I was experimenting with Claude code doing similar (don’t need wrappers really) and the result was a huge amount of mediocre code and my weekly limit burnt. The code “works” but oh my the duplication and potential bug surface is off the chart.
Stopped my experiment and back to human in the loop plan->execute cycle which is way more effective.
Thankfully I don’t think we’re at jarvis levels yet.
The whole point of Mato is to make human-in-the-loop supervision easier, not to encourage autonomous loops.
In my daily workflow I constantly run multiple coding agents at the same time. The annoying part isn’t the AI itself — it’s switching between tabs, terminals, and different tools just to check what each agent is doing.
I built Mato mainly because I wanted a faster way to jump between agents, review their outputs, and approve or intervene when needed. Think of it more like tmux for AI workers, where a human manager can oversee multiple agents at once.
Personally I’m also skeptical of fully self-driving loops. In practice the plan → execute → review cycle with a human in the loop is still the most reliable way to work with AI today.