This product was not featured by Product Hunt yet. It will not be visible on their landing page and won't be ranked (cannot win product of the day regardless of upvotes).
Dzong Mail is the AI email assistant that lives on your machine. It sorts your inbox, drafts replies, tracks follow-ups & shows what your inbox is really made of - powered by local AI that works offline, or your own API keys. Gmail, Outlook, any IMAP. MIT licensed. No AI tier. $0 forever.
Every AI email assistant makes the same quiet ask: give us your inbox. Your messages on their servers, their model reading them, $20–30/month for the privilege.
We asked a dumber question: why does the mail have to travel to the assistant?
It doesn't. The assistant can travel to the mail.
Dzong Mail is a full AI email client that runs entirely on your computer:
🧠 Local AI via Ollama, works offline. Or bring your own OpenAI / Anthropic key
✍️ 3 draft replies per email, written the wayYOUwrite to that specific person
🌙 Morning briefing: overnight mail labeled, drafts waiting, your inbox priced in minutes
🧹 Bulk unsubscribe, ranked by how much of each sender you actually read
📊 Inbox health score + reply debt (warning: humbling)
↩️ Every automated action logged and undoable
📬 Gmail, Outlook, Fastmail, iCloud, any IMAP. Unlimited accounts
💸 $0. Forever. No "AI plan", no seats, no trial. There's no cloud to bill you for. 🫡
🔓 MIT licensed. Read every line of code that touches your mail.
Why "Dzong"? Bhutan's fortress-monasteries, where communities kept their records behind walls they owned. Walls were never the problem. Whose walls is the question.
Dzong Mail was submitted on Product Hunt and earned 2 upvotes and 1 comments, placing #143 on the daily leaderboard. Dzong Mail is the AI email assistant that lives on your machine. It sorts your inbox, drafts replies, tracks follow-ups & shows what your inbox is really made of - powered by local AI that works offline, or your own API keys. Gmail, Outlook, any IMAP. MIT licensed. No AI tier. $0 forever.
On the analytics side, Dzong Mail competes within Email, Open Source, Artificial Intelligence and GitHub — topics that collectively have 628.9k followers on Product Hunt. The dashboard above tracks how Dzong Mail performed against the three products that launched closest to it on the same day.
Who hunted Dzong Mail?
Dzong Mail was hunted by Kapil Pawar. A “hunter” on Product Hunt is the community member who submits a product to the platform — uploading the images, the link, and tagging the makers behind it. Hunters typically write the first comment explaining why a product is worth attention, and their followers are notified the moment they post. Around 79% of featured launches on Product Hunt are self-hunted by their makers, but a well-known hunter still acts as a signal of quality to the rest of the community. See the full all-time top hunters leaderboard to discover who is shaping the Product Hunt ecosystem.
For a complete overview of Dzong Mail including community comment highlights and product details, visit the product overview.
Kapil Pawar
Hey Hunters 👋 I'm Kapil, maker of Dzong Mail.
Every AI email assistant makes the same quiet ask: give us your inbox.
Your messages on their servers, their model reading them, $20–30/month for the privilege.
We asked a dumber question: why does the mail have to travel to the assistant?
It doesn't. The assistant can travel to the mail.
Dzong Mail is a full AI email client that runs entirely on your computer:
🧠 Local AI via Ollama, works offline. Or bring your own OpenAI / Anthropic key
✍️ 3 draft replies per email, written the way YOU write to that specific person
🌙 Morning briefing: overnight mail labeled, drafts waiting, your inbox priced in minutes
🧹 Bulk unsubscribe, ranked by how much of each sender you actually read
📊 Inbox health score + reply debt (warning: humbling)
↩️ Every automated action logged and undoable
📬 Gmail, Outlook, Fastmail, iCloud, any IMAP. Unlimited accounts
💸 $0. Forever. No "AI plan", no seats, no trial. There's no cloud to bill you for. 🫡
🔓 MIT licensed. Read every line of code that touches your mail.
👉 Follow us on Linkedin - here
⭐ Star us on GitHub: github.com/peopleofproduct/dzong-mail
3 things I'd love you to try:
Let the local model draft a reply, then pick from 3 takes
Open Analytics & check your inbox health score (be brave)
Connect your $3/month IMAP host, not just the big two
Brutal feedback welcome, especially from people who've sworn off email assistants.
What would make you switch? 👀