MindMac
A native macOS AI chat client that connects to Ollama, LM Studio and cloud APIs, with inline writing in other apps and locally stored data.
MindMac is a native macOS AI chat client for people who want to use local LLMs and cloud services in the same app. Its inline mode lets you ask questions or generate text inside Notes, Mail and browsers without switching to a chat window. It runs on Intel and Apple Silicon Macs with macOS 13 or newer.
Local connections include Ollama, LM Studio, LocalAI, GPT4All and llama.cpp. It also supports MLX servers and custom endpoints compatible with OpenAI's Chat Completions API. For cloud models, it connects to OpenAI, Azure OpenAI, Gemini and Claude, along with services such as OpenRouter, Mistral AI and Groq.
The app stores its data on your Mac and keeps API keys in Apple Keychain. MindMac doesn't route prompts through its own servers. When you choose OpenAI, your prompts go directly to OpenAI's servers; a local connection uses the model backend you select. You don't need a MindMac account, though OpenAI access requires an OpenAI account and API key separate from ChatGPT Plus.
For longer work, MindMac has searchable conversation history, nested folders and reusable prompt templates. You can choose how much earlier conversation text a model receives, adjust keyboard shortcuts and appearance, and export chats to PDF or Markdown. Document uploads, web search, voice input and text-to-speech extend the chat interface. DALL·E handles image generation.
