The best way to run Hermes on your Mac!

A dynamic library providing Virtualization-based process isolation capabilities

Keep Codex running forever

A terminal emulator for the web

Learn LLM internals step by step - from tokenization to attention to inference optimization.

Tool to build & run portable, lightweight, self-contained virtual machines.

The cost efficiency of S3 with the speed of local RAM. A multi-tenant vector and full-text search engine featuring a tiered RAM → NVMe → S3 architecture for microsecond latency on top of object sto…

An efficient AI coding agent

The best-benchmarked open-source AI memory system. And it's free.

Collaborator is a place to create with agents.

Official skills for the GLM family of models.

CS6868: Concurrent Programming

Pure-Go implementation of JSONata 2.x for high-throughput streaming evaluation

Rust client for the Synology Drive sync protocol, reverse-engineered from the official macOS client.

rvLLM: High-performance LLM inference in Rust. Drop-in vLLM replacement.

Zig INferenCe Engine — Local LLM inference on AMD GPUs and Apple Silicon

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

Self-referential self-improving agents that can optimize for any computable task

A web, mobile and desktop client for pi

A Zig-native web framework. File-based routing, SSR, type-safe APIs, WASM client interactivity. No Node. No npm. Just zig build serve.

Local knowledge graph for Claude Code. Builds a persistent map of your codebase so Claude reads only what matters — 6.8× fewer tokens on reviews and up to 49× on daily coding tasks.

Privacy-first API platform built with Tauri v2. No login, no cloud, ~60 MB RAM. A lightweight Postman alternative.

⚒️ The open source dark software factory for expert engineers.

HF CLI extension to run local coding agent powered by llmfit and llama.cpp

Ghostty-based macOS terminal with vertical tabs and notifications for AI coding agents

Rust-native hybrid training & inference engine for Apple Neural Engine + Metal GPU

macOS utility to customize notification position and appearance

Programming language for safe AI agents

OpenTUI is a library for building terminal user interfaces (TUIs)