macai is a free, open source api development & testing project written in Swift and released under Apache-2.0. It has 931 GitHub stars, 77 forks and 44 open issues, and was last pushed 1 months ago. On this registry it ranks #88 of 103 tracked projects in API Development & Testing, with 5 head-to-head comparisons available.

What is macai?

macai is an all-in-one native macOS AI chat application that connects to virtually any AI provider — ChatGPT, Claude, xAI (Grok), Google Gemini, Perplexity, Ollama, OpenRouter, and almost any OpenAI-compatible API — and it is built for people on macOS 14.0 or later who want one app instead of a different client per provider.

What it is

macai is a Swift application distributed as a native macOS client, published under the Apache-2.0 licence with 931 stars and 77 forks on GitHub. It is an API client rather than a hosted service: the user supplies their own API tokens for commercial providers, or runs open-source models locally through Ollama, and macai holds those providers side by side in a single window. It is macOS-native and lightweight by design, with a minimalist light and dark interface, and it syncs chats, messages, and settings across devices through iCloud Sync.

The concrete problem it solves is provider sprawl. Anyone working with several LLMs otherwise juggles separate vendor web interfaces, separate token stores, and separate chat histories, and paid subscriptions for each. macai replaces that arrangement with one macOS application where each provider is registered as an API service and reached with the user's own API token. Because it also speaks OpenAI-compatible APIs, it reaches providers that have no dedicated client, and because it supports Ollama, it covers models that never leave the machine.

Key capabilities

  • Connects to ChatGPT, Claude, xAI (Grok), Google Gemini, Perplexity, OpenRouter, Ollama, and almost any OpenAI-compatible API from one client.
  • Runs against local open-source models through Ollama, with llama3.1 and llama3.2 recommended, configured by adding a new API service in the API Service tab under Expert mode.
  • Ships feature work including vision, image generation, search, reasoning, and import/export.
  • Syncs chats, messages, and settings across devices with iCloud Sync.
  • States no telemetry or usage tracking by macai, noting Apple may collect anonymized telemetry when iCloud Sync is enabled.
  • Installs as a notarized universal binary from GitHub Releases, or as a Homebrew cask via brew install --cask macai.
  • Builds from source by cloning the repository and opening macai.xcodeproj in Xcode, where Debug builds disable iCloud Sync through the DISABLE_ICLOUD compilation condition and Release builds enable it.

Who uses it and how

  • macOS users on 14.0 or later, on both Intel and Apple chips, who want a native app rather than a browser tab per vendor.
  • Developers and analysts who already hold API tokens from OpenAI, Anthropic, Google, xAI, or OpenRouter, and who therefore pay per token instead of per subscription seat.
  • Local-model users on Apple M1/M2/M3/M4 hardware who pull models with ollama pull, point macai at the Ollama service, and keep inference on-device.
  • Multi-device users who rely on iCloud Sync to keep conversations and settings consistent across Macs.
  • Contributors who build from source, including those without an Apple Developer account who accept a build without iCloud Sync.

Getting started

Download the notarized universal binary from GitHub Releases, or install the cask with brew install --cask macai. For source builds, clone https://github.com/Renset/macai.git and open macai.xcodeproj in Xcode.

How it compares

The referenced facts list no competing paid products, so macai stands alone in this registry as the only native macOS multi-provider AI chat client described here. Ollama appears in the facts as the local backend it can drive, not as an alternative to it.

When to use it — and when not to

Choose macai if the machines are Macs running macOS 14.0 or later and the intent is to bring your own API tokens, whether from commercial providers or from a local Ollama install. Do not choose it if you need Windows or Linux support, or if you expect the application to include model access rather than requiring separately obtained API credentials. Self-hosters and source builders should also note that iCloud Sync requires an Apple Developer account for signing, that Debug builds carry the DISABLE_ICLOUD flag by default, and that the project is still in active development with 44 open issues.

project readme (upstream, from github) — read inline
Macai App icon

macai

GitHub top language GitHub code size in bytes GitHub Workflow Status GitHub GitHub all releases

macai (macOS AI) is a simple yet powerful native macOS AI chat client that supports most AI providers: ChatGPT, Claude, xAI (Grok), Google Gemini, Perplexity, Ollama, OpenRouter, and almost any OpenAI-compatible APIs.

Table of Contents

Downloads

Manual

Download latest universal binary, notarized by Apple.

Homebrew

Install macai cask with homebrew: brew install --cask macai

Contributions

Contributions are welcome. Take a look at Issues page to see already added features/bugs before creating new one. You can also support project by funding. This support is very important for me and allows to focus more on macai development.

Buy Me A Coffee

Why macai

  • macOS-native and lightweight
  • User-friendly: simple setup, minimalist light/dark UI
  • Feature-rich: vision, image generation, search, reasoning, import/export and more
  • iCloud Sync: keep chats, messages, and settings in sync across devices
  • Private and secure: no telemetry or usage tracking by macai (Note: Apple may collect anonymized telemetry when iCloud Sync is enabled)

Run with ChatGPT, Claude, xAI or Google Gemini

To run macai with ChatGPT or Claude, you need to have an API token. API token is like password. You need to obtain the API token first to use any commercial LLM API. Most API services offer free credits on registering new account, so you can try most of them for free. Here is how to get API token for all supported services:

If you are new to LLM and don't want to pay for the tokens, take a look Ollama. It supports dozens of OpenSource LLM models that can run locally on Apple M1/M2/M3/M4 Macs.

Run with Ollama

Ollama is the open-source back-end for various LLM models. Run macai with Ollama is easy:

  1. Install Ollama from the official website
  2. Follow installation guides
  3. After installation, select model (llama3.1 or llama3.2 are recommended) and pull model using command in terminal: ollama pull
  4. In macai settings, open API Service tab, add new API service (Expert mode) and select type Ollama":
  1. Select model, and default AI Assistant and save
  2. Test and enjoy!

System requirements

macOS 14.0 and later (both Intel and Apple chips are supported)

Project status

Project is in the active development phase.

Build from source

Option 1: With Apple Developer Account (Full Features)

If you have an Apple Developer account and want to build with iCloud Sync support:

  1. Clone the repository: git clone https://github.com/Renset/macai.git
  2. Open macai.xcodeproj in Xcode
  3. Select your team in Signing & Capabilities
  4. (Optional) To enable iCloud Sync in Debug builds, remove DISABLE_ICLOUD from Build Settings → Swift Compiler → Active Compilation Conditions
  5. Build and run

Note: By default, Debug builds have iCloud Sync disabled via the DISABLE_ICLOUD flag to simplify contributor setup. Release builds have iCloud Sync enabled.

Option 2: Without Apple Developer Account (No iCloud Sync)

If you don't have an Apple Developer account, you can still build and run the app without iCloud Sync:

Using Xcode:

  1. Clone the repository: git clone https://github.com/Renset/macai.git
  2. Open macai.xcodeproj in Xcode
  3. Select the macai target → Build Settings tab
  4. Search for CODE_SIGN_ENTITLEMENTS
  5. Change the value from macai/macai.entitlements to macai/macai-no-icloud.entitlements
  6. In Signing & Capabilities, set "Signing Certificate" to "Sign to Run Locally"
  7. Build and run

Using Command Line:

git clone https://github.com/Renset/macai.git
cd macai
xcodebuild -scheme macai \
  -configuration Debug \
  CODE_SIGN_IDENTITY="-" \
  CODE_SIGN_ENTITLEMENTS="macai/macai-no-icloud.entitlements" \
  DEVELOPMENT_TEAM="" \
  CODE_SIGNING_ALLOWED=NO \
  build

Note: The app built without iCloud entitlements will work normally, but the iCloud Sync feature will not be available. All other features (chat, API services, personas, etc.) will work as expected.

iCloud Sync Configuration

For Contributors (Debug Builds)

iCloud Sync is disabled by default in Debug builds via the DISABLE_ICLOUD compiler flag. This simplifies the development setup and avoids CloudKit-related signing issues for contributors without an Apple Developer account.

To enable iCloud Sync in Debug builds:

  1. Select the macai target → Build Settings tab
  2. Search for SWIFT_ACTIVE_COMPILATION_CONDITIONS (or "Active Compilation Conditions")
  3. Remove DISABLE_ICLOUD from the value (leaving just DEBUG)
  4. Ensure you have proper entitlements and signing configured (see below)
For Forks / Custom Builds

If you want iCloud Sync to work in a fork or custom build, you must use your own CloudKit container:

  1. Create a CloudKit container in your Apple Developer account
  2. Enable the iCloud capability for the macai target in Xcode, and add your container
  3. Update the CloudKitContainerIdentifier value in macai/Info.plist to your container ID
  4. Ensure your app's bundle identifier matches the one you registered for the container
  5. Remove DISABLE_ICLOUD from Active Compilation Conditions if present

If CloudKitContainerIdentifier is missing, the app falls back to the default container.

License

Apache-2.0

Frequently asked questions

Is macai free to use?

macai is open source under the Apache-2.0 licence. There is no licence fee and no seat count — you can self-host it or, where the project offers one, pay a vendor for a managed version instead.

What does macai do?

All-in-one native macOS AI chat application for virtually any AI provider

What is macai written in?

macai is primarily written in Swift. Its source is publicly available at https://github.com/Renset/macai, and it has 931 GitHub stars.