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).
LLMessenger
Stop counting unread. Start knowing who's waiting on you.
Unread counts show what you received. LLMessenger shows what you owe — who's waiting on you across iMessage, Signal, Telegram & Slack — and drafts replies you approve with one tap. Every claim cites its source messages. Local AI, open source.
Last month I found out a friend had been waiting a week for an answer from me. A week of him thinking I'd seen it and didn't care. My unread badge said 214 — a number that told me everything I'd received and nothing about what I owed.
So I built the opposite of an unread count. LLMessenger tracks message debt across iMessage, Signal, Telegram and Slack. The headline in the app isn't a count — it's "4 people are waiting on you." Then it drafts the way out: replies in your voice, queued for one-tap approval, with a visible 5-second countdown and undo on every send. Auto-send exists only as an opt-in for trivial templated acks — 30-second undo, audit log, kill switch.
I built it to be distrusted first. Every card cites the exact source messages — tap a claim, read the evidence; anything that can't cite a real message gets rejected. It runs on-device by default (Apple Intelligence or Ollama), no server, no telemetry, and it's Apache 2.0 — don't take my word for any of this, read the code.
Honesty corner: it's unsigned (I skipped Apple's $99/yr fee for now), so macOS will grumble once — or skip that entirely:
brew tap googlarz/tap && brew install --cask llmessenger
Demo Mode is the first button on the welcome screen — the entire product on synthetic data, zero accounts connected. 60 seconds and you'll know.
So: what does your badge say right now — and do you know who's actually waiting on you? 👇
finally something that fixes the worst part of group chats, knowing i actually owe a reply somewhere. the source-citing drafts caught me off guard, felt way less risky than just trusting an ai to speak for me.
The idea of seeing "what you owe" across iMessage, Signal, and Slack in one place is genuinely useful, and the source citations on each draft reply gave me way more trust than I expected. Nice work.
About LLMessenger on Product Hunt
“Stop counting unread. Start knowing who's waiting on you.”
LLMessenger was submitted on Product Hunt and earned 6 upvotes and 5 comments, placing #134 on the daily leaderboard. Unread counts show what you received. LLMessenger shows what you owe — who's waiting on you across iMessage, Signal, Telegram & Slack — and drafts replies you approve with one tap. Every claim cites its source messages. Local AI, open source.
LLMessenger was featured in Messaging (51.9k followers), Privacy (11.2k followers), Artificial Intelligence (473.1k followers) and GitHub (41.3k followers) on Product Hunt. Together, these topics include over 150.6k products, making this a competitive space to launch in.
Who hunted LLMessenger?
LLMessenger was hunted by Dawid Piaskowski. 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 LLMessenger stacked up against nearby launches in real time? Check out the live launch dashboard for upvote speed charts, proximity comparisons, and more analytics.
Dawid Piaskowski