DEV Community: Surya Jyoti Mantry

Nature Explorer: A Local AI Field Journal

Surya Jyoti Mantry — Tue, 20 Oct 2026 14:38:46 +0000

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

What I Built

Nature Explorer is a digital field journal designed to help people notice more when they step outside.

Take a photo of a plant, bird, insect, animal, fungus, or natural feature. Choose a category, and the field assistant suggests an identification, description, likely habitat, confidence level, and a short field note. You can save the discovery to a personal collection, then search and filter your finds later.

The collection stays in the browser, so there is no account to create and no database to set up. The idea is to make the screen a quick companion for an outdoor observation—not the destination.

Demo

https://youtu.be/gn9LlaW3EgU

Code

https://github.com/suryastack/Nature-Explorer

How I Built It

The frontend is built with React, TypeScript, and Tailwind CSS. A separate Node.js and Express backend accepts the image and sends it to Ollama, which runs the open-weight Gemma 3 4B vision model locally.

The model returns a structured suggestion that the app displays as a field note. Discoveries are saved in the browser: image files go into IndexedDB, while lightweight details such as category and date are stored in localStorage.

There is no hosted AI API, database, or user account in the MVP. After downloading the model, image analysis runs through Ollama on the user's computer.

Why Does Open Innovation Matter?

Nature photos can reveal personal routines and locations. Running the vision model locally lets people explore an image without sending it to a hosted AI service or creating an API account.

Open-weight models also make the project easier to adapt. Developers can inspect the setup, experiment with other compatible vision models, and improve the field assistant without redesigning the whole app around a closed API.

For this project, open innovation made a private, locally run nature journal possible on an everyday laptop.

Prize Categories

Best Use of Gemma

Study Buddy: A Local AI Study Partner Built with Gemma 3

Surya Jyoti Mantry — Wed, 14 Oct 2026 13:58:36 +0000

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

What I Built

I built Study Buddy for my friends who need a quick, focused way to prepare for exams at the last minute. They wanted to practise short question-and-answer sessions on different topics and keep important points handy.

Study Buddy lets users save and organize notes, then turn a note into a short summary, five quiz questions, and an answer key. My friends tried it and said it was useful for last-minute exam preparation, practising questions on a topic, and keeping important points in one place.

Demo

https://youtu.be/ddcUgjEjD7s

Code

https://github.com/suryastack/Study-Buddy

How I Built It

The frontend uses React, Redux Toolkit, and CSS. An Express backend handles notes and study-set requests.

For AI, I used Gemma 3 1B, an open-weight model, running locally through Ollama. When someone clicks “Make me a quiz,” the app sends the selected note to Express, which asks the local Ollama instance to generate the study set.

Why Does Open Innovation Matter?

The model runs on my own computer, so notes go to local Ollama instead of a hosted AI API. There’s no AI API key or per-request API charge. After the initial model download, Gemma can generate study sets locally. I can also try a different Ollama-compatible model without rebuilding the whole app.

Prize Categories

Best Use of Gemma

Nature Explorer: A Local AI Field Journal

Surya Jyoti Mantry — Wed, 07 Oct 2026 11:17:51 +0000

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

What I Built

Nature Explorer is a digital field journal designed to help people notice more when they step outside.

The collection stays in the browser, so there is no account to create and no database to set up. The idea is to make the screen a quick companion for an outdoor observation—not the destination.

Demo

https://youtu.be/gn9LlaW3EgU

Code

https://github.com/suryastack/Nature-Explorer

How I Built It

There is no hosted AI API, database, or user account in the MVP. After downloading the model, image analysis runs through Ollama on the user's computer.

Why Does Open Innovation Matter?

Nature photos can reveal personal routines and locations. Running the vision model locally lets people explore an image without sending it to a hosted AI service or creating an API account.

For this project, open innovation made a private, locally run nature journal possible on an everyday laptop.

Prize Categories

Best Use of Gemma

Study Buddy: A Local AI Study Partner Built with Gemma 3

Surya Jyoti Mantry — Sun, 04 Oct 2026 15:08:44 +0000

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

What I Built

I built Study Buddy for my friends who need a quick, focused way to prepare for exams at the last minute. They wanted to practise short question-and-answer sessions on different topics and keep important points handy.

Demo

https://youtu.be/ddcUgjEjD7s

Code

https://github.com/suryastack/Study-Buddy

How I Built It

The frontend uses React, Redux Toolkit, and CSS. An Express backend handles notes and study-set requests.

For AI, I used Gemma 3 1B, an open-weight model, running locally through Ollama. When someone clicks “Make me a quiz,” the app sends the selected note to Express, which asks the local Ollama instance to generate the study set.

Why Does Open Innovation Matter?

Prize Categories

Best Use of Gemma