DEV Community: Arkendu Kundu

FriendStudy AI — an open-source AI study companion for students

Arkendu Kundu — Sun, 11 Oct 2026 04:32:16 +0000

I built FriendStudy AI — an open-source AI study companion for students 📚

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

💡 What I Built

I built FriendStudy AI, an AI-powered study companion designed to help students study more effectively.

Students often switch between multiple tools to understand difficult topics, create study plans, practice questions, and track their progress. I wanted to bring these activities together in one simple workspace.

FriendStudy AI helps students organize their learning, practice concepts, and build consistent study habits with the help of AI.

✨ Features

🤖 Ask AI questions about study topics.
📅 Generate personalized study plans.
🧠 Practice with AI-generated quizzes.
📈 Track study progress.
🔥 Maintain study streaks.
🎯 Organize daily study goals.
📚 Keep learning activities together in one workspace.

🎯 Who I Built It For

I built FriendStudy AI for students who want a simple study companion to help them understand concepts, practice questions, and stay consistent with their studies.

Students sometimes struggle not because they lack motivation, but because planning, learning, and revision are scattered across different tools.

FriendStudy AI brings these activities together so students can spend more time learning and less time organizing their study workflow.

🛠️ How I Built It

Here is the technology stack behind the project:

Frontend: React and JavaScript
Backend: Python and FastAPI
AI model: Qwen 2.5 3B through Ollama
Deployment: Vercel for the frontend and Render for the backend

I used an open-weight AI model so I could experiment with AI-powered study assistance without relying entirely on a proprietary model API.

🌍 Why Open-Source AI Matters

Open-source AI and open-weight models give developers more freedom to understand, customize, and experiment with AI systems.

For FriendStudy AI, using Qwen 2.5 3B through Ollama gave me an opportunity to explore local model inference and build an AI-powered learning experience using tools that developers can inspect and adapt.

This approach also makes it possible to experiment with different models and configurations as the project evolves.

I believe open innovation matters because students and developers should have opportunities to build useful tools without being completely dependent on closed platforms.

🚀 Try FriendStudy AI

🌐 Live demo: https://friendstudy-ai-hf26.vercel.app/

💻 GitHub repository: https://github.com/arkendukundu-dev/friendstudy-ai-hf26

🔮 What's Next?

I would like to improve FriendStudy AI by adding:

More personalized learning plans
Better quiz generation
Topic-wise progress tracking
More study resources and learning modes
Improved mobile responsiveness

💭 Final Thoughts

Building FriendStudy AI helped me explore how open-source AI can be used to solve a practical problem for students.

I wanted to create something more useful than a basic chatbot: a study companion that brings planning, practice, and progress tracking together.

This project is an ongoing learning experience for me, and I look forward to improving it with feedback from other developers.

What feature would you add to an AI study companion to make learning easier?

devchallenge #weekendchallenge #hf26challenge

TouchGrass AI — a little less scrolling, a little more living

Arkendu Kundu — Sun, 11 Oct 2026 04:15:37 +0000

🌱 TouchGrass AI — a little less scrolling, a little more living

live demo: https://touchgrass-ai.vercel.app/

github repository: https://github.com/arkendukundu-dev/touchgrass-ai

hf26challenge #hacktoberfest #opensource #ai #react #python

🌍 the problem

we spend so much time looking at screens that sometimes we forget to experience the world outside them.

many of us want to spend more time outdoors, explore new places, build healthier habits, or simply take a break from endless scrolling. but knowing we should take a break isn't always enough.

i wanted to turn that simple idea into something fun and actionable.

🌿 introducing touchgrass ai

touchgrass ai is an open-source, ai-powered wellness app that encourages people to step away from their screens and reconnect with the real world through small, achievable activities.

instead of just telling you to spend less time online, it gives you little outdoor quests to complete in real life.

✨ what can you do with it?

🌱 daily quests: discover activities that encourage you to get outside and explore.
🤖 ai-powered suggestions: generate personalized activity ideas using open-source ai.
⭐ xp and levels: earn experience points as you complete quests.
🔥 streak tracking: build consistency through small daily actions.
📝 field notes: record thoughts and experiences from your offline adventures.
🎯 custom quests: create your own challenges.
📊 progress tracking: see your journey toward healthier digital habits.
📴 offline-friendly fallback: keep using built-in quests when ai is unavailable.

🛠️ how i built it

i used the following technologies:

frontend: react, vite, and css
backend: python and fastapi
open-source ai: qwen 2.5 3b through ollama
storage: browser local storage
deployment: vercel for the frontend and render for the backend

🧠 why open-source ai matters here

for a project focused on digital well-being, i didn't want the solution to depend entirely on a closed-source ai service.

using an open-weight model such as qwen 2.5 3b through ollama gives developers the freedom to experiment with local inference, customize model behavior, and explore different models without depending on a paid proprietary ai api.

local inference can also help keep prompts on a user's own machine when configured that way. the model is replaceable, which makes the project easier to experiment with and extend.

i also wanted the basic experience to remain useful without ai. the built-in quests provide a fallback, so the app's core idea doesn't disappear when a model is unavailable.

🚀 try it yourself

🌐 live demo: https://touchgrass-ai.vercel.app/

💻 open-source code: https://github.com/arkendukundu-dev/touchgrass-ai

the project is built with an extensible architecture, and there's plenty of room to improve quest personalization, add achievements, and introduce more ways to encourage offline exploration.

🔮 what's next?

some ideas i'd love to explore:

more personalized quests based on interests and available time
achievements and community challenges
more outdoor activity categories
improved accessibility and mobile experiences

🌱 final thoughts

ai doesn't always need to keep us glued to a screen. sometimes, it can help us find a reason to put the screen down.

that's the idea behind touchgrass ai: use technology to make more room for real life.

i'd love to hear your feedback and ideas. what feature would make you more likely to step away from your screen and explore the world?

hf26challenge #hacktoberfest #opensource #ai

Hi

Arkendu Kundu — Sun, 11 Oct 2026 04:13:01 +0000