IRL Side Quest (Turn real life into a game)

Priyansh — Sun, 11 Oct 2026 09:55:56 +0000

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

What I Built

IRL Side Quest is a real-world adventure generator powered by locally running Gemma 4. It creates fun, bite-sized quests that encourage people to step away from their screens, explore their surroundings, and make ordinary moments more interesting.

Feeling bored? Generate a side quest! You might be challenged to find something unusual, discover a new walking route, observe nature, or complete a small outdoor activity.

The goal is simple: turn everyday life into an adventure, one quest at a time.

The app includes AI-generated quests, different quest categories, a simple XP and leveling system, achievements, and locally stored progress. Players can complete quests at their own pace without accounts, subscriptions, or complicated setup.

Code

IRL Side Quest is currently in the concept and planning stage. This submission presents the project's vision, proposed architecture, and planned use of locally running Gemma 4. The implementation and source code are not yet available and will be developed as the project progresses.

How I Built It

IRL Side Quest uses Gemma 4 through Ollama for local AI inference. The application sends quest preferences to a local Next.js API route, which communicates with Ollama and returns a structured quest for the interface to display.

Technology stack:

Next.js and React — user interface and application routing.
TypeScript — type-safe application logic.
Tailwind CSS — styling and responsive design.
Ollama + Gemma 4 — locally generated quests using an open-weight AI model.
localStorage — saves player XP, completed quests, achievements, and progress in the browser.
Lucide React — icons and visual elements.

The architecture avoids cloud AI APIs, API keys, authentication, and a dedicated database. Quest completion is self-reported, keeping the game simple and easy to build on.

Why Does Open Innovation Matter?

IRL Side Quest is designed around the idea that AI should empower people without demanding their attention or personal data.

Using an open-weight model through local inference means quest generation does not require sending prompts to a third-party AI service. Players can experiment with locally available models, inspect the architecture, and adapt the project to their needs.

There are also no per-request cloud AI charges. Once the model is installed, quest generation can work without an internet connection, provided the local application and model are running.

Most importantly, the app challenges the usual goal of keeping people engaged on a screen. Instead, AI creates the experience and then encourages the user to put the device away.

The ultimate objective isn't to spend more time in the app. It's to make something interesting happen outside it.

Prize Categories

Best Use of Gemma — IRL Side Quest uses the Gemma 4 open-weight model through Ollama to generate real-world side quests locally.

Say It For Me — Because Sometimes You Know What You Mean, Just Not How to Say It

Priyansh — Sat, 03 Oct 2026 19:14:11 +0000

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

What I'll Build

Say It For Me is a personal communication assistant designed for a real problem: sometimes you know exactly what you feel or what you want to communicate, but you cannot find the right words.

This is especially common in everyday conversations:

replying to an awkward message
saying no without sounding rude
apologizing without making excuses
asking someone for help
setting a boundary
rescheduling plans
supporting a friend
replying when emotions make it difficult to think clearly

The idea is not to let AI speak for someone.

It is to help them express their own intention in their own way.

A user gives Say It For Me the message they received, explains what they want to communicate, and chooses how they want the response to sound.

For example:

Message: "Are you coming tonight?"

Intent: I can't come, but I don't want them to think I'm avoiding them.

Tone: Friendly

Say It For Me could suggest a few natural responses rather than giving the user one "perfect" answer.

The user can then edit, combine, or completely ignore the suggestions.

The person stays in control: That is the central idea behind the project.

Demo

Project status: Idea / early build concept

Code

The project repository is available on GitHub. The implementation is currently in progress.
Repository: https://github.com/priyansh-bahoria/Say-It-For-Me

How I'll Build It

The first version is intentionally lightweight.

AI — Gemma 4 + Ollama

Gemma 4 will be the core open-weight model, running locally through Ollama. It will take the user's message, intention, tone, and relevant preferences and generate several possible replies.

Memory — MongoDB Atlas

MongoDB Atlas will store lightweight personalization data such as communication preferences and approved examples.

Application — Next.js + TypeScript + Tailwind CSS

The interface will be a small web application focused on one simple interaction: helping the user turn an intention into a message that feels natural to them.

Initial flow

┌─────────────────────────────┐
│         Next.js UI          │
│                             │
│ Message + Intent + Tone     │
└──────────────┬──────────────┘
               │
               ▼
┌─────────────────────────────┐
│        User Context         │
│                             │
│       MongoDB Atlas         │
│ Preferences + Examples      │
└──────────────┬──────────────┘
               │
               ▼
┌─────────────────────────────┐
│          Opencode           │
│              +              │
│           Ollama            │
│          (Gemma 4)          │
└──────────────┬──────────────┘
               │
               ▼
┌─────────────────────────────┐
│      Suggested Replies      │
│                             │
│  1. Reply                   │
│  2. Reply                   │
│  3. Reply                   │
└──────────────┬──────────────┘
               │
               ▼
┌──────────────────────────────┐
│       User Chooses & Edits   │
└──────────────────────────────┘

The first version will deliberately avoid unnecessary complexity such as RAG, vector databases, fine-tuning, or complicated agent systems.

The objective is to make the core experience work well first.
The architecture may differ once when the final product comes out.

Why Does Open Innovation Matter?

This project is specifically suited to open AI because the problem involves personal communication.

A communication assistant may eventually process messages that contain private or sensitive context.

Using Gemma locally through Ollama means the actual AI generation can happen on the user's machine without sending the conversation to a closed AI API. MongoDB Atlas is used separately for lightweight personalization data such as preferences and approved examples.

That gives the project several useful properties:

the model can run locally
the user has more control over their data
the application is not locked to one AI provider
the model can potentially be replaced or adapted later
the system can continue to evolve as open models improve

For this project, open innovation is not just about avoiding a paid API.

It changes the relationship between the user and the AI system.

The user can understand the stack, run it themselves, change components, and decide where their data goes.

Does it help one real person communicate something they were struggling to say?
Yes.
I built this idea around a special person in my life who often struggles to find the right words when replying to someone. Like many people, she sometimes turns to AI chatbots for help writing those responses.
I shared the idea with her, and she loved it. She found the concept genuinely useful, which gave me the motivation to actually build it.

Hackathon

This project is being built for the Hacktoberfest Weekend Challenge — Build for a Friend.

The challenge asks participants to build something with open-source AI at its core for a real friend or someone they care about.

Say It For Me approaches that prompt literally:

Start with one person. Solve one real problem. Use open AI to make the solution possible.

Prize Categories

Planned partner categories:

Best Use of Gemma: The project uses Gemma as the core open-weight AI model.
Best Use of MongoDB Atlas: MongoDB Atlas provides the personalization layer for storing communication preferences and approved examples.

DEV Community: Priyansh

IRL Side Quest (Turn real life into a game)

What I Built

Code

How I Built It

Why Does Open Innovation Matter?

Prize Categories

Say It For Me — Because Sometimes You Know What You Mean, Just Not How to Say It

What I'll Build

Demo

Code

How I'll Build It

Why Does Open Innovation Matter?

Hackathon

Prize Categories