AI coding agent optimized for small LLMs. 87% benchmark with 4B-active model.

Private, fast, and honest web browser

MLX-VLM is a package for inference and fine-tuning of Vision Language Models (VLMs) on your Mac using MLX.

OpenAI and Anthropic compatible server for Apple Silicon. Run LLMs and vision-language models (Llama, Qwen-VL, LLaVA) with continuous batching, MCP tool calling, and multimodal support. Native MLX …

Web search and content extraction extension for Pi coding agent

iperf3: A TCP, UDP, and SCTP network bandwidth measurement tool

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

The Ethereum extension for Postgres.

LLM inference server with continuous batching & SSD caching for Apple Silicon — managed from the macOS menu bar

ACP adapter for pi coding agent

LLM inference in C/C++

The open-source ElevenLabs alternative for local voice cloning, design, create, dubbing and dictation Desktop App

An open, sub-millisecond, single-executable Firebase alternative with type-safe APIs, built-in WebAssembly runtime, realtime subscriptions, auth, and admin UI built on Rust, SQLite & Wasmtime.

PocketBase JavaScript SDK

Haskell project template using Nix + Flakes + VSCode (HLS)

Nix flake for a fully declarative NixOS on Raspberry Pi

Hub for information regarding the "de-link" development kit, based on the ESP32-S3. Offers hardware access to 24-pin e-paper communication over SPI, 4-bit SDMMC, USB-C, button array, and optional m…

Http syntax for the zed editor

Koka language compiler and interpreter

The open-source app everyone uses to manage agents at work

Symphony turns project work into isolated, autonomous implementation runs, allowing teams to manage work instead of supervising coding agents.

High-performance browser automation bridge and multi-instance orchestrator with advanced stealth injection and real-time dashboard.

A tiling window manager for macOS 🍉

a tiling window manager for macos

A light theme for Visual Studio Code

Training neural networks on Apple Neural Engine via reverse-engineered private APIs

A secure persistent personal agent server in Rust. One binary, sandboxed execution, multi-provider LLMs, voice, memory, Telegram, WhatsApp, Discord, Teams, and MCP tools. Secure by design, runs on …

Fastest, smallest, and fully autonomous AI assistant infrastructure written in Zig