VSCode Cheerleader

Supercharge your dev experience with an anime coding companion

Electron TypeScript VS Code

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.

[Read More]

Instagram CLI

THe ultimate weapon against brainrot

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

[Read More]

Eidos

Building a C++ Deep Learning Library from Scratch

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
[Read More]

Introductory RL

Assorted Collection on Deep Reinforcement Learning

Python PyTorch TensorFlow

Reinforcement learning (RL) is a way of training an agent to make sequences of decisions by finding the optimal action-taking policy through trial and error interactions with the environment. It is a powerful tool for solving complex problems in robotics, finance, and gaming. To broaden my knowledge in ML, I worked on a few small projects to learn fundamental deep RL algorithms such as (Double) DQN, REINFORCE, DDPG, and PPO. Please see this project if you are interested in NEAT and Pong instead.

[Read More]

Pong and NEAT

Neuroevolution beats human players

Python PyTorch

NEAT, or NeuroEvolution of Augmenting Topologies, is a genetic algorithm for evolving neural networks. Hayson and I used the neat-python library to train a neural network to play Pong as an optional course project to develop an AI that compete in Pong tournament. The agent maximizes the reward by learning to hit the ball back to the opponent.

NEAT
Pong game

Checkout Hayson’s amazing blog post where he explained the theory of how NEAT works!

[Read More]

WeDream

Duolingo for Sleep

Swift Xcode Firebase Express

Sleep deprivation is a widespread issue, expected to worsen as distractions increase. Despite understanding sleep’s benefits, many find it challenging to maintain a healthy night routine. This is especially prominant for students who later face difficulties in focusing and retaining information.

Inspired by the engaging features of Duolingo, WeDream motivates users to stay committed to improving their sleep habits. We are dedicated to empowering individuals who actively seek to improve their daily lives and become the best versions of themselves.

[Read More]