DEV Community: Astha Soni

Small Actions. Infinite Impact.

Astha Soni — Thu, 29 Oct 2026 10:29:47 +0000

Hacktoberfest Open-Source AI Challenge — Week 4: Ghost in the Machine

What I Built

I built EcoSphere, an interactive sustainability website designed to encourage people to take small, meaningful actions to protect our planet.

My interpretation of Ghost in the Machine is the hidden influence of technology on our world. Technology can feel invisible, but its impact on our environment is real. With EcoSphere, I wanted to use a digital experience to remind people that even small actions can make a difference.

The website includes interactive environmental challenges, progress tracking, and a responsive interface that makes sustainability engaging and accessible.

Demo

🌐 Live Website: https://asthasonimicrosoft-code.github.io/myrepo12/

Code

💻 GitHub Repository: https://github.com/asthasonimicrosoft-code/myrepo12

The project is built using HTML, CSS, and JavaScript.

How I Built It

I built the website using three core web technologies:

HTML for the structure and content.
CSS for the layout, visual design, animations, and responsive styling.
JavaScript for interactive challenges, progress tracking, and user interactions.

I focused on making the website easy to navigate, visually engaging, and accessible across different screen sizes.

Open-source AI usage: [Add the name of the open-weight AI model, agent framework, or local inference tool you actually used, and explain how it contributed to the project.]

Why Does Open Innovation Matter?

Open innovation gives developers the freedom to experiment, learn from others, and build on shared knowledge. Open-source tools make it easier for students and independent developers to explore new ideas without needing expensive infrastructure or relying entirely on closed platforms.

For a project like EcoSphere, this spirit of openness means that others can explore the code, suggest improvements, contribute new features, and adapt the idea to their own communities.

I believe technology becomes more meaningful when people can learn from it and build upon it together.

The Spirit of It

EcoSphere is built around a simple idea: small actions can create a meaningful impact when people take them together.

I wanted to turn an everyday environmental message into an interactive digital experience rather than just another page of information. This project also gave me an opportunity to practice front-end development and explore how technology can be used to communicate a positive message.

Prize Categories

[Add the applicable partner prize categories after checking the official challenge rules.]

Project: EcoSphere

Live Demo: https://asthasonimicrosoft-code.github.io/myrepo12/

Source Code: https://github.com/asthasonimicrosoft-code/myrepo12

FocusFlow AI — Your Smart Study Planner

Astha Soni — Fri, 23 Oct 2026 04:38:17 +0000

FocusFlow AI — Plan Smart. Focus Deep. Achieve More.

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

What I Built

I built FocusFlow AI, a smart study planner designed to help students manage their daily tasks, stay focused, and build better study habits without making productivity complicated.

As a student, I understand how difficult it can be to balance assignments, programming practice, exams, and personal goals. Sometimes, planning what to study takes more time than actually studying!

That's why I created FocusFlow AI: a simple, modern productivity dashboard that helps students get organized and start working.

Key Features

Task Management: Add, complete, and delete study tasks.
Priority Management: Organize tasks by High, Medium, and Low priority.
Pomodoro Timer: Use a 25-minute focus session to concentrate on one task at a time.
Progress Dashboard: Track total tasks, completed tasks, and overall completion percentage.
Browser Storage: Keep your tasks saved using local storage.
Responsive UI: Access the planner on desktop, tablet, or mobile.
Modern Design: Enjoy a clean dark interface with purple accents and smooth animations.

The idea is simple: spend less time organizing your day and more time learning something meaningful.

Demo

Try FocusFlow AI here:

https://asthasonimicrosoft-code.github.io/focusflow-ai/

Explore the dashboard, create study tasks, track your progress, and try the Pomodoro timer.

Code

GitHub Repository:

https://github.com/asthasonimicrosoft-code/focusflow-ai.git

The project is built with three core web technologies:

HTML5 for the structure.
CSS3 for the styling, animations, and responsive design.
JavaScript for task management, progress calculations, timer functionality, and local storage.

The project is designed to be beginner-friendly, easy to understand, and simple to extend with new features.

How I Built It

I built FocusFlow AI using HTML, CSS, and JavaScript, keeping the project lightweight and easy to run in a web browser.

I focused on creating a polished user interface while making sure the main features were functional.

The application uses JavaScript to manage tasks, update progress statistics, and control the 25-minute Pomodoro timer. Browser local storage helps preserve tasks between visits.

For the visual design, I used a dark background, purple highlights, responsive layouts, and subtle hover animations to create a modern productivity dashboard.

What about AI?

The current version is a productivity planner, not yet an AI-powered application. It does not currently integrate an open-weight model, local inference engine, or AI agent.

My next goal is to integrate an open-source model, such as Gemma running locally through Ollama, to provide personalized study suggestions and help students plan their learning sessions.

This would allow me to build on the existing project while exploring open-source AI in a practical way.

Why Does Open Innovation Matter?

Open innovation makes it possible for developers, students, and independent builders to learn from one another, experiment freely, and improve existing ideas.

For a student developer like me, open-source projects are an opportunity to move beyond tutorials and build something real.

I created FocusFlow AI as a foundation that others can explore, learn from, and improve. In the future, integrating an open-weight AI model could also give users more control over their data and let them experiment without depending entirely on a closed AI API.

I believe useful technology should be accessible to people who want to learn, build, and contribute, regardless of their experience level.

My Agent Session

I developed this project using HTML, CSS, and JavaScript.

I have not included a DevRelay agent session in this submission. If I create and save a session for this project, I will add its link here.

The Lazy Payoff

FocusFlow AI is designed to reduce the small bits of friction that make studying harder than it needs to be.

Instead of keeping tasks scattered across notes or trying to calculate progress manually, students can organize tasks, mark completed work, and see their progress in one place.

The built-in Pomodoro timer also makes it easy to start a focused 25-minute study session without needing a separate timer application.

The biggest payoff is simplicity: open the dashboard, choose a task, start the timer, and get to work.

Prize Categories

This project is a student productivity web application built with HTML, CSS, and JavaScript.

I have not claimed an open-source AI partner category yet because the current version does not include an AI model or agent integration. I will update this section if I implement a qualifying open-source AI integration and confirm the relevant challenge category.

Final Thoughts

FocusFlow AI started with a simple idea: make it easier for students to focus on their goals instead of worrying about how to organize them.

This is one step in my journey as a developer, and I hope to keep improving it by adding open-source AI capabilities and useful features for students.

If you like the project, feel free to explore the code, share feedback, or contribute!

Live Demo: https://asthasonimicrosoft-code.github.io/focusflow-ai/

GitHub: https://github.com/asthasonimicrosoft-code/focusflow-ai.git

Hacktoberfest #OpenSource #WebDevelopment #JavaScript #Productivity #AI

Altrix Health Copilot: An AI-Powered Vision for Smarter, More Accessible Healthcare

Astha Soni — Thu, 15 Oct 2026 09:49:51 +0000

Altrix Health Copilot: Smarter Insights. Healthier You. 💚

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

What I Built

I built Altrix Health Copilot, a modern healthcare-focused web project designed to make personal health information easier to explore and understand.

The idea is to create a digital health companion that helps people engage with their health through an intuitive, visually appealing interface. Altrix aims to make health technology feel more accessible, especially for people who want a simpler way to organize and understand their health-related information.

The long-term vision is to develop it into a useful health companion for individuals, wellness-focused users, and organizations looking for approachable digital health tools.

Demo

🌐 Live Website: https://asthasonimicrosoft-code.github.io/altrix_health_copilot

Explore the Altrix Health Copilot interface and its design.

Code

💻 GitHub Repository: https://github.com/asthasonimicrosoft-code/altrix_health_copilot.git

The project is built using separate HTML, CSS, and JavaScript files, making the frontend easy to explore, understand, and improve.

I welcome feedback, suggestions, and contributions from the open-source community!

How I Built It

I built Altrix Health Copilot using:

HTML to structure the website and its content.
CSS to create a modern, polished interface with a healthcare-inspired visual style.
JavaScript to support frontend interactions.
GitHub to host the source code.
GitHub Pages to make the website publicly accessible.

I focused on making the experience visually engaging while keeping the code organized into separate files.

The current version is a frontend prototype and a foundation for future development. Integrating an open-weight AI model is a planned next step so that the project can provide more personalized, conversational health assistance. The current version should not be considered a medical diagnostic tool.

Why Does Open Innovation Matter?

Open innovation makes it possible for developers, students, and creators to learn from one another, experiment with new ideas, and improve projects collaboratively.

For a project like Altrix Health Copilot, open-source development creates opportunities to explore AI models, improve accessibility, and build more transparent health-related experiences without depending entirely on a single proprietary platform.

It also gives other developers the freedom to inspect the code, suggest improvements, and contribute ideas that can help the project grow.

I believe that useful technology should be easier to access, understand, and improve together.

Prize Categories

Challenge: Hacktoberfest Open-Source AI Challenge Week 2: Side Hustle.

My project explores the potential for a healthcare-focused digital product. Open-weight AI integration and further development are planned next steps.

TerraAI: Touch Grass — An Open-Source AI That Turns Screen Time into Green Time

Astha Soni — Sun, 11 Oct 2026 13:10:16 +0000

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

What I Built

Demo

Code

How I Built It

Why Does Open Innovation Matter?

My Agent Session

Prize Categories

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

What I Built

🌿 TerraAI — Touch Grass: Less Screen Time, More Green Time

I built TerraAI, a web-based outdoor activity planner designed to help people take a break from their screens and reconnect with nature.

In a world where we spend hours studying, working, and scrolling on our devices, sometimes the best thing technology can do is help us step away from it.

TerraAI encourages users to spend more time outdoors by suggesting simple activities based on their mood, available time, and interests.

🌱 What can you do with TerraAI?

🚶 Discover mindful walking activities.
🌿 Find simple gardening ideas.
🐦 Explore birdwatching activities.
🧘 Take a mindful outdoor break.
⏱️ Choose an activity that fits your available time.
🌙 Switch between light and dark themes.

The project is designed for students, people working at desks, nature lovers, and anyone who wants to spend less time scrolling and more time experiencing the world.

My goal: Make the screen the shortest part of the outdoor experience.

Demo

🌐 Try TerraAI here:

https://asthasonimicrosoft-code.github.io/terra-ai/

Open the website, enter how you're feeling, select your available time, choose an activity, and discover your next outdoor adventure!

Code

💻 GitHub Repository:

https://github.com/asthasonimicrosoft-code/terra-ai

The project uses three main files:

index.html — Website structure and planner interface.
style.css — Visual design, responsive layout, and themes.
script.js — Activity recommendation logic and AI integration.

The repository is publicly available, and I welcome suggestions and contributions that make TerraAI more useful.

How I Built It

I built TerraAI using HTML, CSS, and JavaScript to keep the project lightweight, accessible, and easy to run in a web browser.

The project explores browser-based AI through Transformers.js and an open-weight model from the Hugging Face ecosystem. It also includes a JavaScript fallback recommendation system for situations where the AI model cannot load.

Here's how the main components work:

Frontend: HTML provides the page structure, while CSS handles the outdoor-inspired design and responsive interface.
Interactions: JavaScript collects the user's mood, available time, and activity preference.
AI exploration: Transformers.js provides a way to load compatible machine-learning models directly in the browser.
Fallback: If model loading fails, the application can still suggest an activity using its built-in recommendation logic.
Deployment: GitHub Pages hosts the website, so users can access it through a public link.

I deliberately chose a browser-based approach instead of requiring users to install Ollama or run a separate Python backend.

The current version is a prototype, and the AI model integration is experimental. The model requires an internet connection to download its files unless a compatible model has already been cached. The fallback recommendations do not themselves require an AI model.

Why Does Open Innovation Matter?

For me, open innovation means being able to experiment, learn, and build without being locked into a single proprietary AI service.

TerraAI explores several important advantages:

1. Accessibility for beginners

Using open-source web libraries and available open-weight models makes AI experimentation more approachable for developers who are still learning.

2. More flexibility

I can experiment with compatible models, compare their performance, and change the implementation as the project grows.

3. Fewer infrastructure requirements

A browser-based approach means I don't need to maintain a dedicated AI server for this prototype or ask users to install Ollama.

4. More control over the experience

The application combines AI experimentation with my own interface and recommendation logic, allowing me to shape how the technology serves the user's needs.

5. Technology with a real-world purpose

The most important part of TerraAI isn't keeping users engaged with another screen. It's using technology to encourage real-world experiences.

Open-weight models still have their own licences, hardware requirements, and limitations, and browser-based AI may require internet access. However, open innovation gives me the freedom to explore alternatives and learn how these systems work.

My Agent Session

I don't have a DevRelay agent-session link to share yet. I'll add it here if I publish a session documenting the development process.

Prize Categories

Primary theme: Touch Grass — outdoor activities and real-world experiences supported by open-source AI.

TerraAI explores browser-based AI and open-weight models to help users discover activities beyond their screens.

Note: This submission focuses on the challenge theme. Any additional partner prize categories should be selected only if the project meets their specific eligibility requirements.

🌿 Less Screen Time. More Green Time.

TerraAI is my attempt to explore a simple idea: technology doesn't always have to keep us online. Sometimes, it can help us find a reason to go outside.

If you like the idea, check out the project, try the demo, and share your feedback!

Hacktoberfest #OpenSourceAI #TouchGrass #TerraAI #JavaScript #TransformersJS #HuggingFace