Native macOS GUI for Apple's container CLI — Docker Desktop-style, SwiftUI, free & open source

macOS menu-bar app that surfaces and kills orphan listening ports.

The end of web parsing. The beginning of scalable pixel-native search. link: https://pixelrag.ai/

A real-time method that estimates the 3D human pose directly in the popular Bio Vision Hierarchy (BVH) format, given estimations of the 2D body joints originating from monocular color images. Our c…

817 structured cybersecurity skills for AI agents · Mapped to 6 frameworks: MITRE ATT&CK, NIST CSF 2.0, MITRE ATLAS, D3FEND, NIST AI RMF & MITRE F3 (Fight Fraud) · agentskills.io standard · Works w…

国行 Mac 一键开启完整 Apple 智能(端侧 + Private Cloud Compute 云端)· macOS 27 / Apple Silicon

Yet another coding agent harness, lightweight and written in go.

Climb coach, a gift for my son -- Lele

A human-in-the-loop, simple enough, well-behaviored workflow for small-and-medium projects.

a learning-first RAG engine for classic RAG scenario.

GPT built from scratch — assembled from my NeetCode ML course submissions

A tiny inference engine implementation for learning purpose. Supports duo backends: Apple Silicon and Nvidia GPU backend.

A local workbench for agents doing continuous work across sessions, commands, human input, and external events.

Agent Workbench is a local-first web workspace for managing coding-agent work across multiple projects and multiple sessions.

Zero-config entity resolution & record linkage. The zero-tuning Fellegi-Sunter path beats hand-tuned Splink head-to-head and scales from a CSV to a verified 100M-row dedupe in 9.2 min. Fuzzy/exact/…

Menu bar manager for macOS 26

agent multiplexer that lives in your terminal.

DeepSeek 4 Flash and PRO local inference engine for Metal, CUDA and ROCm

Run LLMs with MLX

Examples in the MLX framework

Nano vLLM

Based on Nano-vLLM, a simple replication of vLLM with self-contained paged attention and flash attention implementation

A course of learning LLM inference serving on Apple Silicon for systems engineers: build a tiny vLLM + Qwen.

Transformer Explained Visually: Learn How LLM Transformer Models Work with Interactive Visualization

The best ChatGPT that $100 can buy.

The simplest, fastest repository for training/finetuning medium-sized GPTs.

The load-test tool and 24/7 high, chaos traffic simulator.

✨ The best JVM observability, troubleshoot, and optimize. 🚀 Unlock deep insights instantly via our dashboard, CLI and Harness. 📊

Use a reMarkable tablet as a mouse.

A curated list of projects related to the reMarkable tablet