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).
Pipe
Self-hosted unified inbox + AI that reads it for you
Your private second brain. Pipe merges WhatsApp, email, Telegram, Teams and more into one thread per person, then an AI reads it all — summarizing long threads and voice notes, telling you who's waiting on a reply, and drafting replies in your voice. Self-hosted and MIT-licensed: your messages, media and a daily encrypted backup live on your own server, never a company's. Local AI by default — nothing private leaves your box.
Hey Product Hunt 👋
I built Pipe because I got tired of my life being scattered across six apps I don't control. My conversations — WhatsApp chats, emails, years of voice notes and photos inside them — all live on someone else's servers, under someone else's terms. They can rate-limit me, lock me out, change the rules, get breached, or just shut down. The day that happens, the record of my relationships is gone, and there was never really an export button that gave me all of it.
Pipe flips that. It pulls every channel — WhatsApp, email, Telegram, Teams, Instagram — into a single thread per person, on hardware you control. Then it adds an AI layer that actually reads everything: it summarizes long threads and voice notes, gives you a daily brief, tells you who's waiting on a reply, and drafts responses in your own style. The AI runs locally by default (Ollama + local whisper) — the private jobs are hard-wired to never leave your box.
And because it's yours, it's a real archive: a daily encrypted backup of everything — messages, the WhatsApp bridge sessions, the irreplaceable media. Restore is tested, not theoretical. "Export" is just copying a folder.
Stack is deliberately boring so it lasts: vanilla Node + SQLite + a PWA, zero framework. MIT-licensed, single-tenant, self-hostable in one `docker compose up`.
Honest status: it runs in production for me, every day — but it's early. If you self-host, I'd love your feedback and issues.
Rather not run it yourself? There's a managed version that funds the project → pipe.one
Ask me anything — happy to go deep on the architecture, the WhatsApp bridge, or the local-AI privacy model. 🙏
honestly the "drafting replies in your voice" bit is what i'd care most about, but right now it sounds a bit like a black box. would love to see a way to actually train it on past messages per contact so it picks up little things like how i sign off to my mum vs my manager, basically just make the tone matching feel less generic.
Privacy-first unified inbox is genuinely useful. One thing that would make it indispensable for me: a quick "context on this person" sidebar that surfaces any shared files, upcoming deadlines, or open promises you both made in the thread, so I can catch up on a contact in seconds without scrolling. Would feel like a true second brain rather than just a merged chat.
About Pipe on Product Hunt
“Self-hosted unified inbox + AI that reads it for you”
Pipe was submitted on Product Hunt and earned 3 upvotes and 3 comments, placing #147 on the daily leaderboard. Your private second brain. Pipe merges WhatsApp, email, Telegram, Teams and more into one thread per person, then an AI reads it all — summarizing long threads and voice notes, telling you who's waiting on a reply, and drafting replies in your voice. Self-hosted and MIT-licensed: your messages, media and a daily encrypted backup live on your own server, never a company's. Local AI by default — nothing private leaves your box.
Pipe was featured in Productivity (658.2k followers), Messaging (52k followers), Artificial Intelligence (475.9k followers) and GitHub (41.4k followers) on Product Hunt. Together, these topics include over 306.2k products, making this a competitive space to launch in.
Who hunted Pipe?
Pipe was hunted by Alvaro S Zweig. 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.
Want to see how Pipe stacked up against nearby launches in real time? Check out the live launch dashboard for upvote speed charts, proximity comparisons, and more analytics.
Alvaro S Zweig