TabType v0.1.2 — fixes two bugs that could stop TabType working entirely, and makes suggestions much faster and more relevant. Recommended for everyone, especially if the model never finished downloading for you.

🛠 Fixed

• Model download stuck at "Downloading 0%" forever. Two separate bugs: the progress handler was silently discarded, so the UI never moved; and the stall watchdog measured a directory that cannot grow while a multi-GB file is in flight, so it cancelled perfectly healthy downloads after 10 minutes — and since a cancel threw away the partial file, every retry restarted from zero. If your connection couldn't pull the whole model in one 10-minute run, TabType could never install a model at all.
• Downloads now resume. Files stream into TabType's own store and continue with an HTTP Range request, so a dropped connection, a quit, or a relaunch keeps every byte already transferred. Retries that made progress no longer count against the retry limit, so flaky connections eventually finish.
• Crash when the Mac's power state changed (Low Power Mode, plugging in/out) — a main-actor isolation trap in the power monitor.
• Suggestions replying instead of completing. With a conversation on screen the model would sometimes answer the other person rather than finish your sentence. Prompting is now strictly continuation-only, with guards at the sampler.
• Weights disappearing. Models were kept in ~/Library/Caches, which macOS purges under disk pressure. The store moved to Application Support; already-downloaded models are detected in either location, so nothing re-downloads on update.

⚡ Faster

• Suggestion latency in chat apps drops from ~0.8–1.5 s to ~160–270 ms. Conversation transcripts are normalized (timestamps, presence, "(edited)" stripped) and only re-read when the conversation actually changes, which keeps the model's cache warm between keystrokes — 99% prefix reuse.
• Screen captures pause while you type, and switching apps no longer causes a slow first suggestion.

🧠 Smarter context

• 15+ chat apps: adds Telegram, Signal, Teams, Messenger, Element, Beeper, Mattermost, Zulip, Skype and Google Chat to the apps whose conversation TabType reads via accessibility.
• Web chats: claude.ai, ChatGPT, Gemini, WhatsApp Web, Discord, Slack, Perplexity and more now work the same way inside any browser.
• Long-form writing: in Pages, Word, Notes, Ulysses, Bear and friends, TabType reads a much larger window around your cursor plus the document's opening lines, so suggestions deep in a document stay on topic.
• Context from another app — or another browser tab — is now labelled as background instead of being mistaken for what you're writing now.

🔍 Transparency

• Settings → Apps shows each app's profile (Chat / Document / Code editor) and explains in plain English exactly what TabType reads there — plus new per-app controls to turn conversation reading on for any app, or resize its context budget.

Install / Update

Download TabType-0.1.2.dmg below and drag it to Applications, replacing the old copy — your permissions and downloaded model are preserved. New install? macOS will warn about the unnotarized app: System Settings → Privacy & Security → "Open Anyway", then grant Accessibility. Full steps in the README.

SHA-256 ce7e729d1f6ef38081fc4ce9b87fe8998ff14c66a38d7383814f3c2638289700

⚠️ Still an alpha — bug reports are gold. This release exists because of one.

TabType v0.1.1 — a big quality release: suggestions are ×ばつ faster, understand far more context, and a crash is fixed. Recommended update for everyone on v0.1.0.

🛠 Fixed

• Crash when the Mac's power state changed (Low Power Mode toggle, charger events) — a main-actor isolation trap in the power monitor. If v0.1.0 quit on you mysteriously, this was it.
• Reply-drift: the model sometimes answered the conversation on screen instead of completing your sentence. Prompting is now strictly continuation-only, with sampler-level guards for reply openers.
• Suggestions no longer leak context between apps (or between browser tabs) — what you just read elsewhere is now explicitly labeled background, never mistaken for what you're writing now.

⚡ Faster

• Suggestion latency down from ~0.8–1.5 s to ~160–270 ms in chat apps: transcripts are normalized (timestamps/presence/"edited" junk stripped) so the model's KV cache stays warm between keystrokes, and screen captures pause while you type.
• Switching apps no longer causes a slow first suggestion — the new app's context is pre-warmed in the background.

🧠 Smarter context

• Reads the whole visible conversation in 15+ chat apps — now including Telegram, Signal, Teams, Messenger, Element, Beeper, Mattermost, Zulip, Skype, and Google Chat.
• Web chats too: claude.ai, ChatGPT, Gemini, WhatsApp Web, Discord, Slack, Perplexity and more get conversation-aware suggestions inside any browser.
• Long-form writing: in Pages, Word, Notes, Ulysses, Bear, and other writing apps, TabType reads a much larger window around your cursor plus the document's opening lines, so mid-document suggestions stay on topic.
• On 24 GB+ Macs, a higher-precision 8-bit model is now recommended automatically (same speed, better accuracy).

🔍 Transparency

• Settings → Apps now shows exactly what TabType does in every app: profile badges (Chat / Document / Code editor), a plain-English "How TabType works here" card, and per-app controls to change the context recipe — promote any app to conversation reading, or resize its context budget.

Install / Update

Download TabType-0.1.1.dmg below and drag to Applications (replace the old copy — your permissions are preserved). New install? macOS will warn about the unnotarized app: System Settings → Privacy & Security → "Open Anyway", then grant Accessibility. Full steps in the README.

SHA-256 95bd022e8a1160577217d8ac0ab9d2a23e0d936c67076d4540ca76a4cf3150c4

⚠️ Still an alpha — bug reports are gold.

TabType v0.1.0 — the first public alpha. A free, open-source, 100% on-device AI autocomplete for macOS (a Cotypist alternative).

Highlights

• Inline ghost-text completions everywhere you type — press Tab to accept word-by-word or all at once
• 100% local: a Qwen3-4B model runs on-device via MLX; no account, no cloud, no keystroke ever leaves your Mac
• Context-aware: reads the conversation around your cursor (accessibility tree in chat apps, on-screen text elsewhere), your recent messages, and learns your writing style
• RAM-tiered models: 24 GB+ Macs get a higher-precision 8-bit build automatically; a curated catalog (plus custom Hugging Face repos) is available in Settings
• Per-app control: chat-panels-only mode in code editors, per-app pause, per-domain website rules
• Typo-aware suggestions, word alternatives (⌃⌥Space), macros, emoji, autocorrect

Install

1. Download TabType-0.1.0.dmg below and drag TabType to Applications.
2. TabType is not notarized (no Apple Developer account — community help welcome!). On first launch macOS will warn you:
   open System Settings → Privacy & Security and click "Open Anyway".
   Power users can instead run: xattr -dr com.apple.quarantine /Applications/TabType.app
3. Grant Accessibility permission (required) when prompted. Screen Recording is optional but recommended for better context.
4. First launch downloads the AI model (~2.3–4.3 GB from Hugging Face, one time). Suggestions start when the menu-bar icon shows ready.

Notes

• ⚠️ This is an alpha. Expect rough edges — bug reports are the most valuable contribution right now.
• Full AI disclosure, feature comparison vs Cotypist/Sombra/KeyType, and architecture docs are in the README.

SHA-256 9e209d2a24f90355af26e29f2c01a7596566adca1405acb4939c138d7d42b983