Stars
CLI for managing AI agent skills — install, create, and share reusable SKILL.md definitions with automatic script dependency resolution
High-throughput, sub-millisecond Reinforcement Learning engine. Built in Rust and CUDA with a Python/LangGraph orchestration layer. Implements Gumbel MuZero MCTS and lock-free concurrency, entirely…
Tools for concurrent programming in Rust
Ollero is a nvim plugin for integrating Ollama with neovim locally
Multi-agent development workflow plugin for Claude Code — PM, SE, QA, Tech Lead, UI/UX Specialist, Software Architect, DevOps
A high-performance 3D visualization engine for the Wolfram Physics Project. Features GPU-accelerated graph rewriting, interactive force-directed layouts, and a custom rule playground. Built with Re…
An AlphaZero-style AI agent for a custom triangle puzzle game. Features distributed self-play with Ray, a C++ MCTS core, and a PyTorch neural network. Includes async logging via MLflow & TensorBoard.
A CLI tool that streamlines Git workflows by analyzing diffs to craft semantic commit messages. Supports multiple AI providers, custom templates, and pre-commit hooks.
DocEnTr: An end-to-end document image enhancement transformer - ICPR 2022
Arena-Hard-Auto: An automatic LLM benchmark.
Build your own document scanner with OpenCV Python
A React-based pose estimation engine. Uses WebGL/WebGPU to calculate movement accuracy against video feeds entirely in the browser.
A portfolio built with systems thinking. Simulates an OS/IDE environment with a custom virtual file system, Monaco Editor integration, and stateful window layouts. Browsable, interactive, and built…
A bootstrap to API with automated provisioning of cloud resources in Google Cloud Platform using Terraform CDK in Typescript.
Prepare your code for AI. Concatenates your project into a clean, markdown-formatted file with file trees and granular filtering options.
A real-time, 4-player hybrid of Pong and Breakout. Built with Go and WebSockets, powered by a custom Actor Model architecture (Bollywood) for high concurrency and scalable game state management.
A full-featured, hackable Next.js AI chatbot built by Vercel
Promise-friendly Node.js wrapper around youtube-dl / yt-dlp for downloading media.
This repository hosts a full-stack application designed to convert numeric values into their corresponding English word representation. The back-end is built using Django, exposing two primary API …
High-performance In-browser LLM Inference Engine
Vector Storage is a vector database that enables semantic similarity searches on text documents in the browser's local storage. It uses OpenAI embeddings to convert documents into vectors and allow…