标签：#ha

This is a submission for the GitHub Finish-Up-A-Thon Challenge What I Built I built Academia, a modern, delivery-only Learning Management System (LMS) designed for creators who want a premium, distraction-free environment for their students. With Academia, educators can spin up their own custom academy, build out rich curriculums with video and text lessons, and securely invite students via email magic-links. Once a student accepts an invite, they are dropped into an isolated, hyper-clean student portal that tracks their course progress in real-time. This project started two years ago during a hackathon. I had this really great idea, but I was still very much a beginner. Between the tight timeframe, lack of sleep, and my slow coding speed, I just couldn't pull through to finish the project in time to submit. It sat abandoned in my repositories, gathering dust. Finishing it means finally delivering on the exact vision I had in my head two years ago, but with the skills and architecture of today. Demo Live Site Repository The Comeback Story I always told myself I’d finish this project "after the dust settles," but I never got around to it. When I saw this challenge, I knew it was time. Just looking at the 2-year-old repository gave me an instant headache. The packages were entirely outdated, Vercel was throwing massive build errors, and running npm run dev was painfully slow. Basically, everything was lagging. I seriously considered just starting a fresh repo from scratch. I figured I would just look at the shabby design I created two years ago and try to manually copy-paste the "important" code over, because I knew updating the existing mess would be an absolute nightmare. But instead, I decided to lean heavily on GitHub Copilot Auto (so I could automatically get the best models for the job) to see if we could salvage and modernize the original codebase. Here is the story of my before-and-after journey, and how Copilot helped me finally finish what I started. My Expe

This is a submission for the June Solstice Game Jam What I Built SOLSTICE — The Longest...

This is a submission for the GitHub Finish-Up-A-Thon Challenge What I Built The average student opens their notes 3 days before the exam. The above average student opens them the night before. Either way, they both end up on YouTube at 3am watching a guy explain thermodynamics with a whiteboard and too much energy. I built something better. I built Forge AI — a collaborative AI study platform that turns your lecture notes, PDFs, and YouTube links into a full study session with an AI tutor that actually talks back. Here is what it does: 📄 Upload your notes or paste a YouTube link — Forge AI reads everything and builds you a prioritised study plan in seconds. 🧠 Deep Dive into any topic — get full AI generated study notes, a mnemonic memory trick, and a built-in quiz. 🎙️ Talk to your AI tutor live — it listens, speaks back, and you can see the transcript building in real time as it talks. 👥 Create a Forge Room — invite your study group, ask the AI questions together, battle each other in a live quiz, and everyone sees everything at the same time. It started as CrammAI . A solo study tool I built under exam pressure. Well, it could generate a study plan from your uploaded files and quiz you on topics. That was it. No voice. No collaboration. No rooms. No Finesse. Just you, alone, cramming at 2am. Five months later I came back to finish it. The result is Forge AI. Demo Live app GitHub Here is what Forge AI can do: 1. Upload your materials and pick your mode Three modes based on how much time you have: 🧘 Cruise Control — 1+ week until exam 🚀 Turbo Mode — 2 days left ⚡ Zoom Mode — due tonight 2. Paste a YouTube link — it transcribes automatically ts export const apiFetchYoutubeTranscript = async ( url : string ): Promise < string > => { const videoId = extractYoutubeId ( url ); const response = await fetch ( `/api/transcript?videoId= ${ videoId } ` ); const data = await response . json (); return data . transcript ; }; No manual transcription. Paste the link, Forge AI pull