Students spend a lot of time preparing summaries, revision questions, and study notes. I wanted to build a simple tool that could help students do these tasks more easily.
That is how I built LazyMate AI, a lightweight AI study assistant powered by the Gemma 3 1B model through Ollama.
LazyMate AI turns ordinary study notes into useful learning materials through a simple web interface.
Instead of manually organizing every note, students can paste their content or upload a text or Markdown file and ask the AI to prepare a study pack.
.txt or .md file.
Open-weight AI models make it possible for students and independent developers to experiment with AI without depending entirely on paid, hosted AI services.
Because LazyMate AI uses local inference, study notes can remain on the user's computer instead of being sent to a hosted AI API. After the model and dependencies are installed, local generation can work without an internet connection.
This approach is especially useful for students who want to learn and experiment with AI while keeping their costs low.
Building LazyMate AI helped me practise Python, Streamlit, Git, GitHub, and integrating a locally running AI model into an application.
I also learned how to troubleshoot package installation, configure a local model, and test an AI-powered interface.
Demo: I tested the application locally and captured a screenshot of the generated study pack. I will include the screenshot with this post.
I plan to improve the interface, test the different output modes, improve Tamil-language responses, and make the application easier for students to install and use.
LazyMate AI is my small step toward making AI-assisted learning more accessible through open technology.
Built with Python, Streamlit, and Gemma 3 1B. 🦥