Mlx

AI edge infrastructure for macOS. Run local or cloud models, share tools across apps via MCP, and power AI workflows with a native, always-on runtime.

Spark-x2.6 open model series. Pushing the Limits of Agentic Capabilities in On-Device Models

Up to 4× faster LLM decoding on Apple Silicon, lossless. Native MLX port of DeepSeek's DSpark & z-lab's DFlash speculative decoding — Gemma-4, Qwen3.8, Muse-Glimmer, Nemotron, LFM2.5, Ornith-1.0, ternary Bonsai-27B.

The fastest way to run Qwen 3.8 Flash Next, Qwen 3.8 27B and Ternary Bonsai 2 27B on a Mac: 125 tok/s in OpenCode on an M5 Max, and a 27B model on 16 GB Macs. Native MTP speculative decoding on Apple Silicon, exact at any temperature. OpenAI and Anthropic compatible local server.

Agent-ready video dubbing toolkit for Apple Silicon: local Chinese speech and bilingual subtitles. Single-speaker preview; human review required.

Own your AI. The native macOS harness for AI agents -- any model, persistent memory, autonomous execution, cryptographic identity. Built in Swift. Fully offline. Open source.

First LLM Studio: local-first LLM studio for Apple Silicon with MLX runtimes, Compare Lab, benchmark ops, replay, and runtime telemetry.

Rapid-MLX is an open-source (Apache 2.0) OpenAI- and Anthropic-compatible LLM inference server for Apple Silicon, built on MLX, focused on reliable tool calling for coding agents. Up to 4× faster than Apple's MLX (mlx-lm) on the same weights.

Self-hosted LLM gateway. One Go binary turns your Macs and Linux boxes into a private inference cluster — multi-machine routing, sharding via llama.cpp-RPC, per-user keys + quotas + audit, OpenAI- and Anthropic-compatible APIs behind one endpoint. Point Cursor / Claude Code / Aider / SDKs at it.

Run a 105 GB AI model on a Mac that can't hold it. Qwen3.8-Flash-Next 4-bit, streamed from SSD on 16–64 GB Apple Silicon Macs. Fully native Swift, MLX and Metal. Offline, no Python. CLI, Swift library, and Ollama/OpenAI/Anthropic APIs. Works with Claude Code and Codex.

Native LLM inference server for Apple Silicon. OpenAI + Anthropic API compatible. No Python. Zig backend, Swift frontend macOS app with chat, music, voice, video generation.

vMLX - Use MLX models easily - JANGQ (GGUF for MLX) - Not dependant on mlx_vlm

Local AI BGM and sound effects for Claude Code and any MCP client. Stable Audio 3 on Apple Silicon (MLX) and Windows NVIDIA GPUs (PyTorch). No cloud, no API key.

Spark-x2.5 open model series. Pushing the Limits of Agentic Capabilities in On-Device Models

Hit your Claude Code usage limit? Keep going free and offline on a local model: Qwen 3.8, Gemma 4, and Qwen 4 the day it ships. Runs on Apple Silicon Macs (MLX), Linux and Windows (llama.cpp) with no API key. Your code stays home.

Translate entire books with AI you already have.

Synthetic Autonomic Mind - An AI assistant for everyone.

Small enough to run on your Mac. Smart enough to ask. An open-source computer use agent for macOS, with local models (MLX) that see, decide and act. 得心，应手。

Run any agent on any model, models stored as OCI images

M-Courtyard: Local AI Model Fine-tuning Assistant for Apple Silicon. Zero-code, zero-cloud, privacy-first desktop app powered by Tauri + React + mlx-lm.

Open-source iOS app connecting Meta Ray-Ban smart glasses to AI — 5 backends (on-device MLX models, Apple Intelligence, OpenAI, Gemini Live, OpenClaw), on-device neural voice, face recognition & live web search. Private and offline-capable.

A local-first workspace for documents, tasks and meetings on macOS — nested spaces, typed properties, relations and saved views, with transcription, Smart Minutes and an agent running entirely on-device via MLX on Apple Silicon

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.