#apple-silicon

Kubernetes operator for self-hosted LLM inference across a heterogeneous GPU fleet: NVIDIA CUDA, AMD Vulkan, and Apple Silicon Metal. Runtimes: llama.cpp, vLLM, TGI, mlx-server. Multi-GPU sharding, model caching, OpenAI-compatible endpoints. Apache-2.0, run across homelab and on-prem fleets, actively developed.

High-performance OpenAI and Anthropic compatible LLM inference server for Apple Silicon. Native MLX, continuous batching, multimodal models, MCP tool calling, and Claude Code support.

Your coding agent starts every session with amnesia — memo fixes that, 100% on your machine. Persistent memory for Claude Code, Codex, Cursor & any MCP client: Markdown source of truth, hybrid search (MLX/CPU + sqlite-vec), time-machine, contradiction radar, nightly self-optimization. No cloud, no keys.

Generative image and video runtimes for Apple Silicon (MLX): text/image-to-image, instruction editing, masked edit, text/image/reference-to-video, video editing, and restoration.

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

Native Safari browser automation for AI agents. 97 tools via AppleScript — zero overhead, keeps logins, runs silently in background. Drop-in alternative to Chrome DevTools MCP with 40-60% less CPU/heat on Apple Silicon.

Give your tools a voice — speech to text and back, 25 languages, up to ~19× faster than Whisper. On your machine.

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

Run AI models on Apple Silicon and Raspberry Pi

Lumerico's Comprehensive Interface for Deep Learning

Apple Silicon (M1–M4) power, GPU, ANE & memory-bandwidth monitor — sudoless TUI + Python API for profiling local LLM / MLX / CoreML inference

Extreme weight + KV cache compression for LLMs on Apple Silicon (MLX implementation of Google's TurboQuant)

3x faster speeds on MLX | Qwen 3.8 27B | Native MTP Speculative Decoding On Apple Silicon With No External Drafter.