Skip to content

FuJacob/cotabby

Cotabby logo

Cotabby [beta]

Open-source, local AI autocomplete for macOS - an AI-native productivity layer for everything you type.

Visit the landing page →   |   Download for macOS →

License: AGPL v3 Latest release Downloads Stars Platform Visitors

Cotabby is free and open-source - maintained by two students. If it's useful to you, please consider supporting Cotabby's future.

Buy Me a Coffee at ko-fi.com


What It Does

Cotabby shows AI suggestions as ghost text in any macOS text field. Press Tab to accept, or keep typing to ignore.

It also does inline :emoji: autocomplete, / macros (math, unit and currency conversion, dates), and autocorrect that fixes typos with one keystroke.

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

Demo

Watch on YouTube →

Cotabby emoji autocomplete demo Cotabby autocomplete demo
Cotabby autocorrect demo Cotabby inline macros demo

Features

  • Ghost-text autocomplete -- Inline AI suggestions in any macOS text field; Tab to accept
  • Emoji autocomplete -- Type :emoji: and insert without leaving the field
  • Inline macros -- / for math, unit and currency conversion, dates, and random values
  • Autocorrect -- One-key fixes for likely typos
  • Two engines -- Apple Intelligence or local models via llama.cpp
  • Personalize -- Name, languages, length, and per-app control
  • 100% local -- Everything runs on-device
  • Visual context -- Optional screenshot OCR for on-screen awareness

Engines

Apple Intelligence: uses Apple's on-device FoundationModels runtime on macOS 26 or later, no download required.

Open Source: runs local GGUF base models in-process through llama.cpp via CotabbyInference. Rather than instructing an instruction-tuned model, Cotabby treats the model as a pure text continuer and conditions it on your persona, style, language, and on-screen context. Cotabby ships with four built-in downloadable models:

Model File Size Source
tabby-2-nano Qwen3.5-0.8B-Base.i1-Q6_K.gguf ~0.8 GB Link
tabby-2-mini Qwen3.5-2B-Base.i1-Q4_K_M.gguf ~1.4 GB Link
tabby-2-base gemma-4-E2B.i1-Q6_K.gguf ~4.5 GB Link
tabby-2-pro gemma-4-E4B.i1-Q4_K_M.gguf ~5.0 GB Link

Bring your own model

Any GGUF small enough to run on-device works. Drop a .gguf file into Cotabby's models folder and refresh the model list from the menu bar.

Browse the unsloth GGUF collection on Hugging Face for more variants. Smaller quants (Q3_K_M, Q4_K_S) trade quality for size; larger models give better completions at the cost of memory and per-token latency.

Install

Compatibility: Requires macOS 14.0 or later. Apple Intelligence suggestions require macOS 26 or later; on earlier supported systems, use the Open Source engine.

Homebrew

brew tap FuJacob/cotabby
brew install --cask cotabby

Upgrade later with brew upgrade --cask cotabby. The tap repo is FuJacob/homebrew-cotabby.

Manual download

Download and install the latest release from cotabby.app.

Why those permissions?

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

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/cotabby.git Cotabby
cd Cotabby
open Cotabby.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, CotabbyInference, Sparkle, and swift-log for runtime, updates, and logging.
  • Apple's FoundationModels, Accessibility, SwiftUI, and AppKit for on-device generation and macOS integration.
  • GitHub gemoji and Hugging Face for the emoji data and downloadable models.
  • SymSpell by Wolf Garbe (MIT) for autocorrect; dictionary from Google Ngrams (CC BY 3.0) and SCOWL.
  • Everyone who filed issues, tested prereleases, and sent pull requests.

Created by

Originally created by @FuJacob, now developed and maintained by @FuJacob and @jam-cai.

License

Cotabby is licensed under the GNU Affero General Public License v3.0. You can use, study, modify, and redistribute the app, but if you distribute a modified version or make one available to users over a network, you must provide the corresponding source code under the same license.

Third-party dependencies, emoji data, and downloadable model weights keep their own licenses and usage terms. Bundled third-party notices (SymSpell and the autocorrect frequency dictionary) are reproduced in THIRD_PARTY_LICENSES.md.

Sponsor this project

Packages

 
 
 

Contributors

Languages