tabby

Open-source, local-first AI autocomplete for macOS. [beta]

Visit the landing page →

---

Demo

Watch on YouTube →

Email	Slack
Notes	iMessage

What It Does

tabby is a menu bar app that brings inline autocomplete to the text field you're already using. Keep typing in your host app: tabby watches the focused field, generates a continuation, and renders it as ghost text next to your caret. Press Tab to accept a chunk, keep pressing to advance, or just keep typing to diverge.

Everything runs on-device. No hosted API, no cloud round-trip.

Features

• System-wide completions -- Works in any macOS text field (Safari, Notes, Mail, etc.)
• Ghost text UI -- Suggestions appear as translucent overlay text at your cursor
• 100% local -- All inference runs on-device. No data ever leaves your Mac
• Visual context -- Screenshot OCR gives the model awareness of what's on screen
• Low latency -- Optimized for fast response on Apple Silicon

Engines

Apple Intelligence [EXPERIMENTAL]: uses Apple's on-device FoundationModels runtime on macOS 26 or later, no download required. Currently does not perform as well as the Open Source models. We're actively working on improving it.

Open Source: runs local GGUF models in-process through llama.cpp via llama.swift. Built-in downloadable models suggested for use:

Model	File	Size
tabby-fast-1	Qwen3-0.6B-Q4_K_M.gguf	~0.4 GB
tabby-balanced-1	gemma-3-1b-it-Q4_K_M.gguf	~0.8 GB

You can also drop your own .gguf files into tabby's models folder and refresh the model list.

Install

1. Download the latest tabby.dmg from GitHub Releases.
2. Drag tabby.app into Applications and launch it.
3. Grant Accessibility, Input Monitoring, and Screen Recording when prompted.
4. Pick an engine. Apple Intelligence if available, otherwise Open Source plus a model.
5. Start typing in any supported editable field.

If macOS blocks first launch, right-click tabby.app → Open, or allow it in System Settings → Privacy & Security.

Why those permissions?

• Accessibility: read the focused text field's value and caret position.
• Input Monitoring: detect global Tab presses for acceptance.
• Screen Recording: capture a screenshot around the focused field for visual context (OCR).

Requires macOS 15.0 or later. Apple Intelligence suggestions require macOS 26 or later; on earlier supported systems, use the Open Source engine.

Local Development

Requires Xcode and Command Line Tools. Apple Silicon is strongly recommended for local model performance. For setup, build, test, and contribution workflow details, start with CONTRIBUTING.md.

git clone https://github.com/FuJacob/tabby.git
cd tabby
open tabby.xcodeproj

If you want to understand the runtime and suggestion pipeline before contributing, read ARCHITECTURE.md.

Contributing

Contributions are welcome. See CONTRIBUTING.md for setup, build, and PR guidelines, and CODE_OF_CONDUCT.md for community expectations. For a tour of the runtime and suggestion pipeline, read ARCHITECTURE.md.

Acknowledgments

• llama.cpp: local GGUF inference engine that powers the Open Source models
• llama.swift: Swift package wrapping llama.cpp for in-process inference
• Sparkle: in-app update framework
• Apple's FoundationModels framework: on-device Apple Intelligence runtime
• Apple's Accessibility (AX) APIs: focused-field discovery and caret geometry
• The Qwen and Gemma model teams for the open-weight models Tabby ships with
• The Hugging Face community for hosting and distributing GGUF model weights
• Swift, SwiftUI, and AppKit, which together make the menu bar app, overlays, and settings UI possible
• Everyone who has filed issues, tested prereleases, and contributed pull requests

Built by

@FuJacob and @jam-cai

License

tabby is licensed under the GNU Affero General Public License v3.0. The AGPL's network-use clause means any modified version made available to users over a network must also be source-available under the same terms.