Siri Shortcuts Programming Language 🍒

A python CAD programming library

RetDec is a retargetable machine-code decompiler based on LLVM.

A machine learning primer built from first principles. For engineers who want to reason about ML systems the way they reason about software systems.

Production-grade Ghidra MCP Server — 179 MCP tools, 147 GUI + 172 headless endpoints, Ghidra Server integration, cross-binary documentation transfer, batch operations, AI documentation workflows, a…

Jail your AI agent

Native macOS Wayland Compositor written in Rust using Smithay. Experience seamless Linux app streaming on macOS without XQuartz.

An updated and improved Chrome and Firefox extension of the old google chrome extension "Tab Manager".

A lisp that compiles to eBPF

C# bindings generator for uniffi-rs

Windows overlay FS explorations

Turn any website into a typed JSON API using self improving agents

Library and binaries for the reading, creating, and modification of SquashFS file systems

A Swift reimplementation of a Claude Code-style coding agent, built stage by stage to explore what makes coding agents work

Integrate cargo build with flutter plugins and applications.

Lean Standard Library

Semantic search over videos using Gemini Embedding 2 or Qwen3-VL.

Run models too big for your Mac's memory

Open-source Agent Operating System

Python for .NET is a package that gives Python programmers nearly seamless integration with the .NET Common Language Runtime (CLR) and provides a powerful application scripting tool for .NET develo…

Official Swift implementation of Apache Arrow

GPU-accelerated terminal board that puts all your sessions on an infinite canvas

Self-hosted, semantically-connected personal knowledge base

Python DSL that compiles element-wise expressions to parallel Rust. All CPU cores, zero serialization.

Context Gateway is an agentic proxy that enhances any AI agent workflow with instant history compaction and context optimization tools

Production-Grade Autoresearch. Ideal for GPU kernels, ML model development, feature engineering, prompt engineering, and other optimizable code.

Self-hosted GitHub-native micro-PaaS for deploying small web applications.

I replicated Ng's RYS method and found that duplicating 3 specific layers in Qwen2.5-32B boosts reasoning by 17% and duplicating layers 12-14 in Devstral-24B improves logical deduction from 0.22→0.…

Staging repo for development of native port of TypeScript