#apple-silicon

Local AI model manager

A native macOS harness for coding agents that works with any model, on the opencode engine.

Build, edit and run Glaze (Raycast) Mac apps from Claude Code or ZCode for free, using your own subscription instead of Glaze credits. Then publish to the Glaze Store.

caix — native Apple Core AI inference server for Apple silicon (beta): OpenAI/Anthropic API, dashboard, streaming chat with tools/skills/MCP, MTP speculative decoding.

A quantum prompt playground & macOS-native Rust coding agent: morphing fluid entropy into rigid execution checkpoints. Entropy cannot lie.

Local MLX tuned models through OpenAI compatible LLM, image generation and audio inference on Apple Silicon — Rust + PyO3 + MLX

A local multi-model gateway for Codex & Claude Code on Apple Silicon — a Qwable-first agent runtime (planner → executor → repair → critic → judge), fully offline.

Run Qwen3.8-27B fully offline on an Apple Silicon Mac (MLX, 4/5/8-bit) and use it as the local backend for Claude Code. Uncensored/abliterated build supported. No API key, no network. Built by yempik.

An agentic, self-correcting machine learning experimental loop built locally on Apple Silicon using MLX.

OpenAI-compatible LLM proxy that races multiple providers in parallel and returns the fastest usable answer. Cut token cost, slash latency, handle flaky free/local model tiers. Bring your own keys, no markup. Zero-dependency install on macOS & Linux (Apple Silicon, ARM64 SBCs).

Privacy-first local Ollama chat with expert personas, reasoning, multimodal input, context-aware history, and long-term conversation memory.

Notes from running AI on my own Mac mini: model speeds, what broke, the benchmark script, and people building local AI.

Mac-local LLM-from-scratch lab for building and evaluating a small decoder-only language model on Apple Silicon.

Local voice assistant for macOS Apple Silicon — wake-word → on-device STT → Claude → natural TTS, with speaker ID and DE/FR/EN.

Disposable Alpine VM that runs Claude Code fully isolated from macOS, on apple/container.

A cross-platform tool to discover and compare local LLMs, detect hardware specifications, visualize VRAM and RAM usage, and find the best models your device can run.

Real agentic coding, fully on your laptop. No cloud, no Claude, no API key — Qwen 3 Coder 30B on your own GPU via Ollama.

Thin, zero-dependency CLI to run local LLMs on Apple Silicon (vllm-mlx or mlx_lm) with OpenAI- and Anthropic-compatible endpoints — point Claude Code at a local model.

Private, verifiable AI for business data. Verified answers copied from your records, deterministic HDC retrieval, exact aggregation, RBAC and audit trail. Local, offline, no cloud.

Delegate text work to a local model on oMLX from Claude Code, Codex, and other MCP clients — the content never leaves your machine

Offline text-to-speech for Claude Code on macOS. Your coding agent reads its replies aloud in a local voice — no API key, no quota, no cost. Hands-free with voice dictation; interrupt it with a word.

Turn your MacBook's MagSafe cable into a status light for AI coding agents like Claude Code. Menu bar app, open source.

JimmyLabs — a GPT-style language model built from scratch and fully documented on a MacBook Air M1 (8GB, Apple Silicon). Documentation-first educational research platform.

Fix FreeX thermal label printer "Filter failed" errors on Apple Silicon Macs using Rosetta 2, plus USB/Wi-Fi and 4x6 setup.

Pick the best local AI model for your hardware and task, using live Hugging Face data

JavaScript/TypeScript SDK for VeloxQuant-MLX: hardware-aware memory optimization and OpenAI-compatible local inference on Apple Silicon.

Native EXL3 (exllamav3) inference engine for Apple Silicon: MLX-backed C++ engine, CLI and OpenAI-compatible HTTP server

Make complete songs — music, lyrics and cover art — with AI that runs entirely on your own computer. macOS (Apple silicon), Windows & Linux (NVIDIA).

Local colour matching for Premiere Pro / After Effects — Accurate (classical + SegFormer) and Cinematic AI (CanonCGT). Fully on-device. by catheadai.com

LoRA fine-tuning of Qwen2.5 (4-bit) with Apple MLX for freight-text→JSON extraction — honest before/after eval (71%→100% on held-out synthetic set), every number a committed receipt.

Local AI image studio for Apple Silicon Macs: SD 1.5, SDXL/Pony, ERNIE-Image, FLUX. No account, no cloud