DEV Community: Saloni Soni

AII: Turning Ideas into Impact — Building for a Better Digital Experience

Saloni Soni — Sun, 01 Nov 2026 08:28:52 +0000

🌱 AII — Building for a Better Digital Experience

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

What I Built

I built AII, a web-based project that represents my journey into web development and Artificial Intelligence.

As a first-year B.Tech CSE student specializing in AI/ML, I wanted to turn my ideas into something real instead of just learning theory. This project is a step toward exploring how technology can create useful, accessible, and engaging digital experiences.

I built this project with the goal of learning by doing, experimenting with web technologies, and exploring opportunities to integrate open-source AI.

Who is it for?

AII is for people who enjoy exploring technology and discovering new digital experiences. My bigger motivation is to build projects that can eventually help someone in a meaningful way.

Demo

🌐 Live Website: https://saloni2008apk.github.io/aii/

Code

💻 GitHub Repository: https://github.com/Saloni2008apk/aii

The project is built with web technologies, including HTML, CSS, and JavaScript.

How I Built It

I used HTML to structure the website, CSS to style the interface, and JavaScript to explore interactivity. I deployed the project using GitHub Pages so people can access it online.

This challenge encouraged me to think beyond simply writing code and consider how open-source tools and AI could help me build something more useful.

AI model or agent used: [Add the open-weight model, framework, or coding agent you actually used.]

I’m still learning, and this project is part of my journey toward building more capable AI-powered applications.

Why Does Open Innovation Matter?

Open innovation makes technology more accessible to students, beginners, and independent developers like me.

Open-weight AI models and open-source tools can help developers experiment, learn how systems work, customize solutions, and build without depending entirely on closed platforms.

For students who are just starting, open innovation lowers barriers to experimentation and encourages collaboration. It also makes it easier to share ideas, learn from other developers, and improve projects together.

I believe great ideas shouldn't be limited by who has access to expensive tools. Open innovation gives more people the opportunity to create, contribute, and solve real problems.

My Agent Session

[Optional: Add your DevRelay
Thanks for checking out my submission!

GhostScript AI: Where Open-Source AI Brings Memories Back to Life

Saloni Soni — Tue, 27 Oct 2026 07:55:01 +0000

This is a submission for the Hacktoberfest Open-Source AI Challenge Week 4: Ghost in the Machine.

👻 What I Built

What if our memories could become stories that feel like whispers from the past?

Introducing GhostScript AI — The Memory Keeper, a spooky storytelling project inspired by Halloween, forgotten memories, and the power of artificial intelligence.

The idea behind GhostScript AI is simple: users provide a memory, a creative idea, or a story prompt, and the application transforms it into an atmospheric ghost story.

Imagine entering a memory of an old house, a strange sound at midnight, or a forgotten moment from childhood and turning it into a mysterious story.

I wanted to explore how AI can bring imagination to life while giving people more control over the technology behind their creative tools.

This project combines a spooky visual experience with my interest in AI and open-source development.

🎃 Demo

The goal is to create an interactive storytelling experience where users can enter a prompt and explore the story it inspires.

Project status: Experimental project.

A live demonstration will be added when the application is deployed and its functionality is verified.

💻 Code

GitHub Repository: [GhostScript AI — Add your repository link here before publishing]

The planned technology stack includes:

HTML5: Structure of the website.
CSS3: Dark, atmospheric design, animations, and visual effects.
JavaScript: User interaction and application logic.
Open-weight language model: Story generation through a compatible local inference setup.

The AI integration is a key part of the project's direction. The final implementation should identify the actual model and inference tool used.

🛠️ How I Built It

I approached this project as a learning experience in combining web development with open-source AI.

The application is designed around four main steps:

Enter a prompt: The user describes a memory, an idea, or a spooky scenario.
Process the input: The application prepares the prompt for the configured AI model.
Generate a story: The model produces a creative response based on the user's input.
Display the result: The generated story appears in a Halloween-inspired interface.

For the website, HTML, CSS, and JavaScript provide a simple foundation that beginners can understand and extend.

For AI generation, an open-weight model that supports local inference is a promising option. A tool such as Ollama could make it possible to run a compatible model on a user's computer without sending prompts to a hosted AI API.

Local inference requires a suitable model, compatible hardware, and a working integration. The application should not be considered fully offline until those capabilities have been implemented and tested.

🔓 Why Does Open Innovation Matter?

Open innovation is important because AI should not be limited to applications controlled entirely by a single company or closed API.

For a project like GhostScript AI, open-weight models offer the opportunity to experiment, customize the experience, and explore local processing.

Here are the main benefits I want to explore:

1. Privacy comes first

Personal memories and family stories can be sensitive. With a properly configured local model, prompts can be processed on the user's own computer instead of being sent to an external AI service.

2. More freedom to experiment

Developers can explore different compatible models, adjust prompts, and experiment with storytelling styles instead of depending on a single provider.

3. Less dependence on paid APIs

Local inference can reduce per-request API costs. However, running models still requires hardware, electricity, storage, and setup.

4. Learning by building

Open-source tools give beginners an opportunity to understand how AI applications work, explore available implementations, and improve their projects step by step.

5. Technology that can evolve

An open approach makes it easier to adapt a project as new models and tools become available, subject to their licenses and technical requirements.

The biggest lesson for me is that open innovation is not just about using free software. It is about having the freedom to learn, experiment, customize, and make informed choices about the technology we build with.

🤖 My Agent Session

I plan to document the development process using DevRelay.

Agent session: To be added if a saved session becomes available.

This section is optional.

🕯️ The Spirit of It

Halloween reminds us of the mysterious and the unknown. Día de los Muertos reminds us of the importance of remembering the people and stories that have shaped our lives.

GhostScript AI takes inspiration from both ideas.

A memory does not have to disappear just because time passes. Stories allow us to revisit moments, explore our imagination, and preserve pieces of the past.

I wanted to explore the intersection of these ideas with artificial intelligence: not simply generating another spooky story, but experimenting with technology that could help people tell and preserve stories in their own way.

For me, the spirit of this project is curiosity. As a beginner exploring AI and software development, I want to learn by building something creative, meaningful, and capable of growing over time.

🚀 What's Next?

There are several features I would love to explore as the project develops:

A working local AI storytelling engine.
Offline story generation after the model has been downloaded and configured.
Multiple storytelling styles, including horror, mystery, and nostalgia.
A way to save and revisit favorite stories.
Privacy-conscious storage for personal memories.
Support for additional open-weight models.

These improvements would help turn the concept into a more complete storytelling application.

💜 Final Thoughts

Building with AI is not only about using the most powerful model available. It is also about understanding the tools, exploring alternatives, and deciding what kind of technology we want to create.

GhostScript AI is my exploration of that idea through spooky storytelling and open-source AI.

Sometimes, the most interesting things are not the ones hiding in the dark, but the possibilities waiting to be discovered when we open the machine.

What would you build if you could give a forgotten memory a new story? 👻

I'd love to hear your ideas!

Hacktoberfest #OpenSourceAI #GhostInTheMachine #AI #DevChallenge

From Idea to Impact: Building My First MLH Hackathon Project | #mlhacks

Saloni Soni — Fri, 23 Oct 2026 12:35:44 +0000

🚀 From Idea to Impact: Building My MLH Hackathon Project

This is a submission for the MLH x DEV Writing Challenge.

💡 What I Built

I built [Project Name], a project designed to [explain the main purpose of your project and the problem it solves].

The inspiration behind this project was [explain what motivated you to build it].

✨ Key Features

[Feature 1]: [Explain what it does.]
[Feature 2]: [Explain how it helps users.]
[Feature 3]: [Describe another useful feature.]

My goal was to create something that is practical, creative, and useful in solving a real-world problem.

As a developer, I learned [mention the main skill, technology, or lesson you gained while building the project].

🎬 Demo

Check out my project!

Live Demo: [Insert your deployed project link]
GitHub Repository: [Insert your GitHub repository link]
Screenshots/Video: [Insert screenshots or a demo video]

How It Works

The user [describe the first step].
The application [explain the main functionality].
The project produces [describe the result or benefit].

🛠️ Technologies Used

Frontend: [HTML, CSS, JavaScript, React, etc.]
Backend: [Node.js, Python, etc., if applicable]
AI/ML: [Model, API, or framework, if applicable]
Tools: [VS Code, GitHub, DevRelay, etc.]

🤝 Partner Technologies

I used [MLH partner technology name] to [explain exactly how you integrated it into your project].

Working with this technology helped me [describe your experience, what worked well, and what you learned].

[If you didn't use an MLH partner technology, explain that honestly rather than claiming an integration you didn't make.]

🎉 Hackathon Experience

Participating in the MLH hackathon was an exciting opportunity to turn an idea into a working project.

During this experience, I explored new technologies, experimented with different approaches, and learned how to approach problems creatively.

One of my biggest challenges was [describe a real challenge you faced], which I addressed by [explain what you tried or changed].

My biggest takeaway was that building projects is not just about writing code; it is also about learning, collaborating, experimenting, and improving through feedback.

📚 What I Learned

How to transform an idea into a working project.
How to use development tools and technologies more effectively.
How to troubleshoot errors and improve my problem-solving skills.
The importance of testing, user experience, and continuous learning.

🔮 What's Next?

In the future, I plan to improve [Project Name] by adding [planned feature], improving [existing feature], and making it more useful for its intended users.

This is just the beginning, and I look forward to learning more and building better projects.

💚 Final Thoughts

This hackathon experience reminded me that every great project begins with an idea and the willingness to build something.

I'm proud of what I've learned, the challenges I've overcome, and the progress I've made.

Thank you to MLH and DEV for encouraging developers to experiment, build, and share their work!

If you find this project interesting, check out the repository and share your feedback.

Let's keep building, learning, and creating! 🚀

mlhacks #MLH #Hackathon #WebDevelopment #BuildInPublic

Built with Love, Powered by Open-Source AI 💚 | #BuildForAFriend #hacktoberfest2026

Saloni Soni — Fri, 23 Oct 2026 12:26:17 +0000

💝 [Project Name] — Built with Open-Source AI for Someone I Care About

🌟 What I Built

I built [Project Name], an AI-powered tool designed specifically for my friend, [Friend's Name/Nickname], to help them with [describe the real problem].

Instead of creating a project just for the sake of coding, I wanted to build something personal, useful, and meaningful.

The problem: [Explain the difficulty your friend faces.]

My solution: [Explain how your project solves that problem.]

👥 Who I Built It For

I built this project for my [friend / roommate / family member / someone I care about].

They were struggling with [specific problem], so I decided to use technology and open-source AI to make their daily life a little easier.

✨ Key Features

🤖 AI-powered assistance: [Describe the AI feature.]
🔒 Privacy-focused: [Explain how personal data is protected.]
🌱 Open-source AI: Uses [model/framework name] as a core part of the project.
💻 Easy to use: [Explain how your friend interacts with it.]
❤️ Built around a real need: Designed for one specific person rather than everyone in general.

🛠️ How I Built It

Technologies used:

Frontend: [HTML, CSS, JavaScript, etc.]
AI model: [Open-weight model name]
AI framework/agent harness: [Framework name, if applicable]
Local inference: [Ollama / other tool / not applicable]
Development tools: [VS Code, GitHub, DevRelay, etc.]

Development process:

Identified a real problem my friend was facing.
Planned a simple solution around their needs.
Selected an open-source AI model or framework.
Built and tested the main features.
Improved the project based on testing and feedback.
Shared the finished project with my friend.

🌍 Why Open Innovation Matters

I chose open-source AI because I wanted to explore how accessible AI tools can solve real-world problems.

Using [model/framework name] gave me the opportunity to [run AI locally / customize the model / change the workflow / reduce dependence on paid APIs].

Compared with a closed AI solution, my open-based approach offers [specific advantage, such as greater control, offline access, privacy, customization, or lower running costs].

What makes this approach valuable: [Explain the actual benefit your project gains from open-source AI. Be honest about what works locally and what requires an internet connection.]

🎬 Demo

Live demo: [Insert your live project URL]
Demo video or screenshots: [Insert link or images]
Source code: [Insert your GitHub repository URL]

💬 My Friend's Reaction

After building the project, I shared it with my friend.

Their feedback was:

"[Insert your friend's actual reaction or feedback.]"

The most meaningful part of this challenge was seeing how something I built could help someone I care about.

[If you haven't shared it yet, replace this section with your plans to test it with your friend.]

🧠 What I Learned

Through this project, I learned:

How open-source AI can be applied to a real problem.
How to turn an idea into a

TouchGrass AI: Less Screen Time, More Green Time | Building with Open-Source AI #hacktoberfest26

Saloni Soni — Fri, 23 Oct 2026 10:06:02 +0000

🌱 [Project Name] — Building with Open-Source AI

Challenge: Slow and Steady

Tags: #mlhacks #opensource #ai #hacktoberfest

🚀 What I Built

I built [Project Name], a [website/application/tool] designed to solve [describe the problem in one sentence].

The main goal of this project is to help [target users] by providing [main features or benefits].

I wanted to build something practical, beginner-friendly, and useful while exploring how open-source AI can make technology more accessible to everyone.

💡 The Problem

Many people struggle with [describe the problem].

Existing solutions may be expensive, require constant internet access, raise privacy concerns, or be difficult for beginners to use.

My project explores a simpler and more accessible approach using open-source technology.

✨ Key Features

[Feature 1]: [Explain what it does.]
[Feature 2]: [Explain how it helps users.]
[Feature 3]: [Describe another useful feature.]
Simple interface: Easy to navigate and beginner-friendly.
Open-source foundation: Designed to encourage learning, experimentation, and collaboration.

🤖 How I Used Open-Source AI

Open-source AI is an important part of this project because it offers opportunities to experiment, customize solutions, and learn how AI systems work.

Technology used: [Name the actual open-weight model, AI framework, agent harness, or local inference tool used.]

I chose this approach because [explain why it fits your project].

How it works:

The user provides [input or request].
The application processes the input using [actual model, framework, or logic].
The system generates [output or result].
The user receives [the benefit].

If your current version does not yet use an AI model, describe the AI integration as planned work rather than claiming it is already implemented.

🛠️ Tech Stack

Frontend: HTML, CSS, JavaScript
AI / Model: [Actual model or write “Not integrated yet”]
Framework / Runtime: [Actual tools used]
Development environment: Visual Studio Code
Version control: Git and GitHub

⚙️ How I Built It

Identified the problem and defined the project's main purpose.
Designed the user interface and planned the core features.
Developed the application using [actual technologies].
Tested the main features and fixed issues.
Organized the source code and published the project repository.
Explored how open-source AI could improve the application.

🧪 Example Use Case

Scenario: [Describe a realistic situation in which someone would use your project.]

Input: [Example user input]

Expected result: [Explain what the application actually returns.]

🎥 Demo

Live demo: [Insert your deployed project URL]

Screenshots / video: [Insert screenshots or a short demonstration video]

💻 Source Code

GitHub repository: [Insert your public repository URL]

The repository contains the source code, setup instructions, and project documentation.

🌍 Why Open Innovation Matters

Open innovation allows developers to learn from shared knowledge, inspect available source code, experiment with different tools, and build on the work of the wider community.

For students and beginner developers, open-source AI makes experimentation more accessible and provides an opportunity to learn by building real projects.

Through this project, I want to keep learning, contribute to the developer community, and explore how accessible AI can solve practical problems.

🚧 Challenges I Faced

During development, I worked through challenges such as [describe a real technical issue, debugging problem, or design decision].

I approached these challenges by [explain what you tried, learned, or changed].

This experience helped me improve my understanding of [relevant skill or technology].

📚 What I Learned

How to plan and develop a project around a real problem.
How to organize and document a GitHub repository.
How to test features and improve usability.
How open-source tools can support experimentation and collaboration.
The importance of documenting limitations and distinguishing implemented features from future plans.

🔮 What's Next?

[Planned feature 1]
[Planned feature 2]
[Potential AI integration or local inference support]
Better testing, documentation, and accessibility.
Community feedback and contributions.

🙌 Acknowledgements

Thanks to the open-source community and the organizers of the challenge for encouraging developers to experiment, learn, and build in public.

💬 Feedback and Contributions

I'd love to hear your suggestions!

If you find this project interesting, please explore the repository, share feedback, or contribute ideas for future improvements.

Built with curiosity, creativity, and a willingness to learn. 🌱

TouchGrass AI 🌱 — Turn Screen Time into Green Time

Saloni Soni — Thu, 22 Oct 2026 08:50:58 +0000

TouchGrass AI: Using AI to Help People Get Off Their Screens 🌱

A project built for the MLH × DEV Writing Challenge

💡 What I Built

I built TouchGrass AI, a web project designed to encourage people to spend less time on their screens and more time exploring the real world.

The idea is simple: technology should not only keep us connected to our devices; it should also help us reconnect with the world around us.

I wanted to explore how AI could make outdoor activities and real-world experiences more interesting and accessible.

🎯 Why I Built It

We spend so much time scrolling, gaming, and watching content that we sometimes forget to step outside and enjoy the world around us.

I wanted to experiment with a project that uses technology to encourage healthier digital habits and inspire people to try something new.

⚙️ How It Works

TouchGrass AI is built as a web project using:

HTML to structure the website.
CSS to style the interface and make it visually appealing.
JavaScript to add interactivity.

The goal is to develop the project into a helpful experience that encourages users to discover outdoor activities and take breaks from their screens.

AI integration: [Describe the open-source AI model, framework, or AI-powered feature you actually implemented. If AI is not integrated yet, explain your next step honestly.]

🛠️ How I Built It

I worked on the project using VS Code and explored how HTML, CSS, and JavaScript work together to create a website.

As a beginner in AI/ML and web development, I approached the project as an opportunity to learn by building something practical.

Some of the things I focused on were:

Creating the website structure.
Designing the user interface.
Adding interactive functionality.
Exploring how AI could improve the experience.

🚧 Challenges I Faced

One of my biggest challenges was turning a simple idea into a working project while still learning the fundamentals of development.

I had to think about how the website should look, how users would interact with it, and how I could make the concept useful rather than just another website.

This experience reminded me that building something meaningful starts with an idea, experimentation, and a willingness to learn.

📚 What I Learned

Through this project, I learned more about building websites, organizing a project, and breaking a large idea into smaller tasks.

I also learned that hackathons are not only about creating a perfect product. They are about experimenting, solving problems, learning new tools, and sharing what you discover.

🌍 Why Open Innovation Matters

Open-source tools and open-weight AI models can make experimentation more accessible to students and independent developers.

They can help builders learn from existing work, customize solutions, and explore new ideas without having to build every component from scratch.

My next goal is to explore how open-source AI can become a meaningful part of TouchGrass AI, while keeping the project accessible and useful.

🔮 What's Next?

I would love to keep improving TouchGrass AI by exploring features such as:

Personalized outdoor activity suggestions.
Recommendations based on available time and interests.
More engaging and interactive user experiences.
An open-source AI component, where appropriate.

These are future ideas, not claims about features already implemented.

🔗 Project Links

GitHub Repository: https://github.com/Saloni2008apk/TouchGrass-AI
Live Demo: https://saloni2008apk.github.io/TouchGrass-AI/
Screenshots/Demo Video: [Add your screenshot, GIF, or video here]

🙌 Final Thoughts

TouchGrass AI is a small step toward exploring how technology can encourage people to engage more with the world beyond their screens.

I am still learning, experimenting, and improving, and I am excited to see where this project goes next.

If you have suggestions, feedback, or ideas for improvement, I would love to hear them!

Built with curiosity, creativity, and a desire to learn. 🌱

mlhacks #hackathon #webdev #AI #opensource #beginners

TouchGrass-AI : Turning Open-Source AI into Real-World Adventures #hacktoberfest2026

Saloni Soni — Sat, 17 Oct 2026 03:35:17 +0000

TouchGrass-AI: Turning Screen Time into Real-Life Adventures with Open-Source AI 🌱

What I Built

I built TouchGrass-AI, a web project designed to encourage people to take breaks from their screens and spend more time exploring the real world.

In a world where we spend hours scrolling through our phones and sitting in front of computers, TouchGrass-AI aims to make offline activities more interesting, accessible, and fun.

The idea is simple: instead of spending all your free time online, discover small activities that help you reconnect with nature, explore your surroundings, and enjoy life beyond the screen.

Live Demo: https://saloni2008apk.github.io/TouchGrass-AI/

GitHub Repository: https://github.com/Saloni2008apk/TouchGrass-AI

Why I Built It

As a first-year B.Tech CSE student specializing in AI and ML, I wanted to build something meaningful while learning how technology can solve everyday problems.

Digital devices help us learn, communicate, and work, but excessive screen time can also make us forget about the world around us.

I wanted to turn this problem into an opportunity by building a project that encourages people to take action offline instead of simply consuming more digital content.

My goal is to make going outside feel less like a task and more like an adventure.

How I Built It

I started by building the website using:

HTML for the structure.
CSS for the visual design and styling.
JavaScript for interactivity.

I developed the project using Visual Studio Code and published the website through GitHub Pages.

My next step is to integrate an open-weight AI model or an open-source AI framework to generate personalized outdoor activity suggestions based on a user's interests, available time, and surroundings.

This would help transform TouchGrass-AI from a simple website into a more personalized AI-powered experience.

Where Open-Source AI Comes In

Open innovation matters because I want TouchGrass-AI to be accessible, affordable, and adaptable.

Using an open-weight model or an open-source AI framework can give me more control over how the project works. It can also make it possible to experiment with different models, reduce dependence on paid AI APIs, and explore privacy-friendly approaches.

For example, a future version could use a locally running model to suggest activities without sending a user's personal preferences to an external AI service.

I also want to explore whether a lightweight model could run on an ordinary laptop, making the experience more accessible to students and people with limited budgets.

My goal is to make open-source AI the engine behind useful real-world action, rather than adding AI just for the sake of it.

Transparency note: The current version is a web prototype built with HTML, CSS, and JavaScript. Open-weight model integration is a planned next step, not a feature I am claiming is already implemented.

Why This Could Be a Side Hustle

TouchGrass-AI could grow into a small product for people who want healthier digital habits and more enjoyable offline experiences.

Potential users include:

Students who spend too much time on their phones.
Remote workers who need meaningful screen breaks.
Friends looking for fun, low-cost outdoor activities.
Families and communities interested in offline challenges.

Possible future features include personalized activity plans, daily outdoor challenges, group challenges, and premium themed activity packs.

An open-source AI approach could help keep operating costs manageable and make the product easier to customize for different communities.

The business idea still needs real-user testing to determine which features people find valuable enough to pay for.

What Makes This Project Different?

TouchGrass-AI focuses on a simple but meaningful idea: using technology to help people spend less time using technology.

Rather than encouraging users to stay on a platform for longer, the project aims to turn a digital interaction into an offline experience.

I want the AI to help people discover what they can do in the real world, then give them a reason to close the tab and go outside.

Challenges I Faced

As a beginner in AI and ML, one of my biggest challenges was turning an idea into a working website while learning the development process.

I worked on the project using basic web technologies and learned about building, organizing, and deploying a website.

The next challenge is integrating a genuinely open-source or open-weight AI component and testing whether it provides useful recommendations without making the product expensive or complicated.

What's Next?

My next goals are to:

Integrate an open-weight AI model or an open-source AI framework.
Generate personalized outdoor activity recommendations.
Explore local inference for better privacy and lower recurring costs.
Test the project with real users and collect their feedback.
Discover whether users would pay for personalized challenges or other useful features.

Try It and Share Your Feedback 🌍

I would love for students, developers, and open-source enthusiasts to try TouchGrass-AI and share their suggestions.

What feature would make you use it regularly? Would you prefer daily challenges, personalized suggestions, or group activities with friends?

I am building this project as a student, learning one step at a time, and I hope to turn it into something genuinely useful.

Built with curiosity, powered by learning, and inspired by the world beyond the screen. 🌱

Hacktoberfest #OpenSourceAI #SideHustle #AI #WebDevelopment #BuildInPublic

TouchGrass AI: Turning Open-source AI into a Real-World Side Hustle #hacktoberfest2026

Saloni Soni — Thu, 15 Oct 2026 07:28:46 +0000

TouchGrass AI: Turning Open-Source AI into a Real-World Wellness Side Hustle 🌱

What I Built

I upgraded TouchGrass-AI into an AI-powered outdoor activity planner designed to help students spend less time scrolling and more time enjoying the real world.

Users can enter their available time, budget, and interests to receive personalized outdoor activity suggestions.

How I Built It

HTML, CSS, and JavaScript for the user interface.
Ollama to run an open-weight language model locally.
Local inference to generate personalized activity recommendations.

Why Open Innovation Matters

I wanted to explore an AI approach that gives users more control over their data and lets developers experiment with different models.

Local inference can reduce dependence on paid AI APIs and help keep user prompts on the user's own computer. The project also allows the underlying model to be changed as the application evolves.

The Side Hustle

TouchGrass-AI could become a small wellness product offering personalized activity plans, printable outdoor challenges, or group challenges for students.

What I Learned

This project helped me explore how open-weight AI can power a practical product beyond a basic chatbot.

Project: https://saloni2008apk.github.io/TouchGrass-AI/

Source code: https://github.com/Saloni2008apk/TouchGrass-AI

Note: The features and implementation described above should be updated to reflect what is actually working in the submitted version.

TouchGrass AI: Using Open-Source AI to Reconnect with the Real World | #Hacktoberfest 2026

Saloni Soni — Fri, 09 Oct 2026 17:20:00 +0000

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

What I Built

🌿 TouchGrass AI — Reconnect with the Real World

TouchGrass AI is a web project designed to encourage people to take a break from their screens and reconnect with the world around them.

In a world where students and young people spend a lot of time online, I wanted to explore how technology could encourage more meaningful offline experiences.

The project focuses on making it easier to discover outdoor activities, spend time in nature, and build healthier digital habits.

🎯 Who is it for?

Students who spend long hours studying or using screens.
People looking for ideas for outdoor activities.
Anyone who wants to balance their digital life with real-world experiences.

My vision is simple: technology should help us experience more of the real world, not keep us trapped behind a screen.

Demo

🌐 Live Website: https://saloni2008apk.github.io/TouchGrass-AI/

Try the live website and explore the current features.

Code

💻 GitHub Repository: https://github.com/Saloni2008apk/TouchGrass-AI

The project source code is available in my GitHub repository.

How I Built It

I built TouchGrass AI as a web development project using:

HTML — to structure the website.
CSS — to design the interface and layout.
JavaScript — to add interactivity.

I am a first-year B.Tech CSE student specializing in AI and Machine Learning, and this project is part of my journey to learn how to build useful applications.

Open-source AI integration: [Add the name of the open-weight model, open-source AI framework, or local inference tool you actually used, and explain how it powers a feature in TouchGrass AI.]

I want to explore how open-source AI can provide personalized outdoor activity recommendations and help people discover experiences beyond their screens.

Why Does Open Innovation Matter?

Open innovation makes technology more accessible to learners, students, and independent developers.

Open-source AI gives developers the opportunity to study available models, experiment with different approaches, customize solutions, and learn from the wider community.

For a student like me, open innovation lowers the barrier to experimentation and makes it possible to learn by building real projects.

I believe the best use of technology is not just to create more digital experiences, but also to help people live better experiences offline.

My Agent Session

I don't have a shareable agent session to include yet.

Prize Categories

My primary submission is for the **Hacktoberfest . Open source AI Challenge

week 1: Touch Grass**

Built with curiosity, a beginner's mindset, and a goal of making technology more human. 🌱

Thanks for checking out TouchGrass AI!