BTW, I have thinking in build a shell/ipython hybrid. I think is worthless to try to emulate a shell (too much baggage), but instead build something that is alike a shell, but modern.
However, still developers will not buy it. I think maybe it could work for a subset of the user that need to work with data-science and subset of system automation.
I'm using xonsh at work, but currently the main thing I've noticed is that I still prefer iPython QT for exploring data and that xonsh starts up too slowly.
Last I checked I think the thing I'm missing from using iPython purely as a shell is the ability to pipe?
However, still developers will not buy it. I think maybe it could work for a subset of the user that need to work with data-science and subset of system automation.