FriendCare AI 💗 — Your Personal Study and Daily-Life Companion
This is a submission for the Hacktoberfest Weekend Challenge: Build for a Friend.
💖 What I Built
I built FriendCare AI, a friendly web application designed to help students manage their studies and daily routines while taking care of their emotional well-being.
College life can sometimes feel overwhelming. Students have to manage assignments, exams, deadlines, and personal stress at the same time. I wanted to build something simple that could make their day a little easier.
FriendCare AI includes:
- 💬 AI Friend: Chat with a friendly assistant for support, motivation, and everyday guidance.
- 📚 Study Planner: Organize study tasks and keep track of progress.
- 😊 Mood Check-In: Check in with your feelings and receive encouraging messages.
- 💗 Daily Motivation: Get gentle reminders to take small steps toward your goals.
I wanted this project to feel less like another productivity tool and more like a supportive companion for students.
🎬 Demo
GitHub Repository: FriendCare AI
Live demo: Add your deployed website link here when available.
💻 Code
Explore the complete project on GitHub:
🔗 https://github.com/anshikajais890-wq/FriendCare-AI
The project uses HTML, CSS, and JavaScript for the frontend. The AI chat can be connected to a locally running open-weight model through a backend, allowing users to interact with an AI assistant without relying entirely on a paid, closed AI API.
🛠️ How I Built It
I built FriendCare AI using web technologies:
- HTML to structure the application.
- CSS to create a clean, friendly, pastel-themed interface.
- JavaScript to handle chat interactions, mood check-ins, and study tasks.
- Node.js and Express for the backend AI connection, when using the backend-enabled version.
- Ollama with an open-weight model such as Qwen2.5 to run the AI locally.
My goal was to explore how open-source AI could be used to create a useful, approachable application for everyday student life.
🌍 Why Does Open Innovation Matter?
Open innovation matters because AI should be accessible to more people, not only those who can afford expensive APIs.
Using open-weight models and tools such as Ollama gives developers more control over how their applications work. Local inference can also reduce dependence on external AI services and help keep conversations on the user's own machine, depending on how the application is configured.
As a student exploring AI and machine learning, this project helped me understand how frontend development, backend integration, and AI models can work together in a real application.
I hope FriendCare AI inspires other students to build technology that is not only useful but also thoughtful and human-centered.
🤖 My Agent Session
Optional: Add your DevRelay agent session link here if you have one.
🏆 Prize Categories
Add the applicable partner prize categories from the official challenge page. Remove this section if you are not entering a specific partner category.
Built with 💗 to make studying and everyday life feel a little easier.
Top comments (0)