Charm – on-device spelling, grammar, and prediction for macOS

Name: Charm – on-device spelling, grammar, and prediction for macOS
Availability: InStock
Author: theodorehq

by theodorehq·May 22, 2026·3 points·1 comment

Visit Project View on HN

AI Analysis

●●●BangerZero to OneSlickSolve My Problem

Local LLM autocorrect that works system-wide while Grammarly stays stuck in the browser.

Strengths

•Runs Gemma 2B or Qwen 3B entirely on-device with no cloud dependency or accounts.
•System-wide input monitoring catches typos in every app, not just browsers.
•Model auto-unloads after 5 minutes idle to bound RAM usage on consumer hardware.

Weaknesses

•macOS-only with no Windows or Linux support planned in the initial release.
•Requires Accessibility permissions which some security-conscious users may reject.

Post Description

I've spent the last year building Charm, a native macOS menu bar app that corrects spelling, fixes grammar, and predicts your next word.

Three features:

- Spells: NSSpellChecker plus a local LLM for context-aware corrections (catches "definately" -> "definitely" without the false positives macOS autocorrect is known for). - Polish: sentence-level grammar fixes triggered at punctuation boundaries. - Oracle: next-word prediction, Tab to accept.

100% local. Choose Gemma 2 2B or Qwen 2.5 3B; the model downloads once from HuggingFace on first use, then everything runs on your Mac. No cloud option exists, no accounts, no API keys, no telemetry. The model auto-unloads after 5 minutes idle so the RAM cost is bounded.

Built in Swift / SwiftUI. Needs Accessibility and Input Monitoring permissions because text replacement requires reading keystrokes globally. Nothing leaves your machine.

One-time purchase.

I'd love feedback, especially edge cases where corrections go wrong.