Local LLM Platform - Hardware/Software

Project Goal Build a working prototype of our local, privacy-first AI system that includes both software and hardware components — enabling document processing (e.g., summarization or classification) using AI models running entirely offline on edge devices like a NUC, Raspberry Pi, or Jetson. Main Objective / Tasks & Activities Learners will collaborate to integrate AI software with real hardware environments to demonstrate a complete, working edge-AI system. Software Tasks: Set up a lightweight local backend (e.g., FastAPI) to run AI workflows Integrate with quantized open-source language models (e.g., via llama.cpp) Develop a simple UI or CLI to upload documents and display AI outputs Ensure compatibility with low-power, local hardware environments Hardware Tasks: Set up and configure edge devices (e.g., Jetson Nano, Raspberry Pi, NUC) Test local model performance on different hardware setups Optimize system resource usage (RAM, CPU/GPU) Assist with packaging the software for reliable offline use Deliverables: A working MVP that runs a full AI document processing workflow offline on local hardware Source code and system setup documentation Performance benchmarks (inference speed, memory usage) for each hardware type A short demo video of the full system in action

Pebbles AI User Experience Enhancement

Pebbles AI is seeking to enhance the user experience (UX) and user interface (UI) of its flagship application to improve user satisfaction and engagement. The current interface, while functional, lacks intuitive navigation and modern design aesthetics. The goal of this project is to redesign the UI to be more user-friendly and visually appealing, ensuring that it aligns with contemporary design standards. This will involve analyzing the existing interface, gathering user feedback, and applying UX/UI principles learned in the classroom. The project will focus on creating wireframes and prototypes that address identified pain points and enhance overall usability. By the end of the project, Pebbles AI aims to have a clear, actionable design plan that can be implemented by their development team.

Local LLM MVP

Project Goal Build a simple MVP of our offline, privacy-first AI platform that allows users to upload documents and receive AI-generated summaries or classifications locally. This prototype will serve as the foundation for our future edge-AI product. Main Objective / Tasks & Deliverables Learners will: Set up a lightweight local backend using Python (e.g., FastAPI or Flask) Connect the backend to a quantized open-source language model (e.g., via llama.cpp or GGUF format) Develop a simple front-end interface or CLI for uploading documents and displaying AI outputs Implement basic support for common file types (PDF, .txt, .docx) Package the MVP for local testing/use on a laptop or NUC Document their work and provide setup instructions for reproducibility Deliverables: A working MVP that runs entirely offline on local hardware Source code and setup documentation Basic UI or command-line interface for demo purposes