Autocomplete

Autocomplete that knows your meetings

LokalBot suggests the rest of what you are typing in almost any Mac app, with a small model running on your Mac. When your draft names something from a recent meeting, it can bring in what was said there.

Typing an update in TextEdit after a call with John: after “the Harbor beta ships”, autocomplete suggests “Thursday morning, after the accessibility review.” and Tab accepts it word by word.
A suggestion that comes from a meeting earlier that day. Tab accepts it word by word.

Fast enough to stay out of the way

Getting autocomplete to be useful without being intrusive or laggy took a lot of experiments with different models and quantizations. The best balance of suggestion quality and latency on a regular MacBook turned out to be the Gemma 4 E2B base model at 6-bit (Q6_K), running in-process through llama.cpp. On an M4 Max a suggestion takes a median of 56 ms while typing (see the full engine benchmark).

Update, November 19, 2026 — first suggestion after a pause: Cotypist highlights staying fast when you resume typing after a break. Previously, once llama.cpp's 180-second Metal residency keep-alive lapsed, LokalBot's first suggestion after a 5-minute pause took 95–130 ms. LokalBot now warms the loaded runtime with a single throwaway token on screen wake, unlock, click, or the first keystroke—removing that token afterward so the cached prompt stays intact—cutting a 5-minute pause down to 49–53 ms against a 47–49 ms warm reference (benchmark report; 30-minute pauses under heavy memory pressure remain unmeasured).

Context from your own work

Autocomplete lives in the same app as meetings, dictation, and screen recall, which share one memory budget for their models.

How it compares

Cotypist and Cotabby are the closest local-first alternatives. As described on their sites (checked October 13, 2026; LokalBot column updated November 19, 2026):

Cotypist, Cotabby, and LokalBot autocomplete compared
FeatureCotypistCotabbyLokalBot
License and priceProprietary; free for 100 words a day, paid for unlimitedAGPL-3.0, free (beta)GPLv3, free, no limits
PlatformsmacOSmacOSmacOS (Swift), Windows & Linux (Rust + GPUI)
ModelLocal (Gemma 4 E4B recommended)Local GGUF through llama.cpp, or Apple IntelligenceGemma 4 E2B base Q6_K (Balanced) or LFM2.5 1.2B (Lightweight), in-process llama.cpp
First suggestion after a 5-min pauseAdvertised fast resumeNot published49–53 ms on M4 Max (warm-up on wake, click, or key)
Knows what was said in your meetingsNoNoYes, opt-in
Text above the fieldNot documented on its siteOCR of the windowAccessibility text, never from private windows
Also in the appAutocomplete onlyEmoji, macros, autocorrectMeetings, dictation, screen recall, read-only MCP

A head-to-head with Cotabby used identical inputs and the same Gemma 4 E2B weights over 782 next-word checkpoints. LokalBot predicted the exact next word 32.7% of the time (256 of 782) and Cotabby 30.7% (240 of 782), a difference of 2.0 points with a 95% interval of 0.0 to 4.0. In other words, the two are comparable on accuracy; the work now is on the experience around the suggestions.

Try it

Turn on Autocomplete in Settings → Writing. It needs the Accessibility and Input Monitoring permissions and a one-time model download. Tab accepts a word. Password fields and apps you exclude are never read.

Try it locally

Meeting notes that stay on your computer by default.

Free, open source, and no account. For Mac, with Windows and Linux in alpha.

Download for macOS

Apple Silicon · macOS 15+ · or with Homebrew: brew install --cask stevyhacker/tap/lokalbot

macOS · Windows · Linux (alpha) · requirements