Recent hype about loop engineering made me realize that im missing one thing, and that is an agent that should be doing my job at the end of my loop: real user test
i developing a huge b2b ecommerce project codebase. and for every new feature or fixes my job is always to test it on the browser. yuck.
so i have made some research and there is TestSprite, but its not what i really want, i cant even self host it.
so i built OpenUser. now i just engineer the loop with simple prompt: complete {feature} and use /openuser to test it.
it store user persona, struggle, checkpoints, console logs, network logs. the agent has access to all and just fix everything.
this is the real replacement of me at the end of the loop.
everything runs locally, with any coding agents and model.
try it: https://github.com/manalkaff/openuser npx openuser-cli