PrivateAI for Mac answering a Central Park weather question using the National Weather Service website

Native macOS app · Local Ollama models · Open source

PrivateAI for Mac

A local AI agent that can reason over your documents, run supervised terminal work, use native Mac context, and operate a real browser from screenshots.

Local intelligence that can act

PrivateAI connects compatible Ollama models to bounded, inspectable macOS capabilities. Model inference and conversation history stay on your Mac; public services are contacted only when a requested Tool needs them.

01

Local Ollama runtime

Discover compatible installed models, stream thinking and answers, and keep model inference out of a hosted AI account.

02

Visual browser agent

Use a live WebKit browser, rendered screenshots, frame-bound coordinates, and closed-loop actions for modern public websites.

03

Private documents

Read searchable PDFs, Markdown, text, structured data, HTML, and source files with bounded access and resumable analysis.

04

Supervised terminal

Run visible zsh commands, builds, tests, scripts, and diagnostics with output limits, timeout, cancellation, and process cleanup.

05

Native Mac context

Use Apple frameworks for device, locale, storage, network, location, calendar, reminders, contacts, and notifications when authorized.

06

Native conversation UI

Keep local SwiftData history in a macOS interface with Markdown, syntax highlighting, tables, math rendering, and live activity.

Inspect the boundaries

The repository separates schemas, direct executors, integration checks, and model-driven acceptance evidence. Capability claims are tied to current implementation, not roadmap documents.

SwiftNative SwiftUI, AppKit, WebKit, PDFKit, and SwiftData implementation.
Local-firstOllama model inference and conversation storage on the Mac.
SignedDeveloper ID signed, notarized, stapled, and Gatekeeper-validated releases.
Apache 2.0Open-source code, architecture notes, privacy policy, and security process.