Talking it out is underrated. Rubber duck debugging and peer programming are time-tested techniques for thinking clearly, catching bugs, and sparking new ideas. But when you’re coding alone, it’s easy to lose that habit — and with it, a lot of momentum. That’s where Cheerleader comes in: a free, open-source VSCode extension that brings an interactive AI coding companion right into your workspace.

As the final design project of my Praxis II course, I worked with the Toronto Bonsai Society to develop Bonsense, an iOS application that helps bonsai beginners monitor the moisture levels of their plants using computer vision and IoT sensor. We hope that this can make the art of bonsai more accessible to everyone.

Generate 3D environments from real world images and train reinforcement learning agents in the cloud with Trainify. Our platform, built on GCP, powered by agentic LLM, and natively integrated with core RL toolkits, simplifies the process of creating and training AI agents in 3D environments.

In the 24-hour BMEC hackathon, we used few-shot transfer learning with CNN-LSTM to detect slight hand tremors of neurosurgeons during surgery, ensembled with a simple majority voting system with a sliding window time-frequency analysis. This triggers an intervention using a wearable device consistent of servo actuators to stabalize the hand of the surgeon during operation.

Ever opened Instagram just to send a quick message, only to find yourself doomscrolling for hours? Introducing the world’s first TUI + CLI client for Instagram, putting an end to the brainrot hell and turning it back into a productive social networking tool. Download from PyPI and star our GitHub repo (we’re got 5k downloads already)!

pip install instagram-cli

Have you ever felt frustrated by constantly switching your gaze between the lecture slides and your notebook and subsequently missing your professor’s fast paced content? We set out to solve this common classroom challenge by creating a wearable smartglasses that merges both visual fields into one.

As memories pile up in our camera rolls or remain abstract ideas, we wanted to create a way to truly experience them. MemoryMake was born from the idea of transforming ordinary photos and text prompts into dynamic, navigable, and visually engaging 3D environments—so users can explore their cherished moments instead of merely scrolling past them.

Paul, Nelson, and I built Memory Make by taking the unconventional route, stepping away from common hackathon LLM apps and focusing on cutting edge computer vision research. We won the best social hacks at Queen’s University’s QHacks 2025.

Ever gone on LinkedIn and all you saw was “I’m happy to share that I will be working at {Google, Microsoft, Meta, Tesla, etc} this summer”. You probably thought to yourself, “Wow, I really have to start working harder.” That feeling – the urge to level up your own productivity – is a powerful motivator. We recognized this common experience and decided to harness it.

Chi, Nicholas, Dylan, and I built TaskForce, a desktop productivity app where you can create and join study sessions with your friends to roast each other and brag about locking in with GenAI and system-tracking informed analytics in real time!!

Eidos is a project for educational purpose to build a simple deep learning library from scratch in C++. Inspired by libtorch, PyTorch’s C++ frontend, we implemented MLP, CNN, RNN using only Eigen for parallelized linear algebra. James Zheng and I started this project during my final exam month in 2024 and got me grinding it for a month alongside 6 major course finals. Install and try Eidos:

git clone https://github.com/supreme-gg-gg/Eidos
mkdir build && cd build
cmake .. && make
sudo make install

What if looking for a roommate was as easy as a google search – only but more accurate? Our answer is MapMatch. Inspired by retrieval augmented generation (RAG), we integrated semantic search, mind-map navigation, with AWS cloud technologies to match roommates based on their preferences and personalities.