Self-hosted LanguageTool server[0] with browser addon. 18 gigabytes of n-gram data plus machine learning models. You can catch tpyos on 64K of RAM, but not any deep grammar mistakes, un-idiomatic phrases, or mistakes in common proper names.
(The reason I remember this bright and shiny data point is I spent a week or three reverse engineering it and getting access to the inner interpreter; the office staff actually used it, though.)
I should have asked what is it there in replacing yourself with a mishmash of external world.
At one point that was less than $100 of RAM which isn't a big deal for the trade.