Starred repositories
Awesome RSS feeds - A curated list of RSS feeds (and OPML files) used in Recommended Feeds and local news sections of Plenary - an RSS reader, article downloader and a podcast player app for android
FeedFlow is a minimalistic RSS Reader available on Android, iOS, macOS, Windows and Linux. Built with Kotlin Multiplatform, Jetpack Compose and SwiftUI.
A retargetable MLIR-based machine learning compiler and runtime toolkit.
Read chapters directly from this repo - do not use GitHub Pages link.
Remove Google Gemini 3.5 / Veo video watermarks with mathematically precise reverse alpha blending. Standalone Windows CLI — demo/preview build.
SGLang is a high-performance serving framework for large language models and multimodal models.
Cross-platform C++ function hooking library — type-safe, fluent, and honest about its limits.
A simple and easy-to-use library to enjoy videogames programming
This course is designed to guide beginners through the exciting world of Edge AI, covering fundamental concepts, popular models, inference techniques, device-specific applications, model optimizati…
Sample benchmark demonstrating the VK_KHR_cooperative_matrix extension
NVIDIA® TensorRT™ is an SDK for high-performance deep learning inference on NVIDIA GPUs. This repository contains the open source components of TensorRT.
ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator
18 Lessons to Get Started Building AI Agents
Skills for Real Engineers. Straight from my .agents directory.
Vulkan-based implementation of D3D8, 9, 10 and 11 for Linux / Wine
A fast usermode x86 and x86-64 emulator for Arm64 Linux
Run Arm64/x86-64 Linux ELF binaries on macOS Apple Silicon
LLM speculative inference server for consumer hardware & heterogeneous computing
VEO / Gemini 3.5 Nano Banana Pro watermark maintenance tool
Spec-driven development (SDD) for AI coding assistants.
A Visual Studio Extension containing miscellaneous improvements to the editor.
Unsloth is a local UI for training and running Kimi K3, Gemma 4, Qwen3.6, DeepSeek-V4, GLM and other models.
Production-grade engineering skills for AI coding agents.
CLI proxy that reduces LLM token consumption by 60-90% on common dev commands. Single Rust binary, zero dependencies
A powerful, all-in-one Windows maintenance toolkit built entirely in Batch & PowerShell. Designed for power users, sysadmins, and curious tinkerers – now smarter, safer, and fully offline-compatible.