On-Device AI

Private, local AI capabilities powered by Apple Silicon

Meridian includes a built-in AI that runs entirely on your Mac. It helps you extract tasks from emails, summarize activity, create tasks with natural language, and search more effectively — all without sending a single byte of your data to the cloud.

How It Works

Meridian runs a language model locally on your Mac using Apple Silicon’s Metal GPU acceleration. All AI processing happens on your device. No data is sent to any cloud AI service.

Requirements

On-device AI requires an Apple Silicon Mac (M1 or later). The AI model (approximately 2GB) downloads automatically on first launch. Intel Macs can use all other Meridian features, but AI capabilities are unavailable on those machines.

Action Item Extraction

The AI scans your emails and identifies actionable items, creating tasks automatically with appropriate due dates and priorities. You review and confirm extracted tasks before they are added to your task list.

Activity Summarization

Get concise 2-3 sentence summaries of your recent activities, email threads, and calendar events. Quickly understand what has happened without reading through every individual item.

Natural Language Tasks

Describe a task in plain English and the AI converts it into a structured task with a title, due date, priority, and other properties. For example, “remind me to send the proposal to Sarah by Friday” becomes a task with the right title, assignee, and deadline.

Smart Search

Beyond keyword matching, the AI understands the meaning of your search queries and returns semantically relevant results. Search results include AI-generated answer summaries so you can find what you need faster.

Privacy Guarantee

The AI model runs entirely on your device. Your data never leaves your Mac for AI processing. No cloud AI APIs are used. The AI model is not trained on your data. This is a core architectural decision, not a setting you need to enable.