Your Mac finishes
your sentences

System-wide inline autocomplete, powered by a language model that runs entirely on your machine. Private, fast, open source.

Requires macOS 13+  ·  Apple Silicon recommended  ·  GPL v3

Notes.app
Dear team,
I wanted to follow up on the discussion from yesterday's standuptab
regarding the migration timeline.
The current ETA is end of Q2, pending the infrastructure reviewtab
// suggestions appear inline — Tab to accept, Esc to dismiss

Autocomplete that respects your privacy

Private

Everything runs locally on your Mac. No data leaves your device. No accounts, no cloud, no telemetry.

Fast

Suggestions in 100–300ms via Ollama, llama.cpp, or CoreML. Optimized for Apple Silicon.

Open source

GPL v3 licensed. Read every line, fork it, extend it. Built in Swift 6.2 with strict concurrency.

Yours to tune

Per-app exclusion rules, PII filtering, battery-aware pause, and personalization that learns your style.

Three steps. No sign-up.

1

Install a runtime

Install Ollama with Homebrew and pull a small model. That's the whole setup — about a minute.

2

Launch AutoSuggest

It lives in your menu bar. Grant Accessibility and Input Monitoring when prompted.

3

Start typing

Suggestions appear inline in any text field. Press Tab to accept, Esc to dismiss.

Terminal — zsh
$ brew install ollama
$ ollama pull qwen2.5:1.5b
$ open -a AutoSuggest
// grant Accessibility + Input Monitoring — done

Choose your inference engine

Ollama Recommended

Easiest setup. Manages models for you. Great performance on Apple Silicon.

brew install ollama ollama pull qwen2.5:1.5b

llama.cpp

Direct GGUF model loading. Maximum control over quantization and parameters.

brew install llama.cpp llama-server -m model.gguf

CoreML On-device

Apple Neural Engine inference with a bundled model. No server to run.

// Settings > Model Source // Point to a CoreML manifest

Your text never leaves your Mac

No cloud. No telemetry. No accounts.

Privacy at a glance

  • 100% on-device — no cloud inference, ever
  • No telemetry by default, content-free when enabled
  • Personalization is opt-in, PII-filtered & encrypted at rest
  • Stays silent in password fields & secure input
  • GPL v3 — fully auditable
Read the privacy source →

Fine-tune a model on your writing

Train on Mac (MLX)

Fine-tune directly on Apple Silicon using MLX. No GPU rental needed — your M-series chip handles it.

pip install -r requirements-mlx.txt python finetune_mlx.py --data-dir ./data

Train on Colab (free GPU)

Upload your data to Google Colab and train with Unsloth on a free T4 GPU. Ready-made notebook included.

Open finetune_colab.ipynb in Colab Upload data → Train → Download GGUF

One-click import

Export the fine-tuned model as GGUF with an auto-generated Ollama Modelfile. One command to import.

ollama create my-autosuggest -f Modelfile

Privacy-first data

Training data is opt-in, PII-filtered twice, stored locally, and never transmitted.

Settings > Privacy > Enable collection

Questions, answered

Is anything sent to a server?

No. Suggestions are generated by a model running on your Mac — your text, the surrounding context, and any personalization never leave the device. The only network activity is what you set up yourself: downloading a model, or talking to a local runtime on 127.0.0.1.

Why does it need Accessibility and Input Monitoring?

Accessibility lets AutoSuggest read the text field you're focused on and insert a suggestion when you accept it. Input Monitoring lets it notice typing and the Tab / Esc shortcuts. A system-wide autocomplete can't work without them.

Does it store what I type?

Not unless you turn on personalization. When you do, entries are PII-filtered, encrypted at rest, and kept on your Mac — never uploaded.

Will it read my passwords?

No. AutoSuggest detects secure text fields and macOS secure input mode and stays silent there. Common password-manager apps are excluded by default.

Which Macs are supported?

macOS 13 (Ventura) or later. Apple Silicon is recommended for sub-second suggestions; Intel Macs work but are slower.

How do I uninstall it?

Quit AutoSuggest from the menu bar, drag it out of /Applications, and revoke its permissions under System Settings → Privacy & Security. No background remnants.

Ready to type less?

Free, open source, and runs entirely on your machine. No account needed. No internet required.

$ curl -fsSL .../install.sh | bash