Havuz

GlowEffectKit is a SwiftUI SDK for adding animated glow effect to iOS and macOS components, powered by a bundled Metal shader. More compact

🧠 One LLM, split across a Mac (Apple MPS) + a Windows PC (NVIDIA CUDA) — heterogeneous pipeline inference over a framework-neutral wire, bit

Real-time multimodal AI pipelines on Apple Silicon

Run large language models locally on Intel Macs with AMD GPUs - native macOS app with Metal acceleration

The open-source alternative to Minecraft: Java Edition, a complete block-survival game in about 45,000 lines of Swift + Metal. Zero dependen

A practical lab for exploring Apple's Core AI framework, model assets, specialization, and on-device inference.

Native Rust, single-binary MLX inference server for Apple Silicon. OpenAI/Anthropic-compatible LLM serving — text, vision, audio, embeddings

Native macOS terminal with GPU rendering, durable sessions, coding-agent workflows, and SSH connectivity. Session host, daemon, and CLI supp

ML model ports (ASR · TTS · LLM · VLM · vision · audio codecs) on the rlx multi-backend compiler + runtime — CPU/Metal/MLX/CUDA/wgpu

A Metal-rendered creative-coding framework for Swift on Apple platforms: live reload and live coding, generative techniques, GPU shaders and

Object-storage-native KV cache for LLM inference & RL. Cross-restart, cross-conversation, cross-engine via shared S3 bucket.

Apple Silicon mlx with Zero Dependency Java

A macOS island strategy game built with SwiftUI, RealityKit, and Metal. Build towns, trade, raise armies, and conquer a 15-city archipelago.

Most accurate, simple and customisable Apple Intelligence–style glow for SwiftUI, backed by Metal shaders.

Production-grade React Native ink engine with native Skia/Metal drawing and continuous canvas primitives.

Camelid: a Rust-native local inference backend with evidence-gated model compatibility.

Local AI engine in Rust: run GGUF and ONNX models for chat, vision, speech and embeddings on your own GPU, RAM and CPU, with automatic place

Fast KV-cache quantization for Apple Silicon (MLX) — 43 research-adapted compression methods with Metal kernels

Transformer inference via unconventional compute: a single algebraic primitive, a tag-system scheduler, and Apple's Neural Engine through co

neural networks in pure C

A native .NET LLM inference engine and agent runtime for GGUF models. TensorSharp provides a console application, a web-based chatbot interf

TurboQuant KV cache compression for MLX with fused Metal kernels. 4.6x compression at 98% FP16 speed.

TurboQuant MLX: Flagship high-performance model quantization for Apple Silicon. Squeeze maximum inference speed and memory efficiency out of

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

Flash weight streaming for MLX: run massive models larger than your RAM on Apple Silicon.

Native TypeScript game engine — compiles to Metal, DirectX 12, Vulkan, and OpenGL

CLI-native local AI image and video generation for people, scripts, and agents — CUDA on Linux, Metal on macOS, plus desktop, web, iPhone, R

llama.cpp/ik_llama.cpp launcher: loads big MoE models across mismatched multi-GPU rigs by exact VRAM math.