Jango lets you test the parts of your app that need more than one person. It gives your app a group of AI users, each with its own browser, account, goals and memory. Point Jango at your dev URL and watch them sign in and interact with each other in real time. Direct them, join in as yourself, or take control of any user's screen. At the end you get a report with actions, errors and screenshots. Use your own AI key or Jango's managed AI. Available on Mac.
Vercel hosting, with preview deployments and a custom domain. Jango is a Mac app, but a desktop product still needs a fast, trustworthy home on the web: the landing page, download links, and the email-confirmation and password-reset pages the desktop sign-up flow sends people to. Vercel gave me, a solo founder, that whole web surface with no infrastructure to run. Every push gets a preview URL, so I could check copy, pricing and download links before they went live, and connecting usejango.com took minutes. That shaped the launch: I could keep the desktop app focused on running browsers and AI agents locally, and treat the website as something I iterate on daily alongside the product instead of a separate project. It also meant I could ship the prerendered, SEO-friendly marketing pages and the account flows at the same time as the 1.1 release.
Hey Product Hunt 👋 I built Jango because testing multi-user features alone is painful. You end up juggling five browser windows and fake accounts. Jango runs a group of AI users, each with their own login and memory, so you can see how your app holds up when several people use it at once. I'd love your feedback!
Report
The idea of giving each user their own browser and memory is really interesting.
@bonnie_lu27 thank you! the memory bit was surprisingly useful. I can bring the same people back after a change and they kind of remember what they were doing
Report
Having screenshots alongside the errors should make failed tests much easier to dig into.
@baojiang_yang yeah that was a big one for me. when something breaks I want to see what the agent actually saw, not just "failed". saves a lot of guessing
Report
I like that you can jump in yourself instead of just watching the agents run.
Weave
Weave
The idea of giving each user their own browser and memory is really interesting.
Weave
@bonnie_lu27 thank you! the memory bit was surprisingly useful. I can bring the same people back after a change and they kind of remember what they were doing
Having screenshots alongside the errors should make failed tests much easier to dig into.
Weave
@baojiang_yang yeah that was a big one for me. when something breaks I want to see what the agent actually saw, not just "failed". saves a lot of guessing
I like that you can jump in yourself instead of just watching the agents run.
Weave
@xun_jiang12 thanks! honestly jumping in is the fun part. I find most of my bugs when I'm in the chat with them and something weird happens
Being able to take over one of the users when something goes wrong sounds genuinely useful.
Weave
@raaed_muggo12 it's saved me so many times lol. agent gets stuck on something, I take over for a sec, fix it, hand it back
I can see this being handy for chat, collaboration, and anything where one user's action affects another.
Weave
@shubham_nair12 yep that's pretty much where it shines. also been using it for a trading app, two sides going back and forth. what are you building?