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).
Your AI agents are everywhere: terminals, browsers, desktop apps. handup connects them all to one inbox. Agents ask before risky steps and show you the real thing (the command, the diff, the email), and you approve or deny from your desk or phone. They also send you finished work and updates: files, reports, previews. Say no with a reason like "use staging" and the agent changes course. Works with Claude Code, Codex, Cursor and any MCP agent. Local, no account.
I'm Ariel, and I built handup to simplify my workflows. I run a lot of AI agents at once, in terminals, browsers and desktop apps, and I kept hunting around for whichever one was waiting on me. I wanted one place for every decision, and a quick way to swipe through approvals and denials and get back to work.
I now use handup every day, and not just for decisions. My agents send me finished work there too: snapshots, Markdown files, reports and quick "done" notes. It's the one inbox where I can easily interact with all my agents.
How it works:
In terminal you can run `handup setup` and it connects the agents it finds: Claude Code, Codex, Cursor, Gemini CLI, opencode, or anything that speaks MCP.
No comment highlights available yet. Please check back later!
About handup on Product Hunt
“One approval inbox for all your AI agents”
handup was submitted on Product Hunt and earned 0 upvotes and 1 comments, placing #62 on the daily leaderboard. Your AI agents are everywhere: terminals, browsers, desktop apps. handup connects them all to one inbox. Agents ask before risky steps and show you the real thing (the command, the diff, the email), and you approve or deny from your desk or phone. They also send you finished work and updates: files, reports, previews. Say no with a reason like "use staging" and the agent changes course. Works with Claude Code, Codex, Cursor and any MCP agent. Local, no account.
handup was featured in Productivity (663.6k followers), Developer Tools (521.5k followers), Artificial Intelligence (481.6k followers) and GitHub (41.4k followers) on Product Hunt. Together, these topics include over 422.7k products, making this a competitive space to launch in.
Who hunted handup?
handup was hunted by Ariel Frischer. 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 handup stacked up against nearby launches in real time? Check out the live launch dashboard for upvote speed charts, proximity comparisons, and more analytics.
Ariel Frischer
Hey Product Hunt,
I'm Ariel, and I built handup to simplify my workflows. I run a lot of AI agents at once, in terminals, browsers and desktop apps, and I kept hunting around for whichever one was waiting on me. I wanted one place for every decision, and a quick way to swipe through approvals and denials and get back to work.
I now use handup every day, and not just for decisions. My agents send me finished work there too: snapshots, Markdown files, reports and quick "done" notes. It's the one inbox where I can easily interact with all my agents.
How it works:
In terminal you can run `handup setup` and it connects the agents it finds: Claude Code, Codex, Cursor, Gemini CLI, opencode, or anything that speaks MCP.
For any other non-terminal AI agent checkout - https://github.com/gethandup/handup to integrate.
Agents show you the real thing before they act: the command, the diff, the email draft.
Approve, or deny with a note like "use staging instead", and the agent changes course.
Answer from the terminal, the desktop app (vim bindings!), or swipe on your phone.
Everything stays on your own computer or phone. No account needed local and private.