Megakernel to match Apple Silicon Efficiency at 2x the Throughput on a RTX 3090

A subset of Go that translates to C

Grapevine is a self-hostable realtime unified context system

⚡ Native MLX Swift LLM inference server for Apple Silicon. OpenAI-compatible API, SSD streaming for 100B+ MoE models, TurboQuant KV cache compression, + iOS iPhone app.

A free and open immersive video player for the Apple Vision Pro.

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

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

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

The agent that grows with you

Use your cursor subscription in opencode

Sub-millisecond VM sandboxes for AI agents via copy-on-write forking

Official Codebase for "Neural Thickets: Diverse Task Experts Are Dense Around Pretrained Weights"

A lightweight cli for running single-purpose AI agents. Define focused agents in TOML, trigger them from anywhere; pipes, git hooks, cron, or the terminal.

Metal Flash Attention for MLX

Native Mac OS GUI for Using mlx-lm-lora.

Run AI agents isolated in a macOS user account and sandbox-exec. Configured to run Claude Code, OpenAI Codex, Cursor Agent, Google Gemini.

Go bindings to QuickJS

Go bindings to QuickJS

Nightshift uses your leftover Claude / Codex budget to surprise you with useful PRs. Love them or leave them.

Hypernetworks that update LLMs to remember factual information

The production engine for directional ablation. Unalign / remove models censorship efficiently on any hardware.

Flux 2 image generation model pure C inference

PDF Parser for AI-ready data. Automate PDF accessibility. Open-source.

The inference engine the open-source world built for itself.

Apple HomeKit for ESPHome - Alpha WIP