Henji
Summary
Generic AI reply tools produce output that reads like it was written by the same person for every inbox on earth — because it was. Henji exists to fix that: a macOS app that turns typed fragments into replies that sound like the person sending them, not like a template.
The core loop is fast: select a line in Slack or an email thread, hit ⌘↩, get a draft. Henji reads your past messages during setup and refines its model as you edit suggestions, carrying forward your phrasing preferences — 'Will do' over 'OK,' a warmer closing line, a softer lead-in before a request. Tone switches per recipient, so the same decline lands formally to a client and casually to a teammate. The tool works across Mac apps without requiring integrations. It sharpens with use; on day one it is a reasonable approximation, not a mirror.
Bottom line: Pick this if you are on a Mac and spend chunks of your day drafting replies you wish sounded more like you — but plan on a manual fallback for long-form writing or anything that requires attached files or calendar context the tool cannot see.
Community Performance Report Card
No community ratings yet. Be the first to rate this tool!
Community Benchmarks Community
Sign in to submit a benchmarkNo community benchmarks yet. Be the first to share a real-world data point.
Pros
Sign in to edit- Reads your existing message history during setup to establish a voice baseline from day one, so the first draft is calibrated to you rather than a generic register — which means you are not spending the first month correcting output that sounds nothing like you.
- Style memory updates with every edit you make, carrying forward specific phrasing preferences over time, so the tool gets more accurate the longer you use it rather than plateauing at a fixed output quality.
- Recipient-based tone switching — Customer, Colleague, Bestie and similar contexts — adjusts formality automatically, so you are not manually rewriting the same message four times for four different relationships.
- Runs on top of any Mac app via a global shortcut, so you are not locked into a specific email client or messaging platform and do not need to route messages through a separate interface.
- Designed specifically for short, high-friction replies like deadline negotiations and polite declines, which means it handles the messages most people avoid writing — not just the easy ones.
Cons
Sign in to edit- Style learning requires consistent use and active editing of suggestions to reach accuracy; teams expecting a polished personal voice from the first week will be disappointed — the model is an approximation at setup, and users who do not edit drafts get an approximation that stays frozen.
- The tool is Mac-only with no API, no web app, and no self-hosted option, which means Windows and Linux users are excluded entirely, and teams standardized on cross-platform tooling cannot deploy this without carving out a Mac-specific exception.
- Reply generation works from the fragment you type, not from reading the full thread automatically — if context buried three messages back changes what the right response is, you have to surface that context manually in your scribble or the draft misses it.
- The scope is limited to reply drafting for short messages; teams that also need long-form drafting, document generation, or any workflow involving file attachments will hit the tool's ceiling immediately and default to a general-purpose AI writing tool for those tasks — at which point they are maintaining two tools to cover one writing workflow.
Community Reviews
Sign in to write a reviewNo reviews yet. Be the first to share your experience.
About
- Platforms
- macOS
- API Available
- No
- Self-Hosted
- No
- Last Updated
- 2026-06-18T10:24:28.967Z
Best For
Who it's for
- Mac users handling frequent email and messaging
- Maintaining consistent personal writing voice in replies
- Quick drafting without generic AI output
- Users who edit suggestions to train the tool over time
What it does well
- Drafting email replies from short notes
- Generating Slack or chat responses in personal style
- Negotiating deadlines or turning down requests while staying polite
- Adapting tone for different recipients like team or friends
Integrations
Discussion Community
Sign in to commentNo discussion yet. Sign in to start the conversation.
Spotted incorrect or missing data? Join our community of contributors.
Sign Up to ContributeCommunity Notes & Tips Community
Sign in to contributeBe the first to contribute. General notes, observations, gotchas, and tips from people who use this tool day-to-day.
Frequently Asked Questions
- Is Henji free?
- Henji is a paid tool. No permanent free tier is offered.
- Is Henji open source?
- No — Henji is a closed-source tool. Source code is not publicly available.
- What platforms does Henji support?
- Henji is available on: macOS.
Hours Saved & ROI Stories Community
Sign in to contributeBe the first to contribute. Concrete time/cost savings, with context. e.g. "Cut my code review backlog from 4h to 45m per week."
Curated lists that include this category
Most AI writing tools hand you back something that technically answers the message and reads like it was drafted by nobody in particular. Henji, built by Appelier for macOS, takes a different approach: you type a rough note or a few keywords, select the text, press ⌘↩, and get a reply drafted in your voice — pulled from patterns in your past messages and sharpened by every edit you make afterward. The workflow sits on top of any Mac app, so it works in Gmail, Slack, LINE, Messages, and what the vendor describes as the vast majority of the over two million apps on macOS, without requiring per-app integrations or browser extensions.
The differentiating feature is the style memory layer. During setup, Henji reads your existing message history to establish a baseline voice. After that, each edit you accept or modify is stored — preferred phrases, tone tendencies, how you open and close a message — so the gap between ‘AI draft’ and ‘what I would actually send’ narrows over time. The recipient-switching feature extends this: you set contexts like Customer, Colleague, or Bestie, and the same underlying message adapts in register automatically, from formal acknowledgment to casual shorthand, without you rewriting.
The fit is narrow and deliberate. Henji works well for Mac users who send high volumes of short replies — team threads, client nudges, polite deadline negotiations — and who are willing to edit early drafts to train the model. The vendor states that data handling and style learning are described in the FAQ, and the privacy policy addresses server storage questions. Where it breaks: the tool generates one reply at a time from a fragment you provide; it does not read thread context autonomously, draft first messages, or handle anything requiring document attachments or calendar awareness. Teams that need those capabilities will find the tool’s scope a stopping point, not a workaround.