Highlight & Reply (primary)
Select meaningful text in any app and the button appears. Works with drag, box-select, double-click, triple-click, and Ctrl+A. Appears only in whitelisted communication apps, so it stays out of your code editor.
Up and running in about a minute.
Install, add your model, and generate your first reply. That's all it takes to start.
Quick start
1
Download & install
Grab the installer for Windows. It runs quietly in the background after setup.
2
Add your model
Open Settings → API config. Paste your own API key, or point to a local model (Ollama, LM Studio — no key needed). Verify, and you’re ready.
3
Select a message
In any chat, select the message you want to answer. A green button appears beside your selection — hover it and choose Generate reply.
Two ways to invoke
Copy + shortcut (fallback)
Copy text anywhere and press your global shortcut. The main window opens with the text already loaded — no pasting needed. Works even outside the whitelist.
What it does
It reads, asks, then writes
BreatheReply first reads the scene. If a reply needs a fact only you have, it asks one short question instead of guessing, then writes a ready-to-send reply in your voice — and you can steer tone or stance with a click.
It keeps the thread
One conversation, several replies in a row: turn on continuous mode and each reply builds on what came before, so you don’t re-explain the context every time. It ends whenever you say so — or automatically when you switch to another app.
It asks which way you lean
When what’s hard isn’t the wording but the position, it can ask before writing: three plain-language options, each combining the key fact with a stance. Prefer to see a draft first? That’s the default — switch stance from the result panel.
It names where you’ll stall
Under each draft it can point out what is likely to hold you up — being hit emotionally, a timing signal in the message, or a fact only you have — with one practical line on how to get past it.
Auto-detect, or pin a scene
By default it reads each message and decides the scene itself — nothing to pick. If you only ever use it for one thing, pin that scene in Settings — work, customer service, social media, or personal chat — for sharper replies.
The draft is yours to finish
Drafts open in an editor you can change directly — reword, add an emoji, keep what’s already right. Names it doesn’t know become tappable placeholders: fill one in, and every one of its kind in the message is filled at once.
Reply later
Park a message with 6 preset slots (15 min ~ 4 hours) or a custom time. A separate list window keeps everything sorted, and one calm reminder arrives when it’s time.
Auto-fill back into the box
One click sends the reply back into the input field it came from — no manual copy-paste. (Some apps need the cursor placed in the field first.)
Screenshots work too
Text you can’t select or copy — take a screenshot. Two on-device OCR engines read the conversation and reply just the same.
Five focused windows
Main window, reply-later list, settings, screenshot review, and Highlight & Reply each get their own window — open one without losing your place in another. Closing just hides them; nothing is lost.
Settings worth knowing
App whitelist40+ messaging, browser and mail apps are pre-whitelisted so the float only appears in chats. Add or remove apps anytime.
ShortcutsMain window (
Ctrl+Shift+B), the reply-later list (Ctrl+Shift+L) and settings (Ctrl+Shift+,) — all customizable.Communication styleSet a default tone — formal, friendly, thoughtful, or concise — that shapes every reply.
Reply languageAuto-detect, Chinese, or English — independent of the interface language, so replies follow the conversation, not the UI.
Data managementExport your settings to a file (your API key is never included) and import them on another machine. Reset to defaults anytime — it takes effect immediately, and your reply-later list and history are untouched.
PrivacyYour key is encrypted on-device. Messages are never stored. Optional anonymous stats record action types only, and can be turned off.
System requirements
Windows 10 or later. macOS is on the roadmap.