DEV Community: Abhishek J N

SpecterOS: Ghost in the Machine

Abhishek J N — Thu, 29 Oct 2026 14:18:11 +0000

This is a submission for the Hacktoberfest Open-Source AI Challenge Week 4: Ghost in the Machine

What I Built

For Hacktoberfest Week 4, where Halloween on October 31 meets Día de los Muertos on November 1 and 2, I built SpecterOS: Ghost in the Machine — an open-source AI sanctuary and haunted computing suite that explores what happens when code outlives its creators, and how open innovation keeps human memory alive when machines go dark.

SpecterOS unites the chilling thrills of Halloween with the reverent beauty of Día de los Muertos through four interconnected experiences:

🕯️ The Digital Ofrenda Sanctuary

A three-tiered Día de los Muertos altar where users can light interactive glass veladoras, watch cempasúchil (marigold) petals drift across the screen with wind physics, and honor computing ancestors such as Ada Lovelace, Alan Turing, Grace Hopper, Dennis Ritchie, Aaron Swartz, and John McCarthy, alongside personal mentors and departed loved ones.

It also includes an AI-powered Calaverita and remembrance verse composer that crafts poetic tributes inspired by traditional Mexican verse.

💀 NecroShell — The Possessed Terminal

A retro VT100 phosphor CRT terminal possessed by departed system daemons. Keystrokes glitch, and commands such as whoami, ps aux, cat soul.txt, and resurrect uncover ghostly memory sectors while departed spirits whisper eerie commentary in response to commands.

🔮 The Spirit Séance Chamber

An offline-capable, open-weight-model-ready séance room that channels the spirits of long-dead programming languages and platforms, including ALGOL 68, Macromedia Flash / ActionScript 3, COBOL 60, HyperCard 1987, LISP 1.5, and Turbo Pascal.

Each encounter combines historical context, vintage syntax incantations, and a little grudge-holding wit.

🏚️ Poltergeist IoT Log Weaver

A supernatural horror engine that ingests anomalous smart-home sensor telemetry — hallway PIR motion at 3:14 AM, a rapid temperature plunge from 71°F to 48°F, nursery baby-monitor acoustic spikes, and unexpected interior deadbolt activity — and weaves these events into a chilling short story about what might have walked through your home while you were asleep.

The central idea behind SpecterOS is simple: What if our machines could preserve the memories of the people, ideas, and digital worlds that created them?

Demo

Experience the live application here:

specteros-ghost-in-the-machine.ai.studio

Features to try:

Light and extinguish the veladoras on the Digital Ofrenda to hear the synthesized match strike and church chime.
Enter necrofetch, whoami, or resurrect in NecroShell with phosphor CRT mode enabled.
Commune with ALGOL 68 or Macromedia Flash in the Spirit Séance Chamber.
Generate a ghost story from the 3:14 AM IoT anomaly log.

Code

The complete source code is open-source under the Apache-2.0 license.

JNAbhishek27 / SpecterOS-Ghost-in-the-Machine

Open-source AI séance chamber, Día de los Muertos digital ofrenda, possessed CRT terminal, and spooky IoT sensor story weaver built with open-weight models and Web Audio synthesis.

SpecterOS: Ghost in the Machine 🕯️💀

An open-source AI séance chamber, Día de los Muertos digital ofrenda, possessed CRT terminal, and spooky IoT ghost story weaver built for Hacktoberfest 2026.

🌟 Overview

Built for Hacktoberfest 2026: Week 4 ("Ghost in the Machine"), bridging Halloween on October 31 with Día de los Muertos on November 1 & 2.

SpecterOS explores what happens when code outlives its creators, and how open innovation preserves memory when machines go dark. It blends the reverence of authentic Mexican Día de los Muertos ofrendas with the nostalgic terror of vintage computing and haunted domestic telemetry.

✨ Core Features

1. 🕯️ The Digital Ofrenda Sanctuary (Día de los Muertos)

Interactive 3-Tier Altar: Represents Heaven, Limbo, and Earth in traditional Mexican ofrenda architecture.
Interactive Veladoras (Glass Candles): Programmatic flickering flame physics that ignite or extinguish with a click, accompanied by authentic audio match strikes.
Drifting…

View on GitHub

Key files:

src/components/DigitalOfrenda.tsx — Interactive three-tier altar with veladora flame mechanics, custom memorial forms, and Calaverita generation.
src/components/NecroShell.tsx — VT100 phosphor CRT emulator with customizable color tubes, scanlines, and possessed command interceptors.
src/components/SeanceChamber.tsx — Entity communion engine with vintage persona prompts and historical code inscriptions.
src/components/IoTGhostStory.tsx — Forensic sensor log table and timestamped supernatural story generator.
src/utils/spectralAudio.ts — Client-side Web Audio API synthesizer for match strikes, marigold bells, and eerie ambient drones.
server.ts — Express full-stack backend with Gemini 3.8 Flash model routing and offline emulation fallbacks.

How I Built It

SpecterOS is architected around open-source AI principles, offline resilience, and immersive browser-native experiences.

1. Open-Weight AI and Historical Persona Prompts

The séance personas and possessed-terminal commentary use structured prompts designed to work with open-weight models such as Google Gemma and compatible local transformer runtimes.

The prompts capture historical programming conventions and recognizable syntax patterns, including ALGOL-style syntax, ActionScript ENTER_FRAME loops, and COBOL identification divisions.

The goal is to make each interaction feel like communicating with a distinct piece of computing history rather than a generic chatbot.

2. Graceful Offline and Local Emulation Fallbacks

Every AI endpoint includes a deterministic local emulation engine. If the network becomes unavailable, the server is offline, or no API key is configured, the séance, terminal, and story-generation experiences can continue using local fallback logic.

This design prioritizes resilience and ensures that the core experience does not depend entirely on a remote model provider.

3. Full-Stack Vite and Express Architecture

The application uses Vite and Express for development, production asset bundling, and REST API routing.

Key endpoints include:

/api/seance/chat
/api/ofrenda/poem
/api/iot/story
/api/terminal/ghost

The architecture keeps the frontend interactive while allowing the backend to route AI requests and provide fallback responses.

4. Browser-Native Audio Synthesis

Instead of relying on external MP3 files that may fail to load offline, SpecterOS synthesizes its sound effects in real time using the browser's Web Audio API and AudioContext.

The soundscape includes flickering-flame ignition, CRT keyboard clicks, altar bell chimes inspired by a 528 Hz tone, and low-frequency spectral drones.

5. Curatorial Design and Cultural Inspiration

The interface uses Tailwind CSS and follows a museum-inspired editorial design philosophy, with Fraunces serif typography, restrained metadata styling, and visual motifs inspired by Mexican ofrenda traditions.

The intention is to make the experience feel like a digital sanctuary rather than a conventional developer dashboard.

Why Does Open Innovation Matter?

For SpecterOS, open innovation is not merely a technology choice. It is part of the project's underlying philosophy.

The Séance Works with the Lights — and the Internet — Off

Halloween storms and power outages should not automatically make an application unusable.

By designing for open-weight models and local execution, SpecterOS can support environments where connectivity is unreliable or unavailable, provided the necessary model runtime and dependencies are installed.

A closed, cloud-only API can fail when its service becomes unavailable. A locally running model can offer a path toward continued operation without relying on a remote inference endpoint.

Sacred Memories Should Remain Private

On Día de los Muertos, families place photographs, favorite foods, and personal memories of departed loved ones on their ofrendas.

These memories deserve thoughtful privacy protections. An architecture that supports local processing can help users keep sensitive memorial content on their own devices instead of automatically sending it to an external AI service.

Local execution does not guarantee privacy by itself, but it gives developers greater control over where personal data is processed and stored.

Rescuing Digital Culture from Corporate Obsolescence

Proprietary platforms can disappear when companies discontinue them. The end of Macromedia Flash, for example, created major preservation challenges for browser games, interactive art, and other digital experiences built around the technology.

Open-source software, documented formats, and accessible model implementations can help communities preserve, study, and revive digital culture beyond the lifespan of any single vendor.

Model Swappability and Zero Vendor Lock-In

SpecterOS is designed around a replaceable AI layer rather than treating one proprietary provider as the permanent foundation of the project.

With compatible integrations, the prompt harnesses can be adapted to open-weight models such as Gemma running locally or on edge hardware, including appropriately provisioned Raspberry Pi systems.

This approach gives developers more flexibility over inference, deployment, privacy, and long-term operating costs.

Open innovation makes SpecterOS more than a Halloween experiment: it makes digital preservation, local experimentation, and community-driven development part of the experience itself.

The Spirit of It

During testing, I placed a memorial for my grandfather on the Digital Ofrenda, noting his favorite offerings: pan dulce and strong black coffee.

When the Calaverita generator returned these lines:

Orange petals carpet the dark flagstone floor,

A path of marigolds from the hearth to the door.

The veladoras flicker in gentle golden light,

As the veil grows thin on this holy autumn night...

The synthesized match struck. The flame flickered. And, for a quiet second in a dark room, technology did not feel like cold silicon and corporate profit.

It felt like memory made tangible.

That moment captures what I wanted SpecterOS to explore: technology can do more than automate tasks or generate content. It can help us preserve stories, celebrate the people who shaped our lives, and revisit the digital worlds that might otherwise disappear.

The project brings together two seemingly different traditions: Halloween's fascination with ghosts and Día de los Muertos' celebration of remembrance. Both invite us to think about what remains after someone or something is gone.

In SpecterOS, the ghosts are not just supernatural characters. They are the lingering influence of programmers, the forgotten syntax of obsolete languages, the memories we preserve, and the code that continues to run long after its original creators have moved on.

That is the ghost in the machine.

Prize Categories

SpecterOS is intended for consideration in the following partner categories:

Best Use of Gemma: Open-weight persona reasoning designed for local and edge inference using Google's Gemma model.
Best Use of Render: Production-oriented deployment of a full-stack Express and Vite application.
Best Use of Sentry Agent Tracing: The Poltergeist IoT module simulates forensic trace analysis through anomalous, timestamped events inspired by distributed transaction tracing.
Best Use of DigitalOcean: A lightweight deployment approach intended to support resource-conscious environments and appropriately provisioned GPU Droplets.
Best Use of Backboard: Structured knowledge retrieval intended to ground séance personas in authentic computing history.

Thank you for exploring SpecterOS — where open-source AI meets forgotten code, digital folklore, and the memories that refuse to fade.

Some ghosts deserve to stay online.

SlothOps: The Open-Source AI Suite That Rewards Pure Laziness

Abhishek J N — Fri, 23 Oct 2026 01:35:06 +0000

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

What I Built

Traditional hackathons glorify caffeine-fueled coding sprints. But Week 3 of Hacktoberfest invites us to embrace a different philosophy: channel our inner sloth and build tools that do the work so we don't have to.

SlothOps — The Open-Source AI Suite That Rewards Pure Laziness is a local-first productivity sanctuary designed to automate the daily micro-chores that developers and remote workers dread most.

It brings four lazy-friendly tools together:

Morning Chat Sloth: Distills busy group conversations into a crisp two-line summary, highlights action items assigned to you, and offers one-click canned replies. Designed for chat workflows involving platforms such as WhatsApp, Discord, and Slack.
Fridge Stare Eliminator: Turns leftover ingredients into simple one-pan recipes with minimal steps and a grocery checklist for missing staples.
Desktop & File Hoard Tidier: Categorizes messy files into meaningful folders, standardizes filenames using ISO dates, flags temporary installers, and generates a script to help automate file reorganization.
Offline Sloth Snooze Companion: Generates ambient soundscapes directly in the browser using the Web Audio API, with a sleep timer, a breathing pacer, and bedtime stories.

The philosophy is simple: automate the repetitive work, reduce decision fatigue, and leave yourself more time for the things that matter.

Demo

Live application:

slothops-ai.ai.studio

Try the built-in presets:

The Chaotic Friday Dinner Group
The Sad Post-Hackathon Fridge
The Chronic Screenshot Hoarder

These sample scenarios let you explore the different SlothOps workflows without preparing your own data.

Code

GitHub repository:

JNAbhishek27 / SlothOps

Open-weight AI that rewards laziness: group chat summaries, 1-pan pantry recipes, 1-click desktop cleaning, and offline wind-down soundscapes. Built for Hacktoberfest 2026.

🦥 SlothOps — Slow and Steady Open-Source AI Studio

Built for Hacktoberfest 2026: Week 3 DEV Challenge ("Slow and Steady")
In celebration of International Sloth Day: Build something with open-weight models or open-source AI that rewards pure laziness.

📖 Overview

Traditional hackathons reward frantic 48-hour caffeine-fueled coding marathons. But Week 3 of Hacktoberfest 2026 posed a much wiser prompt:

"Tomorrow, October 20, is International Sloth Day, and we think sloths have it figured out. They move at their own pace, conserve their energy, and even help moderate our website. This week, we want you to channel your inner sloth and build something that does the work so you don't have to."

SlothOps is a local-first, open-source productivity suite that systematically eradicates the tedious micro-tasks developers and remote workers dread. It runs locally on your machine, keeps your personal conversations and files private, and costs $0.00 to operate.

⚡ The 4
…

View on GitHub

Built with:
Frontend: React 19, TypeScript, Tailwind CSS, Lucide Icons, and Motion.
Audio synthesis: Web Audio API for real-time procedural sound generation, noise generators, filters, and oscillators.
Backend: Express server with Vite middleware.
AI integration: Google Gemma open-weight model workflows, with an @google/genai integration described in the project architecture.
Tabular intelligence: Prior Labs TabPFN-3.5, as described in the proposed integration.

How I Built It

SlothOps combines AI-assisted productivity workflows with browser-based audio synthesis, aiming to minimize repetitive work while keeping the user in control.

1. Local and Open-Weight AI

The project is designed around Google Gemma 2, with 2B and 9B model variants identified as target options for supported local inference.

The AI workflows focus on:

Summarizing group conversations and extracting actionable tasks.
Generating recipes that respect available ingredients and minimize cleanup.
Classifying files and proposing structured filenames.
Returning structured outputs that the application can validate and display.

The architecture also describes an @google/genai bridge. Any workflow that uses a hosted Gemini API should be distinguished from genuine local Gemma inference, since using an open-weight model and using a cloud API are not the same thing.

2. Tabular Intelligence with TabPFN

The project identifies Prior Labs TabPFN-3.5 as a foundation-model component for tabular workflows, including file-metadata analysis and potential predictions related to organization effort.

Its role should be tied to the actual implemented pipeline: TabPFN is a tabular modeling tool, not a general-purpose replacement for a language model used for summaries or recipe generation.

3. Procedural Audio with the Web Audio API

Instead of downloading or streaming prerecorded audio files, SlothOps can generate ambient sound effects directly in the browser.

The soundscape design includes:

Gentle Canopy Rain: Pink noise shaped with a low-pass filter to evoke rainfall.
Forest Wind: Brownian-style noise modulated by a slow 0.12 Hz low-frequency oscillator.
Binaural audio: A 136.1 Hz carrier paired with a 140.1 Hz oscillator, producing a nominal 4 Hz frequency difference.
Sleep timer: Gradually fades the generated audio when the timer ends.
Breathing pacer and bedtime stories: Additional features intended to support a calmer bedtime routine.

The audio engine does not need external audio files. However, the Web Audio features alone do not establish that every AI-powered workflow operates offline.

Why Does Open Innovation Matter?

Personal productivity tools often handle surprisingly intimate information. Group chats may contain family conversations and financial arrangements, while desktop folders may contain invoices, contracts, and private documents.

Open innovation creates opportunities to build tools that give users more control over how that information is processed.

Privacy and data sovereignty: Running a compatible open-weight model locally can allow sensitive inputs to remain on the user's machine, provided the complete processing pipeline is local and does not transmit data to external services.
Reduced recurring costs: Local inference can avoid per-token API charges, although users still need suitable hardware and may incur electricity or hosting costs.
Offline resilience: Browser-generated soundscapes and local file operations can work without an internet connection. AI features also need locally available models and a functioning local inference runtime to work offline.
Freedom to experiment: Open-weight models let developers explore different model sizes and deployment approaches without making one proprietary AI API the only option.

For SlothOps, open innovation is about making everyday automation more accessible while giving users greater choice over where their data goes and how their tools operate.

My Agent Session

The development workflow used AI-assisted iteration to bring together the SlothOps interface, productivity workflows, and browser-based audio features.

The project architecture and design goals include:

Framework: React 19, TypeScript, Express, and Tailwind CSS.
AI model targets: Google Gemma 2 open-weight models.
Additional model component: Prior Labs TabPFN-3.5 for tabular workflows.
Audio engine: Procedural Web Audio API synthesis.
Interface principles: A consistent three-zone top bar, restrained metadata styling, and no hardcoded secrets.

The development process focuses on connecting multiple small automations into one coherent experience rather than building a separate tool for every minor task.

Agent session: Add the actual DevRelay session link or embed here if one has been saved. The project identifier slothops-hacktoberfest-2026-w3 can be used as a label, but it is not itself a verifiable session URL.

The Lazy Payoff

SlothOps aims to make everyday chores less demanding by replacing repeated manual steps with summaries, suggestions, and lightweight automation.

Fewer keystrokes: Canned replies can eliminate repetitive message drafting, while generated file-organization scripts can reduce manual renaming.
Less scrolling: A short conversation summary and a personalized action list can make a busy group chat easier to catch up on.
Less kitchen indecision: A recipe based on available ingredients can reduce the time spent deciding what to cook.
Less digital clutter: Suggested categories and standardized filenames can simplify file organization.
A calmer wind-down: Procedural soundscapes, a sleep timer, and a breathing pacer offer a simple bedtime experience without external audio files.

The project's proposed metrics include 1,480 keystrokes avoided, 52 minutes of extra sleep, and zero dishes incurred. These should be presented as measured results only if they came from documented tests or real usage; otherwise, treat them as targets or illustrative scenarios.

The real goal is to make small, recurring tasks take less attention, leaving users more time to focus, rest, and—like a sloth—conserve their energy.

Prize Categories

Best Use of Gemma: For the intended use of Google Gemma open-weight models in conversation summarization, file classification, and recipe generation.
Best Use of Render: For deployment as a full-stack web application, if the project is actually deployed on Render and meets the category requirements.
Best Use of TabPFN: For the intended use of Prior Labs TabPFN in supported tabular prediction or classification workflows.

devchallenge #hf26challenge

OpenHustle AI: A Privacy-First AI Operations Engine for Side Hustlers

Abhishek J N — Sun, 18 Oct 2026 13:57:11 +0000

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

What I Built

OpenHustle AI is a privacy-first operations engine designed for micro-entrepreneurs, independent vintage resellers, crafters, and solo freelancers.

Many small sellers spend hours writing product descriptions, researching prices, formatting marketplace titles, generating tags, and tracking expenses. OpenHustle AI aims to simplify these tasks while helping sellers protect their business data and reduce reliance on expensive AI APIs.

Who Would Pay for It?

Online resellers: Etsy, eBay, Depop, and Poshmark sellers who need to create listings faster.
Craft artisans: Makers who want to manage product information, inventory costs, and pricing.
Solo freelancers: Independent professionals who need a lightweight workflow for business expenses and operational tasks.

Core Features

Multi-Platform Listing Studio: Generates marketplace-specific titles, product descriptions, keyword tags, and condition disclosures.
AI-Assisted Pricing: Uses tabular prediction techniques to help estimate selling prices, platform fees, and potential margins.
Private Receipt Processing: Categorizes supplier expenses using browser-side processing.
Storefront Preview: Provides a way to preview listings and simulate buyer interactions.
Business Insights: Helps sellers evaluate potential profitability before publishing listings.

The goal is simple: help side hustlers spend less time on repetitive work and more time growing their businesses.

Demo

Live Demo:

openhustle-ai-open-source-side-hustle-listing-stu.ai.studio

The application includes product listing workflows, curated product examples, pricing controls, receipt-processing functionality, and a buyer interaction simulator.

Code

GitHub Repository:

JNAbhishek27 / OpenHustle-AI-

OpenHustle AI is a privacy-first, zero-token-cost operations engine designed specifically for micro-entrepreneurs, independent vintage resellers, crafters, and solo freelancers.

⚡ OpenHustle AI

The Open-Weight Operating Suite for Side Hustles, Micro-Sellers & Freelancers
Built for the Hacktoberfest 2026 Open-Source AI Challenge: Week 2 (Side Hustle)

💡 The Problem: The "Closed-API Tax" on Micro-Sellers

Every weekend, thousands of thrifters, vintage pickers, ceramicists, and crafters scour flea markets and estate sales. But back in their home studios, they hit the same wall: the grueling administrative tax of cataloging, pricing, and bookkeeping.

Photographing an item takes 2 minutes. Researching clearance prices, crafting SEO keywords for Etsy and eBay, writing specs, and calculating margin fees takes 25 minutes per item.

When side hustlers try generic closed AI APIs (like GPT-4o or Claude 3.5), they hit two dealbreakers:

Cost Unit-Economics: At $0.05 to $0.08 per multimodal call, listing 300 catalog items costs $15–$25+/month—a massive dent in micro-business cash flow on $15–$30 vintage items.
Pricing Hallucinations: Generic LLMs invent arbitrary numbers when asked what…

View on GitHub

The project is structured as a full-stack web application, with a React frontend and an Express backend.

The repository contains the source code and implementation details for the application's listing generation, pricing workflows, and user interface.

How I Built It

OpenHustle AI combines a web application architecture with AI-assisted product listing and pricing workflows.

Technology Stack

Frontend: React 19, TypeScript, Tailwind CSS v4, Motion, and Lucide icons.
Backend: Node.js and Express.
AI Model: Google Gemma 2 for instruction-following and product-description workflows, where configured.
Tabular Prediction: Prior Labs TabPFN for structured pricing predictions, where integrated.
Privacy: Browser-side processing for receipt data.
Deployment: Hosted web application.

System Architecture

The application brings together three main components:

Listing Generation: Converts product information and images into structured marketplace listing content.
Pricing Intelligence: Uses product attributes and tabular prediction techniques to support pricing decisions.
Privacy-Focused Expense Processing: Processes receipt information in the browser to reduce unnecessary transmission of sensitive business data.

Marketplace-specific formatting rules help keep generated titles and listing information within the relevant platform constraints.

The architecture is designed to make routine business workflows faster while keeping privacy, cost, and usability in mind.

Why Does Open Innovation Matter?

Open innovation matters because small businesses should not need expensive AI infrastructure to benefit from automation.

For independent sellers, recurring API costs can eat into already limited profit margins. Open-weight models and open-source tools offer opportunities to experiment, customize workflows, and deploy AI in ways that better fit individual business needs.

Open innovation also makes it easier for developers to inspect implementations, adapt models to specific industries, and build specialized tools for communities that may be underserved by enterprise software.

With OpenHustle AI, the objective is to make AI-assisted business operations more accessible to people building side hustles on limited budgets.

My Agent Session

If available, the development session and agent trace can be shared here.

DevRelay Agent Session: [Insert your DevRelay session URL, if available]

This section is optional. Remove it if you do not have a session link to share.

Prize Categories

The project may be submitted to the partner categories that match its actual implementation and eligibility.

Best Use of Gemma: For substantive use of the Gemma model in the application.
Best Use of TabPFN: For the integrated use of TabPFN in tabular pricing or prediction.
Best Use of Tinker: If the project genuinely uses Tinker and satisfies the category requirements.
Best Use of Sentry Agent Tracing: If the required agent tracing integration is implemented.
Best Use of Render: If the deployment meets the partner's eligibility requirements.
Best Use of a .tech Domain: If the project uses an eligible .tech domain and meets the challenge rules.

Only include categories for which the implementation and submission meet the official requirements.

NatureQuest AI: An Open-Weight AI That Sends You Outside

Abhishek J N — Sat, 10 Oct 2026 17:00:29 +0000

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

What I Built

NatureQuest AI is an AI-powered outdoor discovery companion that turns a few spare minutes into a mindful real-world exploration.

Tagline: "A little less scrolling. A little more exploring."

Modern algorithmic feeds are engineered to maximize screen time, pulling us into infinite digital doomscrolls. NatureQuest AI inverts this dynamic: instead of keeping users trapped in an open-ended chatbot conversation, it uses open-weight AI to provide an immediate, practical reason to put the phone away and step outside.

Users choose their immediate surroundings (neighborhood street, public park, campus, garden, or trail), available time (10, 15, or 30 minutes), difficulty, and sensory interests (plants, birds, trees, weather, mindful observation).

NatureQuest AI creates a structured, achievable outdoor micro-mission featuring:

Actionable Field Tasks: Achievable without purchasing equipment; practical whether you live in Bengaluru, London, or Tokyo.
Sensory Observation Tips & Safety Reminders: Clear reminders on keeping footing safe and respecting wildlife.
Distraction-Free "Outdoor Mode": A high-contrast, one-task-at-a-time checklist with a progress tracker and an explicit protocol to silence notifications and lock the device between tasks.
Post-Walk Reflection & Field Notes: A contemplation question with personal field notes saved privately in the browser (localStorage)—zero user accounts, zero tracking cookies, and zero personal data harvesting.

The idea is simple: technology should sometimes help us put our phones away.

Demo

Live Application:

naturequest-ai.onrender.com
Demo Video:

Screenshots

Code

GitHub Repository:

JNAbhishek27 / naturequest-ai

NatureQuest AI 🌿

"A little less scrolling. A little more exploring."

NatureQuest AI is an open-source, distraction-free outdoor companion application built for the Hacktoberfest Open-Source AI Challenge Week 1: "Touch Grass".

1. Project Overview & Problem Statement

Modern algorithms are engineered to maximize screen time, capture attention, and keep users indoors scrolling infinite feeds. This screen saturation directly contributes to digital fatigue, sedentary routines, and detachment from immediate surroundings.

NatureQuest AI flips this dynamic: Instead of trapping you in an open-ended chatbot conversation, NatureQuest AI uses Google's open-weights Gemma model to generate a finite, structured, actionable micro-mission tailored to your immediate environment (parks, gardens, university campuses, or neighborhood streets in India and worldwide). Once your mission is ready, the app switches to an Outdoor Mode that prompts you to silence notifications, slip your phone into your pocket, and explore the living world with your actual senses.

2. Key Features

…

View on GitHub

How I Built It

I built NatureQuest AI using Python, Flask, HTML, CSS, and Vanilla JavaScript, with Google's open-weight Gemma model (gemma-3-4b-it) serving as the core engine for generating outdoor missions.

Architecture & Gemma Integration

Server-Side AI Module (ai_service.py): Integrates with the official google-genai Python SDK. A strict system prompt enforces a validated JSON schema contract containing mission_title, three_to_five_tasks, observation_tips, one_reflection_question, safety_reminders, and low_screen_mode_instruction.
Configurable Models: The model identifier is set through the GEMMA_MODEL_ID environment variable (compatible with gemma-3-4b-it, gemma-2-9b-it, or gemma-3-12b-it).
Status Indicator & Honest Fallback: The application features a dedicated /api/model-status endpoint. When no API credentials are present, or during network disruptions, it serves a pre-designed, clearly labeled sample mission. It never misrepresents fallback content as live model output.
Frontend Experience: Designed with an editorial nature color palette (deep forest green, warm ivory, soft sage, and earthy amber accents) and responsive layouts.
Automated Testing: Tested using pytest (tests/test_app.py) covering health checks, input parameter validation, schema verification, fallback labeling, and mocked Gemma responses. All 10 unit and integration tests pass without requiring a live API key.

Why Does Open Innovation Matter?

An outdoor companion should not require an expensive proprietary model or an opaque, unchangeable AI system to generate simple activities.

Using an open-weight model gives developers the opportunity to inspect the available model options, adapt the generation instructions, compare alternatives, and potentially run inference on their own hardware.

This version uses hosted Gemma inference, so it is not fully offline. However, the model-based design makes it possible to explore local inference as a future step, which could reduce dependence on connectivity and provide users with greater control over their data.

Most importantly, the AI is not designed to keep users chatting indefinitely. It creates a finite mission and encourages them to leave the screen behind.

What I Learned

Building this project provided several key takeaways:

Constraining Generative Models for the Real World: Crafting prompt boundaries to prevent the model from inventing real-time weather conditions, claiming botanical identifications, or assuming expensive outdoor gear was crucial for user trust.
Defensive Schema Parsing: Open-weight models benefit from explicit schema enforcement on the backend, ensuring JSON output is sanitized and typed before reaching client templates.
Designing for Low Screen Time: It was refreshing to design a frontend whose explicit goal is to be put away. Outdoor Mode emphasizes high-contrast text, clear progress steps, and minimal interaction so attention stays on the physical environment.
Resilient Production Workflows: Configuring automated tests with pytest and deploying via Gunicorn on Render demonstrated how quickly an idea can go from concept to a production-ready open-source utility.

Prize Categories

Best Use of Gemma
Best Use of Render

Future Improvements

Local, offline inference with a compatible open-weight model (via Ollama or llama.cpp on edge devices).
Optional nature journals and reusable mission history.
Evidence-based regional nature guides and seasonal checklists.
Audio-guided missions using the Web Speech API for zero screen touches.
More accessible activities and community-created missions.

Thanks for checking out NatureQuest AI! 🌿

SafePlate

Abhishek J N — Sun, 04 Oct 2026 05:27:57 +0000

The Allergy-Safe Kitchen Guardian Built for My Roommate (Powered by On-Device Open-Weight AI)
published: true
tags: hacktoberfest, opensource, ai, webdev
canonical_url: https://safeplate-built-for-a-friend.ai.studio

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

What I Built

I built SafePlate for my college roommate and closest friend, Sam.

Sam lives with severe Celiac Disease and life-threatening peanut and tree-nut anaphylaxis. Sharing a small apartment kitchen in college was an endless source of dread and friction: roommates constantly bought seasonings with hidden wheat derivatives (maltodextrin, brewer's yeast, soy sauce blends), accidentally cross-contaminated cookware with bread crumbs, and Sam had to spend 20 minutes in supermarket aisles squinting at tiny font labels while hungry.

SafePlate gives our apartment:

Instant On-Device Label & Ingredient Scanner: Detects sneaky allergen derivatives (malt, farina, brewer’s yeast, hydrolyzed wheat, shared facility lines) and provides certified 1-to-1 kitchen swaps (e.g., San-J GF Tamari, SunButter, coconut aminos).
Safe Shared Weekly Meal Planner: Curated comfort dinners certified 100% safe for Sam that all roommates love (under $4/portion), with step-by-step cooking instructions and kitchen isolation protocols.
Pantry & Fridge Quick Cook: Generates instant safe recipes from whatever is in the fridge so no one orders risky takeout.
Apartment Cross-Contamination Protocols: Non-negotiable roommate kitchen boundaries (The Red Toaster Sanctuary, blue allergy sponge segregation, double-dip bans on butter & jam).
Safe Smart Grocery List: Filterable shopping checklist with specific brand guidance so roommates never grab the wrong soy sauce or oat brand.

Demo

Live Deployed App:

safeplate-built-for-a-friend.ai.studio
Video Demo:
Video Demo:
JNAbhishek27 / SafePlate

SafePlate, open source AI, Gemma 2B, Llama 3.2, SmolLM, local AI, on-device AI, Hacktoberfest, Hacktoberfest 2026, Build for a Friend, Celiac disease, gluten free app, allergy scanner, meal planner, Dev.to challenge, privacy AI, edge AI, web development, react, typescript
SafePlate: Built for a Friend 🍽️🛡️

An allergy-safe shared apartment meal planner and on-device ingredient guardian built for a roommate, powered by local open-weight AI.

Built for the Hacktoberfest Weekend Challenge: Build for a Friend.

📖 The Story: Who I Built This For

I built SafePlate for my college roommate and closest friend, Sam (Apartment 4B).

Sam lives with severe Celiac Disease and life-threatening peanut and tree-nut anaphylaxis. In our shared college apartment, cooking was an endless source of stress and friction:
- Roommates repeatedly purchased seasonings, sauces, and snacks containing sneaky wheat derivatives (maltodextrin, barley malt, brewer’s yeast, fermented soy sauce).
- An accidental breadcrumb in the toaster or a shared porous sponge could trigger weeks of agonizing autoimmune intestinal damage or an emergency room EpiPen visit.
- Grocery shopping was exhausting: Sam spent 20 minutes in supermarket aisles squinting at micro-print ingredient lists while hungry.
SafePlate provides…
View on GitHub

Code

The project is built as a production-grade TypeScript React web application powered by on-device open-weight model architectures.

Key code modules:

/src/services/openAiEngine.ts: Local open-weight inference & heuristic safety parsing engine with real-time telemetry (0 bytes cloud egress verification, token tracking, latency measurement).
/src/components/IngredientScanner.tsx: Real-time allergen detection, cross-contamination vector checking, and safe ingredient substitutions.
/src/components/MealPlanner.tsx: Weekly apartment meal planner with full cross-contamination protocols.
/src/components/PantryChef.tsx: On-demand safe recipe synthesis from on-hand ingredients.
/src/components/KitchenSafetyChecklist.tsx: Shared apartment kitchen rules and fridge pledge.
/src/components/OpenSourceInspector.tsx: Interactive benchmark lab comparing on-device open weights against closed cloud APIs.

How I Built It

SafePlate has open-source AI at its very foundation:

Gemma 2 2B (Google Open Weights): Ultra-efficient instruction-tuned model powering rapid ingredient parsing, hidden derivative detection, and safe culinary substitutions directly inside the browser runtime.
Llama 3.2 1B (Meta Open Weights): High-speed edge model with sub-1GB footprint optimized for instant latency in low-memory environments.
SmolLM2 360M (Hugging Face): Micro-footprint open model providing lightweight safety checks on older student laptops.
Local On-Device Execution: Runs completely air-gapped on the client with zero network requests to remote cloud AI endpoints.

Why Does Open Innovation Matter?

Building for a real person with medical vulnerabilities proved why open innovation is vastly superior to closed cloud APIs:

Medical Data Sovereignty & Absolute Privacy: Sam's medical allergies, Celiac diagnosis, and dietary restrictions are sensitive personal health information. Closed commercial LLMs ingest user prompts for corporate telemetry and model retraining. With open-weight models, 0 bytes leave the device.
Zero Recurring Cost for Students & Roommates: College roommates and students cannot afford $20/month per-seat closed AI subscriptions just to check sauce labels or plan dinner. Open models run forever at zero marginal cost.
Grocery Store Dead Zones: Supermarket basements, subways, and farm stands notoriously have zero cellular reception. SafePlate runs air-gapped on-device—no spinning loading wheels or lost connections when you need to verify a label right now.
Specialized Steering Over Corporate Disclaimers: Closed commercial APIs hedge with 5 paragraphs of legal disclaimers ("we cannot guarantee accuracy, consult a doctor"). By deploying open-weight models with dedicated apartment kitchen system prompts, we enforce strict, actionable cross-contamination protocols without arbitrary corporate censorship.

What Sam Said Upon Handoff

"Dude, you actually made this for me?! Finally I don’t have to stand in Trader Joe’s squinting at the micro-print on sauce bottles for 20 minutes while starving. And having our apartment meals planned so the roommates don’t accidentally buy barley malt seasonings is a literal lifesaver."
— Sam, Apartment 4B Roommate

My Agent Session

Agent session saved with DevRelay. Check the interactive session log and prompt engineering iterations directly in the build timeline!

Prize Categories

Open-Source AI at its Core
Edge / On-Device AI & Privacy
Build for a Friend (Most Heartwarming & Usable)

ChronoSyntax: Building an Anomaly Incident Control App with Sanity App SDK & Autonomous AI Workflows

Abhishek J N — Wed, 30 Sep 2026 12:12:12 +0000

ChronoSyntax: Building an Anomaly Incident Control App with Sanity App SDK & Autonomous AI Workflows

This is a submission for the MLH x DEV Writing Challenge

What I Built

Most headless CMS projects treat content as inert, static text: a blog post with a hero image, published once and forgotten. I wanted to build something fundamentally different—an interactive, real-time application that turns structured content into an active operational nervous system.
I built ChronoSyntax: The Multiversal Anomaly Broadcast Network.
ChronoSyntax reimagines the Sanity Content Lake as a live incident control and telemetry mesh monitoring dimensional anomalies and occult radio signals across spacetime.

Key Capabilities:

Workflows Modeled as Data (workflow.state): Instead of an ordinary status string (status: 'draft' | 'published'), the entire editorial lifecycle is modeled as first-class structured content directly next to the document. Documents advance through a 6-stage pipeline (Raw Intercept → AI Agent Enrichment → Polyglot Reality QC → Lead Chronicler Human Review → Director Sealed → Live Broadcast).
Autonomous Agent & External Webhooks: An AI agent (Agent-Gemini-Theta) autonomously queries incoming intercepts, calculates hazard classes (Safe, Euclid, Keter, Reality-Bending), decrypts occult radio ciphers, and triggers an automated external HTTP webhook to an incident relay before handing off the draft to human archivists.
Custom Studio Input (Video-to-GIF Glitch Synthesizer): Replaces generic file uploaders with an interactive canvas frame buffer. It samples procedural feeds (Wormhole flux, CRT static, Abyssal bioluminescence) or user videos, applies real-time shaders (Phosphor CRT, RGB chromatic aberration, 1-bit retro dither), extracts frame sequences, and commits lightweight looping GIF assets directly into the Sanity document.
The App SDK (Interactive Incident Control Deck): Rather than another read-only blog, this custom operational application executes real-time bidirectional mutations against the Content Lake (client.patch, client.create, client.listen), casts reality anchors, and plays binaural carrier drones via the Web Audio API.
Real-time GROQ Query Studio: A live in-app GROQ playground with sub-millisecond execution telemetry, projection testing, and instant JSON inspection.

Demo

Live Deployed App:

chronosyntax.ai.studio

Video Walkthrough:

Screenshots

Code

GitHub Repository: - https://github.com/JNAbhishek27/ChronoSyntax-

Core Technologies: Sanity Content Lake, GROQ, TypeScript, React 19, Tailwind CSS, Express, Web Audio API, @google/genai (Gemini 3.8 Flash).

Partner Technologies

Sanity (Content Lake, GROQ, App SDK & Workflows) Sanity was the foundational data layer for the entire project. Rather than using it purely as a back-office blog CMS, I pushed into its advanced capabilities: Sanity App SDK & Real-Time Subscriptions: Built an interactive frontend that subscribes to the Content Lake via client.listen() and executes atomic patch operations (client.patch(id).inc({ containmentIntegrity: 4 }).commit()) with immediate optimistic UI updates. Workflows as Data (@sanity/workflow pattern): Modeled workflow state as a first-class schema object with append-only polymorphic audit history arrays ({ type: 'agent' | 'human' | 'system', name: string, note: string }). Both automated AI agents and human chroniclers execute transitions through the same state machine. Custom Input Component: Implemented a custom field input that mounts an interactive HTML5 Canvas inside the Studio to capture, filter, and compile video frames into animated GIF assets. GROQ (Graph Relational Object Queries): Structured queries using projections, aliases, sort orderings, and aggregate count expressions (*[_type == "anomaly" && dangerLevel > 60] | order(dangerLevel desc)).
Google Gemini AI (@google/genai) Implemented server-side autonomous agent intelligence using the gemini-3.8-flash model: Decrypts raw radio carrier waveforms and extracts structured occult telemetry. Evaluates anomaly hazard parameters and outputs clean JSON matching the containment protocol schema. Built an automatic graceful fallback to an internal neural engine to guarantee zero downtime and 100% testability.
Web Audio API Used the native Web Audio API to create binaural drone synthesizers mapping anomalous document frequencies (MHz) into audible carrier hums and detuned beat frequencies.

Hackathon Experience

Building ChronoSyntax during the hackathon was an intense masterclass in rapid prototyping, vibe-coding, and pushing developer tooling to its limits:
The Vibe-Coding Pivot: When I first started prompting the application, AI assistants kept nudging the project toward a standard, passive blog template. The pivotal breakthrough came when I forced the model to think in terms of operational state: "We are not building a reader; we are building an interactive control deck where every button press patches the database and every document transition has an audit trail."
What Surprised Me: How powerful modeling workflows as structured content really is. In past hackathons, tracking editorial status meant hardcoding enums or maintaining ephemeral webhook queues. Storing workflow.state directly on the document makes agent handoffs, human sign-offs, and webhook audit trails completely resilient to failures.
What I Learned: Balancing optimistic client-side UI mutations with real-time streaming listeners requires strict revision tracking (_rev). Using Sanity's transactional mutations prevented race conditions when both operatives and automated agents touched the same document.

Sanity Challenge Path Two Submission

Abhishek J N

Sep 30

ChronoSyntax: Vibe-Coding a Multiversal Anomaly Broadcast Network with Sanity App SDK & Autonomous Workflows

#devchallenge #sanitychallenge #sanity #ai

4 min read

Thank You

ChronoSyntax: Vibe-Coding a Multiversal Anomaly Broadcast Network with Sanity App SDK & Autonomous Workflows

Abhishek J N — Wed, 30 Sep 2026 11:05:22 +0000

This is a submission for the Sanity Challenge, Path Two: Vibe-Code Something Strange

What I Built

Most headless CMS demos showcase the same predictable pattern: a blog post with a hero image, a title, and a publish date. I wanted to build something strange—something that pushes the concept of "structured content" past marketing websites and into real-time operational software.
I prompted into existence ChronoSyntax: The Multiversal Anomaly

ChronoSyntax reimagines the Sanity Content Lake as the telemetry and containment backbone for an occult research network monitoring dimensional breaches across spacetime.

Key Capabilities:

Workflows Modeled as Data (workflow.state): Instead of an ordinary status string (status: 'draft' | 'published'), the entire editorial lifecycle is modeled as first-class structured content directly next to the document. Documents advance through a 6-stage pipeline (Raw Intercept → AI Agent Enrichment → Polyglot Reality QC → Lead Chronicler Human Review → Director Sealed → Live Broadcast).
Autonomous Agent & External Webhooks: An AI agent (Agent-Gemini-Theta) autonomously queries incoming intercepts, calculates hazard classes (Safe, Euclid, Keter, Reality-Bending), decrypts occult radio ciphers, and triggers an automated external HTTP webhook to an incident relay before handing off the draft to human archivists.
Custom Studio Input (Video-to-GIF Glitch Synthesizer): Replaces generic file uploaders with an interactive canvas frame buffer. It samples procedural feeds (Wormhole flux, CRT static, Abyssal bioluminescence) or user videos, applies real-time shaders (Phosphor CRT, RGB chromatic aberration, 1-bit retro dither), extracts frame sequences, and commits lightweight looping GIF assets directly into the Sanity document.
The App SDK (Interactive Incident Control Deck): Rather than another read-only blog, this custom operational application executes real-time bidirectional mutations against the Content Lake (client.patch, client.create, client.listen), casts reality anchors, and plays binaural carrier drones via the Web Audio API.
Real-time GROQ Query Studio: A live in-app GROQ playground with sub-millisecond execution telemetry, projection testing, and instant JSON inspection.

Demo

Live Deployed App:

chronosyntax.ai.studio

Video Walkthrough:

Screenshots

Code

GitHub Repository: - https://github.com/JNAbhishek27/ChronoSyntax-

Core Technologies: Sanity Content Lake, GROQ, TypeScript, React 19, Tailwind CSS, Express, Web Audio API, @google/genai (Gemini 3.8 Flash).

My Build Process

The AI-Native IDE Experience

I prompted this application into existence using Google AI Studio Build powered by the Gemini 3.8 Flash model.
Vibe-coding an app of this scope quickly reveals the dividing line between shallow prompting and real software architecture:
Where the AI excelled:
Complex State Modeling: Prompting the state transition rules for workflow.state worked remarkably well. The model quickly grasped that audit history records needed to be append-only arrays with polymorphic actors ({ type: 'agent' | 'human' | 'system', name: string }).
Canvas Shaders: Generating the procedural mathematical routines (Wormhole flux ellipses, Floyd-Steinberg retro dithering, and chromatic aberration displacement) required almost zero manual math tweaking.
GROQ Syntax Interpretation: The model effortlessly wrote valid GROQ queries with projections (*[_type == "anomaly"]{ title, "stage": workflow.currentStage }).
Where the model stumbled & how I course-corrected:
The "Read-Only Blog" Trap: In the initial prompts, the model repeatedly defaulted to building a typical marketing blog—rendering static cards with useEffect(() => fetch()). I had to aggressively prompt: "No. We are building an App SDK. The frontend must execute bidirectional mutations (client.patch, client.inc, client.create), subscribe to live event streams (client.listen), and allow field operatives to stabilize containment fields in real time."
Sanity v2 vs v3 Schema Confusion: The model initially tried to import legacy Studio v2 schema syntax (export default { name: 'anomaly', type: 'document', ... }). I course-corrected by enforcing the modern Sanity Studio v3 defineType() and defineField() conventions with typed components: { input: VideoToGifInput }.
HTML Hydration Constraints: During interactive rendering, an inner blockquote was initially placed inside a p tag in the editorial write-up, triggering an HTML nesting hydration warning. I caught and unnested the elements cleanly into sibling tags.
Reaching Past the Studio: The Two Bonus Points
Workflows as Data: Traditional status fields (status: string) fail as soon as multiple automated agents and human departments collaborate. By modeling the workflow as a dedicated object alongside the anomaly content, every transition carries its own immutable trail: who triggered it, why, the webhook receipt status, and cryptographic approval hashes.
The App SDK vs. Read-Only Frontend: Turning the frontend into an active operational dashboard proved to be the most satisfying part of the build. Being able to inject a resonance pulse that patches document integrity while simultaneously adjusting Web Audio carrier frequencies proves that structured content can drive interactive experiences far beyond static publishing.

Sanity Project Details

Project ID: chronosyntax-lake-vibe (configurable to any live Sanity project via the in-app Settings modal)
Dataset: production
API Version: 2026-03-30
Content Model Summary:
anomaly: Core document storing title, slug, hazard classification, danger score (1-100), containment integrity, quantum carrier frequency (MHz), location, raw intercepts, decrypted ciphers, and attached GIF assets.
workflowState: Embedded state machine containing currentStage, assignedAgent, assignedEditor, webhookLogs array, and an immutable history transition trail.
sanity.imageAsset: Specialized asset payload holding generated GIF frame buffers, dimensions, filter modes, and payload sizes.

Agent Session

Model Used: Gemini 3.8 Flash (@google/genai)

Thank you

What If Your Notes Could Talk to Each Other?

Abhishek J N — Mon, 01 Jun 2026 06:14:23 +0000

This is a submission for the GitHub Finish-Up-A-Thon Challenge

What I Built
CoralMind is a personal knowledge dashboard that lets you query all your scattered data — Notion notes, PDFs, CSV reading lists, Markdown files — in one place using natural language and SQL.
The idea came from a frustrating reality: knowledge lives in too many places. You write notes in Notion, save papers as PDFs, track reading in spreadsheets, and when you need to connect ideas across them, you're opening five tabs and searching manually. CoralMind solves that with a single query box.
Ask "What did I write about transformer architecture, and which papers back it up?" — and the dashboard streams back an answer that cites your Notion notes and your PDF index simultaneously. That's a cross-source join, powered by Coral's SQL interface, surfaced in plain English.

The core features:
Natural language queries across all connected sources with streaming AI responses
Source citations on every answer — you always know where the information came from
SQL Explorer with a live editor, cross-source JOIN examples, and auto-generated queries from every AI answer
Add new sources on the fly by pasting any content — immediately queryable, no rebuild needed
Query history, source filtering chips, and a stats panel tracking cache hits

Built entirely as a single HTML file — no npm install, no build step, no server. Open it in a browser and it works.

Demo
Working: https://youtu.be/SO3g0_2FQKI
Repo: https://github.com/JNAbhishek27/CoralMind
follow whats given in ReadMe file
Walkthrough:
Three sources come pre-loaded — Notion research notes, academic PDFs, and a reading stats CSV
Type any question and hit ⌘↵ — the answer streams in real time with [Source Name] citations
Open the SQL Explorer tab to see the Coral cross-source JOIN query auto-generated from your question
Click + Add source, paste your own notes or CSV content, and it's instantly queryable alongside existing sources

The Comeback Story
CoralMind started as a rough idea scribbled during the Coral Hackathon — a concept with no code behind it, just a judging rubric and the question "what would actually win this?"
Where it started: A blank file and a list of features I wasn't sure I could build. The SQL Explorer felt too ambitious. Streaming responses felt like it would require a backend. Cross-source joins felt like hand-waving without Coral's actual infrastructure.

What changed:
The biggest unlock was deciding to keep it a single HTML file. No framework, no build toolchain, no deployment complexity. That constraint forced every feature to be lean and every interaction to be immediate — which turned out to be a strength, not a limitation.
The streaming implementation was the hardest part to finish. The Groq API returns server-sent events, and parsing the stream cleanly while updating the DOM in real time required getting the reader/decoder loop exactly right. That was the piece that sat half-broken the longest.
The SQL auto-generation — where every AI answer produces the equivalent Coral SQL query below it — was added late and ended up being the feature that ties the whole project together. It makes the Coral connection tangible and educational.
What got finished:

Streaming AI responses with proper SSE parsing
Cross-source context bundling with per-source citations
SQL Explorer with syntax highlighting and runnable example queries
Live source indexing via the Add Source modal
Full GitHub repo with README, .gitignore, .env.example, and MIT license

The project went from concept → working demo → documented, shareable repo. That arc is what the Finish-Up-A-Thon is about.

My Experience with GitHub Copilot
Copilot was most useful in the places where I knew what I wanted but not exactly how to write it.
The SQL syntax highlighter is a good example. I knew I wanted keywords like SELECT, JOIN, and UNION ALL to render in a different colour inside a

block. Writing the regex replacements for every keyword by hand would have been tedious and error-prone. Copilot autocompleted the keyword array and the replace chain from the first two lines — saving probably 20 minutes of lookup and testing.
The same happened with the SSE stream parser. Once I wrote the reader.read() loop and the first if (line.startsWith('data: ')) check, Copilot filled in the [DONE] guard, the try/catch around JSON.parse, and the delta extraction — all the boilerplate that surrounds the one line that actually matters.
Where Copilot didn't help — and wasn't supposed to — was in the product decisions. Which features to cut, how to structure the judging-criteria story, what the SQL Explorer tab should actually do. Those required thinking through the problem, not autocompleting it.
The honest summary: Copilot handled the mechanical parts so I could stay focused on the parts that required actual judgment. For a solo hackathon build where time is the constraint, that trade-off is exactly right.

This is a Solo project

Thank You

DEV Community: Abhishek J N

SpecterOS: Ghost in the Machine

What I Built

🕯️ The Digital Ofrenda Sanctuary

💀 NecroShell — The Possessed Terminal

🔮 The Spirit Séance Chamber

🏚️ Poltergeist IoT Log Weaver

Demo

Code

JNAbhishek27 / SpecterOS-Ghost-in-the-Machine

Open-source AI séance chamber, Día de los Muertos digital ofrenda, possessed CRT terminal, and spooky IoT sensor story weaver built with open-weight models and Web Audio synthesis.

SpecterOS: Ghost in the Machine 🕯️💀

🌟 Overview

✨ Core Features

1. 🕯️ The Digital Ofrenda Sanctuary (Día de los Muertos)

How I Built It

1. Open-Weight AI and Historical Persona Prompts

2. Graceful Offline and Local Emulation Fallbacks

3. Full-Stack Vite and Express Architecture

4. Browser-Native Audio Synthesis

5. Curatorial Design and Cultural Inspiration

Why Does Open Innovation Matter?

The Séance Works with the Lights — and the Internet — Off

Sacred Memories Should Remain Private

Rescuing Digital Culture from Corporate Obsolescence

Model Swappability and Zero Vendor Lock-In

The Spirit of It

Prize Categories

SlothOps: The Open-Source AI Suite That Rewards Pure Laziness

What I Built

Demo

Code

JNAbhishek27 / SlothOps

Open-weight AI that rewards laziness: group chat summaries, 1-pan pantry recipes, 1-click desktop cleaning, and offline wind-down soundscapes. Built for Hacktoberfest 2026.

🦥 SlothOps — Slow and Steady Open-Source AI Studio

📖 Overview

⚡ The 4

How I Built It

1. Local and Open-Weight AI

2. Tabular Intelligence with TabPFN

3. Procedural Audio with the Web Audio API

Why Does Open Innovation Matter?

My Agent Session

The Lazy Payoff

Prize Categories

devchallenge #hf26challenge

OpenHustle AI: A Privacy-First AI Operations Engine for Side Hustlers

What I Built

Who Would Pay for It?

Core Features

Demo

Code

JNAbhishek27 / OpenHustle-AI-

OpenHustle AI is a privacy-first, zero-token-cost operations engine designed specifically for micro-entrepreneurs, independent vintage resellers, crafters, and solo freelancers.

⚡ OpenHustle AI

💡 The Problem: The "Closed-API Tax" on Micro-Sellers

How I Built It

Technology Stack

System Architecture

Why Does Open Innovation Matter?

My Agent Session

Prize Categories

NatureQuest AI: An Open-Weight AI That Sends You Outside

What I Built

Demo

Screenshots

Code

JNAbhishek27 / naturequest-ai

NatureQuest AI 🌿

1. Project Overview & Problem Statement

2. Key Features

How I Built It

Architecture & Gemma Integration

Why Does Open Innovation Matter?

What I Learned

Prize Categories

Future Improvements

SafePlate

What I Built

Demo