StudySync AI

A multi-agent study ecosystem that converts YouTube videos and notes into autonomous learning paths. Powered by Gemini 2.5 Flash, it plans, summarizes, and masters topics alongside you.

Comment

🌟 Inspiration

I’ve been there. 2 AM, 47 browser tabs open, three YouTube tutorials half-watched, and a PDF textbook that felt more like a brick than a resource. I was drowning in information but starving for knowledge. I realized that the problem wasn't a lack of resources—it was the cognitive load of managing them. I needed a partner, not just a tool. That’s how StudySync AI was born.

🚀 What it does

StudySync is a multi-agent ecosystem that acts as your browser's "frontal lobe." It takes your YouTube videos and PDFs and transforms them into an autonomous, structured study plan. It doesn't just summarize; it understands. It tracks your "Topic Pulse" to find your weak spots and builds a multi-day schedule that adapts to your specific goals.

🛠️ How we built it

We built the core using Gemini 2.5 Flash for its massive context window and lightning-fast reasoning. The frontend is a sleek, glassmorphic React dashboard designed for deep focus. The backend is a Flask-powered multi-agent system that coordinates between data retrieval, planning, and memory modules. We used MongoDB Atlas for persistent long-term memory and Google Cloud for high-performance hosting.

🚧 Challenges we ran into

The biggest hurdle was case-sensitivity! Moving from Windows development to Linux production on Vercel caused several "Ghost File" errors that nearly derailed our deployment. We also faced challenges in grounding the AI to ensure it stayed 100% faithful to the source material without hallucinating.

🏆 Accomplishments that we're proud of

We are incredibly proud of the "Mission Control" UI. It's not just a dashboard; it's an experience that makes study sessions feel like a high-stakes mission. Achieving sub-second response times for complex multi-agent planning was another huge win.

📚 What we learned

We learned that "Agentic" is the future. Moving away from simple prompt-response cycles to a multi-agent system where different modules handle specific parts of the learning process (Planner, Summarizer, Monitor) changed everything.

🛰️ What's next for StudySync AI

We’re looking to add real-time voice-sync for lecture recording and a "Peer Network" where students can share AI-generated knowledge clusters across different disciplines.

Built With

Share this project:

Updates