DEV Community: Aditya Alibade

Touch Grass Go: Turning Real-World Nature Adventures into an RPG

Aditya Alibade — Sun, 11 Oct 2026 15:08:19 +0000

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

We sit for hours on end in front of screens, switching between tabs, scrolling down feeds, and playing games. But what if we could harness that same determination that gets us to play games to get us to explore the world around us?

This thought process gave birth to Touch Grass Go , an android app, that turns real-world exploring into an RPG nature quest.

The Idea

What if real life had quests, experience points, levels, and daily streaks?

With Touch Grass Go, your next adventure could be as simple as observing birds in your neighborhood, practicing mindfulness outdoors, or discovering interesting leaves along your walk.

The goal is simple: make exploring nature engaging while encouraging users to spend less time staring at their screens.

Features

Character Progression — Build your character, earn XP, and level up as you progress.
Interactive Maps — Explore your surroundings with OpenStreetMap integration, custom markers, and an India-centered map view.
Nature Quests — Discover activities involving mindfulness, birdwatching, and leaf inspection.
Quest Completion Tracking — Confirm completed quests and track your progress.
Daily Streaks — Stay consistent and track consecutive days of outdoor exploration.
Adventure Journal — Save timestamped entries and personal reflections from your experiences.
AI-Powered Quest Generation — Generate nature quests using local Gemma model support, with an offline fallback.
Quest Safety Validation — Validate generated quests using keyword checks and geographic-bound checks.
Offline-First Experience — Keep the core adventure experience focused on local functionality rather than depending entirely on cloud services.

Building with Offline-First AI

One of the most interesting aspects of this project was exploring how AI can work locally instead of relying entirely on cloud APIs.

The quest-generation system supports local Gemma integration and an offline fallback for situations where AI inference is unavailable.

Combining AI with real-world activities creates an interesting challenge: the technology should encourage people to experience the world, not become another reason to stay glued to their phones.

Tech Stack 🛠️

Platform: Android
Programming Language: Java
UI: XML layouts
Maps: OpenStreetMap with osmdroid
AI: Local Gemma model integration with offline fallback
Architecture: Offline-first Android application

What Makes This Project Different?

Many apps compete for our attention with endless feeds, notifications, and digital rewards.

Touch Grass Go takes a different approach: use game mechanics to encourage real-world exploration.

Instead of spending another hour completing virtual missions, users can earn progress by engaging with nature and documenting their adventures.

It's a simple idea with an important mission: make going outside feel like an adventure.

Prize Categories

Featured Category

Gemma — Best Use of Gemma: Using Google's open-weight Gemma model for AI-powered nature quest generation, with an offline fallback when AI inference is unavailable.

This category is relevant because local Gemma integration is part of the project's AI-powered quest-generation concept.

🔗 Explore the Project on GitHub

Want to explore the source code and see how the project works?

👉 GitHub Repository: https://github.com/AdityaAlibade/touch-grass-go.git

If you find the project interesting, consider starring the repository and sharing your feedback or ideas!

What I Learned

Building Touch Grass Go brought together Android development, map integration, offline-first AI, and gamification around one real-world problem: how can technology encourage healthier interactions with the world around us?

This project explores how digital experiences can motivate people to take action beyond their screens.

Sometimes the best quest isn't inside a game.

Close the feed. Open the world. Earn your XP outside.

Your Turn!

If your real life had an RPG quest system, what outdoor quest would you complete first?

Would you go birdwatching, explore a new trail, discover local plants, or create your own adventure?

Share your ideas in the comments!

Tab Bankruptcy: Turn Your Chrome Tab Chaos into a Local AI-Powered Vault

Aditya Alibade — Mon, 05 Oct 2026 04:42:10 +0000

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

What I Built

I built Tab Bankruptcy, a local AI-powered Chrome tab manager for a friend who had a habit of keeping way too many browser tabs open across multiple Chrome windows.

The problem was simple: after collecting dozens or even hundreds of tabs, finding one specific tab became difficult, and closing the browser meant potentially losing that entire context.

Tab Bankruptcy lets them:

Capture tabs across multiple Chrome windows
Save complete browsing sessions locally
Automatically categorize tabs using AI
Generate short AI summaries
Search tabs by title, URL, category, or summary
Filter tabs by category
Restore saved sessions back into Chrome
Preserve window grouping, tab order, and pinned tabs where possible

Instead of treating all those tabs as clutter, Tab Bankruptcy turns them into a searchable personal vault.

Demo

🎥 Demo Video: https://youtu.be/0Kyy7g3F-cs

The demo shows the complete workflow:

Chrome tab chaos → Capture → AI categorization → AI summaries → Search → Restore

Code

💻 GitHub: https://github.com/AdityaAlibade/Tab-Bankruptcy.git

The project is organized into three main parts:

Chrome Extension — captures and restores browser tabs
FastAPI Backend — handles local APIs and persistence
React Dashboard — provides the interface for searching and managing sessions

How I Built It

The project is built around local open-source AI, rather than a cloud AI API.

Tech Stack

Chrome Extension — TypeScript + Manifest V3
Frontend — React + TypeScript + Vite
Backend — Python + FastAPI
Database — SQLite
Local AI Runtime — Ollama
AI Model — Qwen2.5-Coder:7B

The architecture is:

Chrome Extension
       ↓
    FastAPI
       ↓
    SQLite
       ↓
React Dashboard
       ↓
    Ollama
       ↓
Qwen2.5-Coder:7B

The extension captures the user's tabs and sends the session to the local FastAPI backend. SQLite stores the session and tab information.

When AI functionality is needed, the backend sends the relevant tab title and URL information to the locally running Ollama model. The model produces categories and short summaries, which are then stored locally.

The dashboard provides local search and filtering without requiring another AI request.

The restore flow works in reverse: the dashboard creates a restore request, and the Chrome extension uses Chrome's Tabs API to recreate the saved session.

There is no cloud AI API required.

Why Does Open Innovation Matter?

Open innovation made it possible to build this project around local AI instead of depending on a closed AI API.

For Tab Bankruptcy, this matters because browser tabs can contain sensitive or personal information. Running the AI locally means the project does not need to send tab information to an external AI provider just to categorize or summarize it.

Using Ollama and an open-weight model also gives the project flexibility. The AI model can potentially be replaced with another compatible local model without redesigning the entire application.

More importantly, it let me experiment with AI as part of a real application rather than treating it as a separate cloud service.

Final Thought

Tab Bankruptcy started with a very ordinary problem: "I have too many tabs and I can't find anything."

The goal wasn't to build another complicated AI application.

It was to build something small, useful, and personal — and use open-source AI where it actually improves the experience.

Your tabs don't have to become a bankruptcy.

Glad to Join You All!

Aditya Alibade — Thu, 01 Oct 2026 17:54:34 +0000

Nice to join you all!

Thank you for the warm welcome and support. Looking forward to learning, contributing, and growing together.

Excited for what’s ahead!