Question 1

What does Thuki even mean?

Accepted Answer

Thuki (Thư ký) is Vietnamese for secretary: a personal assistant who handles the details so you can focus on the work. The product is built for quick, throwaway conversations powered by local AI models: ask something, get an answer, move on. No history you didn't ask for, no cloud logging everything you type. Long term, Thuki is being built toward a fully agentic assistant that can actually do work on your behalf (Gmail, Calendar, Slack, and more via MCP integrations). The kind of assistant that handles the task, not just the answer.

Question 2

Which Mac does Thuki run on?

Accepted Answer

Thuki requires macOS 13.4 (Ventura) or later on Apple Silicon (M1 or later). Intel is not supported — Thuki ships no Intel build. The local model runs on the built-in GPU. On first launch macOS asks for two permissions: Accessibility (for the global shortcut that summons Thuki from any app) and Screen Recording (for the /screen command). Grant both once. Check the GitHub releases page for the current supported builds.

Question 3

Does Thuki run the AI model itself?

Accepted Answer

Yes, by default. Thuki ships its own local inference engine, a bundled llama.cpp server, and runs the model right on your Mac with nothing else to install. You pick an open model, Thuki downloads it once, then runs it on-device and streams the answer back. Prefer your own Ollama install? It still works as an optional provider, but it is no longer required.

Question 4

Why not just use LM Studio, Jan, or Ollama directly?

Accepted Answer

Those are destinations: you switch to a window, paste your context, read the answer, switch back. Thuki inverts that. Double-tap Control and it appears over whatever you are doing, already holding your selected text, then vanishes when you dismiss it. It also ships its own engine, so there is no separate runtime to wire up. Same local models; the difference is the summon-anywhere workflow around them.

Question 5

Do I need an internet connection?

Accepted Answer

No. After the initial model download, the model runs on your own hardware, so everyday use works offline. Web tools like /search reach the internet when you use them.

Question 6

Which models can I use?

Accepted Answer

Open models like Llama, Gemma, Qwen, Mistral, and Phi. Onboarding suggests a few Staff Picks sized for your Mac, and you can browse and download more in Settings. You pick the model; the built-in engine runs it. See "Does Thuki run the AI model itself?" for how models are managed.

Question 7

Where is my data stored?

Accepted Answer

A single SQLite file on your disk. There is no backend, no server, no log you cannot cat. Delete the file and the data is gone.

Question 8

Is there a subscription or per-query charge?

Accepted Answer

No. Once you download Thuki there is no cloud service billing you. Your GPU does the work.

Blog

Thuki v0.15: a Built-In Local AI Engine for macOS

Thuki Is Not an AI Model. Here Is What It Actually Does

Building Thuki: Engineering a Floating AI Overlay on macOS

Local AI on macOS in 2026: How Thuki Compares

Why Thuki Has No Cloud Tier

Meet Thuki: a Floating AI Assistant for macOS