SlothMate AI: An Open-Source, Local-First AI Study Assistant for Smarter and Effortless Learning

This is my submission for the Hacktoberfest Open-Source AI Challenge Week 3: Slow and Steady.

I built SlothMate AI, a local-first AI study assistant designed to make studying easier by automating repetitive academic tasks.

Students often spend a lot of time organizing lecture notes, extracting important concepts, preparing revision questions, and planning what to study next. SlothMate AI helps reduce this effort by turning unorganized notes into useful study material.

The goal is simple: spend less time organizing and more time understanding.

This is the local demo address. It works when the application is running on your computer, but it is not a publicly accessible website yet.

Public demo link: To be added after deployment.

GitHub Repository: https://github.com/ayush6301633/slothmate-ai

Replace ayush6301633 with your actual GitHub username after creating and publishing the repository.

I built SlothMate AI using a lightweight web application architecture.

When a student enters their notes and selects a task, the Flask backend sends a prompt to the locally running Ollama model. The model generates the requested output, which is then displayed on the website.

The application is designed to work without a paid, hosted AI API. After downloading the model and installing the dependencies, users can run inference locally, even without an internet connection.

Open innovation is central to SlothMate AI because students should have more control over the AI tools they use.

With a conventional hosted AI API, users may depend on an external provider for inference, pricing, availability, and data handling. A local-first approach offers an alternative.

Open-source software and open-weight models also make it easier for beginners to learn how AI applications work beyond simply calling a commercial API. Model licences and capabilities vary, so users should check the terms of the model they choose.

SlothMate AI is designed to reduce the repetitive work involved in preparing study material.

Instead of manually rewriting notes, creating revision checklists, and drafting practice questions, students can ask their local AI assistant to generate a first draft in one place.

The project has four core study workflows: summarizing, planning, quiz generation, and concept explanation.

I have not yet measured the actual time saved with users, so I won't claim a specific percentage or number of hours. My next step is to test the application with real student notes and compare the time taken to prepare revision material manually versus using SlothMate AI.

Focus: Open-Source AI and Local Inference.

I am highlighting the use of an open-weight model, local processing, and a flexible open-source application architecture. I will select any applicable official partner prize categories after checking the challenge's eligibility requirements.

SlothMate AI is built around a simple idea: not every task needs to consume our time and energy.

By combining open-weight AI with a lightweight web application, I wanted to create a practical study assistant that students can run, customize, and learn from.

* Slow down. Automate the repetitive work. Learn at your own pace. *