made this project possible by providing access to community-driven tools, ideas, and development resources.

With open-source AI and collaborative development:

Anyone can study how the system works.
Developers can improve, adapt, and expand the project.
New cultural traditions and memorial practices can be represented without relying on a closed platform.
Innovation happens faster because the community builds together rather than behind proprietary walls.

If this project had relied solely on a closed API ecosystem, customization and transparency would have been much more limited. Open-source tools empowered me to experiment freely and build something that reflects a personal interpretation of remembrance and digital legacy.

My Agent Session

During development, AI-assisted workflows helped with brainstorming, interface design ideas, content refinement, and project documentation.

Repository: https://github.com/SandipSAM2025/Virtual-Ofrenda

GitHub Profile: https://github.com/SandipSAM2025

The Spirit of It

A memorial is more than a collection of photographs. It is a place where stories continue to live.

Virtual Ofrenda explores the idea that memories do not disappear when someone is gone. Through digital experiences and AI-enhanced storytelling, fragments of a person's life can continue to inspire, comfort, and connect people.

For me, the true "Ghost in the Machine" is not a supernatural presence. It is the collection of memories, emotions, and stories that technology helps preserve. Every photograph, message, and shared memory becomes a small digital echo that keeps a person's legacy alive.

Prize Categories
Best Open-Source AI Project
Ghost in the Machine Challenge
Community Choice
Most Creative Use of Open AI Technology

Developed by: @SandipSAM2025
Project Repository: https://github.com/SandipSAM2025/Virtual-Ofrenda
Live Demo: https://sandipsam2025.github.io/Virtual-Ofrenda/

Sloth Desk

Sandip Sahoo — Thu, 22 Oct 2026 15:59:12 +0000

This is a submission for the Hacktoberfest Open-Source AI Challenge Week 3: Slow and Steady

What I Built

I built SlothDesk — an offline, zero-cloud desktop file cleaner and auto-organizer designed to reward total laziness.

Everyone dreads sorting their overflowing Downloads or Desktop folder. Messy downloads with cryptic names like receipt_9921_oct.pdf, assignment_final_v2.docx, and temp_scraper_v2.py sit around for weeks because manually inspecting, renaming, and filing them is tedious cognitive work.

SlothDesk lets you channel your inner sloth. It inspects file headers and text previews, asks a local open-weight model to semantically categorize and standardize the filenames, and automatically moves them into structured directories (such as Invoices & Finance, Coursework & Notes, Code & Dev, and Media). You kick back, take a nap, and let local open-source AI do all the digital chores in the background.

Demo

Live Interactive Demo: https://sandipsam2025.github.io/SlothDesk/

The web demo showcases the complete pipeline in action: an animated sloth companion, drag-and-drop clutter intake, real-time simulated offline inference streams, and instant reorganization into structured vaults.

Code

GitHub Repository: https://github.com/SandipSAM2025/SlothDesk

SandipSAM2025 / SlothDesk

SlothDesk 🦥

Slow & Steady Offline AI File Tidier
Channel your inner sloth — let open-source AI clean your digital clutter while you nap.

📌 Overview

SlothDesk is a zero-cloud, local desktop utility and interactive showcase designed for the "Slow and Steady" Open-Source AI Challenge (celebrating International Sloth Day).

Instead of wasting cognitive energy manually inspecting, renaming, and filing messy downloads (receipt_9921_oct.pdf, assignment_final_v2.docx, temp_scraper_v2.py), SlothDesk utilizes a compact local open-weight model (Llama 3.2 3B via Ollama) to semantically inspect file headers, generate descriptive names, and organize files into dedicated directory vaults automatically.

💡 Why Open Innovation Matters

Advantage	Why It Matters for SlothDesk
🔒 100% Zero-Leak Privacy	Invoices, medical records, tax receipts, and proprietary source code never leave your device. Model inference runs strictly against local memory with zero external telemetry.
⚡ True Offline Independence	Works reliably on airplanes, rural retreats, and during internet

…

View on GitHub

How I Built It

SlothDesk is built around open-source AI and local inference:

Local Inference Engine: Powered by Ollama running open-weight models locally (optimized for Llama 3.2 3B or Phi-3.5-mini).
Core Automation Daemon: Written in Python using the official ollama client library, os, and shutil. It reads a lightweight 200-byte preview snippet from each file and queries the local model with strict JSON schema constraints:


json
  {
    "category": "Invoices_and_Finance",
    "new_name": "Electricity_Bill_Oct2026.pdf"
  }

Listing Studio: Private Marketplace Copy with Local AI for Independent Sellers

Sandip Sahoo — Tue, 13 Oct 2026 17:04:14 +0000

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

What I Built

I built Listing Studio, a privacy-first product listing writer for independent sellers.

Small sellers often spend a lot of time writing product titles, descriptions, tags, and promotional copy for every item they list. Listing Studio helps sellers turn simple product notes into polished marketplace content for platforms such as Etsy, eBay, Depop, Shopify, and Instagram.

The seller enters:

Product name
Category
Condition
Materials and product details
Price
Target marketplace
Writing voice

Listing Studio then generates:

A marketplace-ready title
A product description
Searchable tags
Basic price positioning guidance

The result can be edited and copied directly into a marketplace listing.

This could be useful for Etsy sellers, handmade product creators, vintage sellers, jewelry makers, ceramic artists, digital product creators, and other small businesses that need to create many listings quickly.

Demo

Try the live demo here:

Listing Studio Demo

The application works directly in the browser. No account or installation is required for the default experience.

Code

The project is open source on GitHub:

Listing Studio Repository

My GitHub profile:

SandipSAM2025 on GitHub

The project uses a simple structure:

index.html for the application interface
style.css for responsive styling, themes, colors, and animations
script.js for the listing generator and interactions
README.md for project documentation

How I Built It

I built Listing Studio with plain HTML, CSS, and JavaScript so that it is lightweight, easy to understand, and easy to run.

The interface includes:

Responsive desktop and mobile layouts
Light mode and dark mode
Product image upload and drag-and-drop preview
Warm, Playful, and Minimal writing voices
Editable generated content
Copy-to-clipboard actions
Animated buttons and result transitions
Browser-based local storage for theme preferences

The project also includes an optional local AI integration through Ollama. When Ollama is installed, the application can send the product prompt to a locally running open-weight model such as Llama 3.2.

The default browser writer works without Ollama, so the application is still usable offline and without an API key. The local AI path allows sellers to use an open-weight model on their own computer instead of depending on a hosted AI provider.

Why Does Open Innovation Matter?

Open innovation matters because independent sellers may enter private product information, business ideas, pricing details, customer-related information, and unreleased designs into a writing tool.

A local-first approach gives sellers more control:

Product details do not need to be sent to a hosted AI company.
Sellers can run an open-weight model on their own computer.
They can change the model or prompt without being locked into one provider.
They can avoid usage-based AI API costs.
The project can continue working without an internet connection.
The code is simple enough for sellers and developers to inspect and customize.

A closed AI API could generate similar text, but it would require sending the prompt to an external service and could introduce API costs, privacy concerns, rate limits, and vendor lock-in.

Listing Studio demonstrates how open tools can make a small, practical business workflow more private, flexible, and affordable.

Prize Categories

Open-source AI
Local-first AI
Privacy-focused AI
Side Hustle*This is a submission for the Hacktoberfest Open-Source AI Challenge Week 2: Side Hustle*

🌿 FrostBite: Offline AI Garden Scout

Sandip Sahoo — Wed, 07 Oct 2026 17:38:08 +0000

🌿 FrostBite: Offline Open-Weight Garden Scout

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

📖 What I Built

FrostBite is a lightweight, zero-cloud CLI tool that helps gardeners step away from the screen and into the soil.

Runs 100% offline on your machine — no internet required.
Accepts your USDA hardiness zone or region and looks up historical frost benchmark dates locally.
Prompts a locally running open-weight SLM (smollm2:1.7b) to output a concise 5-step outdoor gardening checklist.
Renders the checklist in an ASCII index-card format directly in your terminal and saves it as garden_todo.txt.

This way, you can fold the slip, pocket a pencil, close your laptop, and head outdoors. It’s designed for gardeners, hobbyists, and anyone who wants to spend less time staring at screens and more time tending to nature.

🎥 Demo

👉 Live Demo Repo

💻 Code

👉 GitHub Repository

🛠️ How I Built It

Language: Python 3.10+
Inference Engine: Ollama (local loopback at http://localhost:11434)
Model: smollm2:1.7b — ultra-compact 1.7B parameter open-weight model designed for fast, local CPU/RAM inference.
Dependencies: requests for local REST communication.
Offline Frost Data: USDA hardiness zones & frost benchmark lookup table.
CLI Workflow: Python scripts (garden_cli.py, frost_data.py) generate the ASCII checklist and save it locally.

🌱 Why Does Open Innovation Matter?

Closed APIs often require subscriptions, internet connectivity, or send your personal data to external servers. With open-weight models and local inference:

Privacy: All data stays on your device.
Accessibility: Free to run, no API costs.
Customization: Fine-tune for your region’s frost dates and local crops.
Resilience: Works offline in the field, even with no signal.

Open innovation made it possible to build a tool that is practical, portable, and empowering for everyday gardeners.

🧑‍💻 My Agent Session

I used a local agent workflow to dispatch prompts to smollm2:1.7b via Ollama. The session generates structured, actionable outdoor tasks in under 3 seconds — keeping the screen time minimal and the outdoor time maximal.

🏆 Prize Categories

Best Use of Open-Source AI
Touch Grass Challenge
Sustainability & Environment

✨ Closing Note

FrostBite embodies Hacktoberfest’s Touch Grass theme: the screen is the shortest part of the experience. You grab your slip, then head outside to garden.

Built with ❤️ by Sandip.

Study Mate

Sandip Sahoo — Sun, 04 Oct 2026 17:57:24 +0000

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

What I Built

I built StudyNotes – Student Learning Hub, a lightweight, responsive, and distraction-free study portal designed for my college friend and roommate, Alex.

Alex is an undergraduate student preparing for rigorous semester examinations. Like many learners, they were constantly overwhelmed by multi-hundred-page lecture slides, fragmented group chat notes, and bloated educational platforms filled with pop-up ads, trackers, and mandatory login walls.

StudyNotes solves this problem by serving as an instant, zero-friction revision companion that:

Organizes syllabus concepts across core subjects (Data Science, Web Technology, Machine Learning, Cyber Security, Software Engineering, and Human Resource Management) into clear, bite-sized study cards.
Highlights crucial definitions, key formulas, and exam takeaways tagged with visible "Important for Exam" badges.
Features a live client-side search engine that filters across subjects, topics, and technical keywords without requiring a backend.
Includes a native Dark/Light mode toggle that protects students' eyes during late-night cram sessions and remembers preference via localStorage.

Demo

Live Web App:https://sandipsam2025.github.io/studymate/#notes
Preview: Fully responsive, accessible, card-based interface with live keyword filtering, instant topic switching, and dynamic theme persistence.

Code

You can view the full source code, inspect the vanilla architecture, or fork the repository on GitHub:

SandipSAM2025 / studymate

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

What I Built

I built StudyNotes – Student Learning Hub, a lightweight, responsive, and distraction-free study portal designed for my college friend and roommate, Alex.

StudyNotes solves this problem by serving as an instant, zero-friction revision companion that:

Organizes syllabus concepts across core subjects (Data Science, Web Technology, Machine Learning, Cyber Security, Software Engineering, and Human Resource Management) into clear, bite-sized study cards.
Highlights crucial definitions, key formulas, and exam takeaways tagged with visible "Important for Exam" badges.
Features a live client-side search engine that filters across subjects, topics, and technical keywords without requiring a backend.
Includes a…

View on GitHub

Repository: https://github.com/SandipSAM2025/studymate
Main Branch: https://github.com/SandipSAM2025/studymate/tree/main

How I Built It

To keep the application beginner-friendly, bloat-free, and instantly deployable without server costs or maintenance overhead, I built the entire system using core web fundamentals:

Frontend Architecture:
- HTML5: Clean, semantic structure with accessible navigation, landmarks, and ARIA labels.
- CSS3: Custom responsive design using modern CSS Grid and Flexbox, powered by CSS custom properties (variables) for smooth light/dark mode transitions.
- Vanilla JavaScript: Event-driven architecture implementing real-time input filtering, array queries, dynamic DOM rendering, and localStorage state management.
Open-Source AI & Development Workflow:
- To draft, organize, and refine the educational dataset into concise revision summaries and high-yield exam takeaways, I used open-weights models (Llama 3 / Mistral via local inference).
- Local inference allowed rapid iteration over subject metadata and keyword taxonomy offline, ensuring complete data privacy with zero token limits or API subscriptions.

Why Does Open Innovation Matter?

Open innovation is essential for educational equity:

Unrestricted Learning Access: Proprietary ed-tech tools increasingly lock revision notes behind subscriptions, ads, and paywalls. Using an open-source, zero-dependency model ensures that any student worldwide can access, fork, and self-host this learning hub for free.
Privacy and Offline Independence: Leveraging open-source AI locally ensures that student notes, curricula, and revision workflows are generated privately without exposing academic data to commercial cloud platforms.
Inspectability & Community Growth: Because the codebase uses pure HTML, CSS, and Vanilla JS, beginner developers and classmates can easily audit the code, contribute new subject modules, or adapt the repository for their own university curriculum.

My Agent Session

Development and code review were facilitated using an open-agent workflow, focusing on clean separation of concerns, strict zero-dependency requirements, and mobile-first responsiveness.

Prize Categories

Best Project Built for a Friend
Most Impactful Open Source Learning Tool