The world outside my window

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

What I Built

🌿 The World Outside My Window

Go live the moment. Capture what matters. Keep the memory.

The World Outside My Window is a local-first, AI-powered photo journal designed to help people preserve the little moments they experience in the real world.

Whether it's a peaceful walk in the park, a visit to the beach, a trip with friends, or an ordinary day that becomes a special memory, users can upload photos, describe what happened, share how they felt, and use AI to turn their experiences into beautiful, personalised journal entries.

Instead of letting meaningful moments disappear into a crowded camera roll, this project gives them a place to live as stories that can be revisited later.

The idea is simple: spend less time staring at a screen and more time experiencing the world around you. The app is designed to help people preserve their memories after experiencing life, rather than encouraging endless scrolling.

Demo

Demo video: https://drive.google.com/file/d/1CdobNpa3iD0JP7XgMw07UrL68ijiv42z/view?usp=sharing

The video will demonstrate the journal interface, creating a memory, generating a journal entry with AI, and saving and revisiting memories.

This project currently runs locally on my computer.

Code

GitHub repository: https://github.com/Monisha14206/The-world-outside-my-window

How I Built It

I built this project using:

• React + Vite for the frontend.
• Python + Flask for the backend and API.
• SQLite for storing journal entries.
• Local file storage for uploaded photographs.
• Ollama + Qwen 2.5 3B for local inference with an open-weight language model.

The core AI feature is designed to transform a user's own notes, experiences, and feelings into a journal title and narrative that they can review and edit before saving.

The React frontend communicates with the Flask backend, which handles journal operations and requests to the locally running Ollama model. Journal entries are stored in SQLite, while uploaded photographs are kept in local storage.

I chose a local-first architecture so the application can run on a personal computer without requiring a paid AI API or a cloud database.

Why Does Open Innovation Matter?

Open innovation makes AI development more accessible to students, independent developers, and anyone who wants to experiment with new ideas without relying entirely on closed, paid AI services.

For this project, open-weight models and local inference provide more control over model selection, prompts, and the journal-writing experience. They also make it possible to explore a privacy-conscious approach where personal journal entries and photographs can remain on the user's computer in the intended local setup.

Most importantly, this project explores a different way to use AI: not to keep people glued to their screens, but to help them preserve the experiences they have away from them.

I want technology to help us remember life, not replace living it.