Team real submission for DEVSOC 2025
A privacy-first, self-hostable application for organizing notes and sourcing references efficiently. It leverages Llama.cpp with Llama 3.2 (3B) for structuring notes and enhances responses using Retrieval-Augmented Generation (RAG) with SearXNG for improved search-informed insights and references, locally.
- AI-Powered Note Organization – Use Llama 3.2 to structure, summarize, categorize and query your notes.
- Smart Reference Sourcing – Fetch relevant sources with SearXNG’s privacy-friendly meta-search.
- Collaborative Workspaces – Create and join private rooms to organize notes, brainstorm ideas, and efficiently gather resources for academic projects.
- Self-Hostable & Secure – Full control over your data, no third-party dependencies.
- Customizable & Extendable – Open-source and easily integrated into your workflow.
Ensure you have the following installed:
- Docker & Docker Compose (To start SearXNG docker image)
- Python 3.10+
- Node.js
- No data leaves your server.
- SearXNG ensures anonymous web searches.
This project is licensed under the MIT License. See LICENSE for details.