Loading...
Loading...
Omlx: LLM inference server with continuous batching & SSD caching for Apple Silicon — managed from the macOS menu bar. It is listed under Development & Code on AI Registry as a free tool.
The tools below are approved listings in the same category, ordered by how closely their tags match Omlx. This is an automatic list. We have not written a researched verdict for Omlx yet, so treat it as a shortlist and check each vendor's pricing page before switching.
Built from each tool's listing. Vendors can update their own listing after claiming it.
JANG — GGUF for MLX. YOU MUST USE JANG_Q RUNTIME.
JANG is an open source quantization method for running larger AI models on Apple Silicon Macs. It is built around the MLX framework and shrinks model files so that bigger, more capable models fit in the memory of a laptop or desktop Mac while keeping output quality higher than uniform quantization at the same size. St...
Sandbox your local AI agents so they can read/write only what they need
Agent Safehouse is a macOS native sandbox for local AI coding agents. It wraps an agent process in kernel level enforcement through the operating system's sandbox facility, so an agent running with its permission prompts switched off still cannot write outside the project directory or read sensitive files. A destructiv...
Bonsai Demo
Bonsai is the family of compressed language models from PrismML, and the demo is the hosted way to try them before downloading. PrismML builds what it calls ultra dense intelligence: models quantized to ternary or one bit weights so that capable reasoning fits on phones, laptops and edge hardware instead of a datacente...
Free, sub-second on-device AI dictation for macOS.
This is a dictation application for macOS that turns speech into polished text at the cursor, inside whatever app is in focus. Audio is transcribed on the Mac itself, stripped of verbal clutter, formatted according to the user's settings and then inserted directly into the target application, with a clipboard fallback ...
Open-source AI meeting notes for Mac.
Humla is a free, open source AI notepad for Mac that records meetings without adding a bot to the call. It captures both sides of a conversation, shows the transcript as it is produced and writes summaries from a chosen preset such as a client recap or an internal action list. Transcription and summaries can run entire...
Every agent's model. One place.
Magpie is a desktop app that lets coding agents use models from any vendor. A user adds a provider once, such as DeepSeek, Kimi, GLM, Qwen, OpenRouter or Ollama, or signs in with an existing Claude or ChatGPT plan, and then picks that model from agents like Codex, Claude Code, Gemini CLI, OpenCode, Goose or Cursor CLI ...