Today's the day. Operum is live on Product Hunt.
An AI product team on your desktop, with expert workflows built in. You stay in charge: nothing merges without a Tester's pass.
If you try it, tell me what breaks. I read everything π
https://t.co/xe22uhOKoh
Best question on our Product Hunt launch so far: "How do you keep AI-built apps secure?"
Our answer: the agent that writes the code can never approve it. A separate Tester has to pass every PR. Maker-checker, built in.
https://t.co/xe22uhOKoh
We build Operum with Operum.
The rule I trust most: green CI isn't enough. A separate Tester agent has to approve the exact commit before anything merges, even my own changes.
Tomorrow it's on Product Hunt.
CI was green. The Tester still said no.
Fixed, re-tested, approved 23 min later. I merged.
Operum won't merge until the Tester approves that exact commit.
Launching on Product Hunt tomorrow.
@ServerForAgent@therealdanvega@CodingGarden@stolinski Yup! forgot to mention that 1 laptop is like control center - main team running my own old github account, 4 others are mac/windows/linux boxes running the same project using separate github accounts so it's easier to split/measure
@trq212@mattpocockuk Understanding fundamentals of the underlying frameworks important for high quality delivery. But at the same time proper testing strategy may almost eliminate this requirement. Good engineering judgement still matters though.
You already have one great agent in Cursor.
Operum gives it a team on your own repo: PM, Architect, Engineer, Tester, Marketing, Community.
Each role runs its own model. Grok plans, Composer builds.
A separate Tester checks every PR before merge. You supervise from a cockpit.
Thanks @BetaList for featuring Operum!
Six AI agents (PM, Architect, Engineer, Tester, Marketing, Community) take the work from issue to PR to QA to merge in your own GitHub repo, with your approval where you want it.
Try it and tell us what's rough.
https://t.co/ugud8eMZIU
@buildwithrg You can build one (custom) with Operum in 1 -2 days. You could experiment with it - just describe what kind of app you need and agents do the rest
Hey #Founders , it's time to try out Operum Desktop. Built by solo founders with Builders community in mind. We are running 30 agents (5 teams) - so far flight is normal
Our AI team shipped 290 changes in 11 days. Here's why we moved our launch.
On Oct 15 we decided Operum shouldn't be locked to one AI engine.
Since then:
β 346 commits
β 290 changes merged
β 226 tasks closed
β 2 releases
Most of it was shipped by Operum's own AI agents. We build Operum with Operum.
Result: Operum now runs on Cursor and Claude. More engines are coming before launch.
What Operum is: six AI agents (PM, architect, engineer, tester, marketing, community) that work like a real team. Describe what you want in plain English. They plan, build, test, ship and help you launch it.
Websites, web apps, stores, internal tools, SaaS. No code, no terminal.
Stressful? Kind of. Exciting? Absolutely.
Free tier available. If you already have Claude or Cursor, you're ready.
Honest feedback wanted, good and bad π
@alprimak Trailer: 1 minute.
The product: a bit longer π
v0.60.0 is out: 247 PRs merged in the 8 days since v0.59.0, planned, built and QA'd by our own AI team on GitHub.
The trailer was imagined. The PRs weren't.
On Product Hunt Tue, Nov 10.