Obsidian is commercial closed source app with subscription. Free for personal use only, commercial license is $50/year. I am not going to build my PIM around proprietary tool with subscription!
If your concern is about the lack of a clear migration path, Obsidian vaults are just folders with markdown files, which can be used with absolutely anything, you can literally use them in Emacs or VSCode if you want. The most popular PDF annotation plugin is AGPL-3 licensed and its format is also transparent so you can migrate to something else.
Not really, markdown has tons of tiny implementation details. And I can not use PDF annotation plugin in Emacs...
> markdown has tons of tiny implementation details. And I can not use PDF annotation plugin in Emacs
The same can be said about any other open format, I guess. There's no free lunch, you're always locked in by the implementation/workflow details, and have to write actual code (or use the code written by someone else) to migrate off to a different tool. The point is to not be locked by the format obfuscation or the storage.
I need to be absolutely sure PDF annotation tool will be around in a year 2050! Obsidian may withdraw their subscription offer at any time! Or raise subscription to $10000 per year (someone here says much higher price would be a steal!). I will always be able to run Logseq PDF annotator! Maybe in virtual machine. Or I will patch it (I have source code!!!). I have control over it!
And I really really hate fiddling with plugins. I was never much of Vim/Emacs guy for this reasons (prefer integrated IDEs such Idea). Logseq just works without setting up dozens of plugins and scripts. I use vanilla version with two plugins (video timestamp annotations and extra theme).
Refactoring is perhaps strong word, more like mouse dragging and copy&paste. It just feels like refactoring code. I can move things around without worrying something disappears or gets forgotten. I can also leave things half finished, without negative effects on readability and discoverability.
I want my data checked into git, and directly accessible. I don't feel like custom schemas and database drivers, as a user, do anything but make the operational loop painful.
I can quickly use any mdast library/toolkits and some terrible shell scripts to make anything possible in moments.
But rather than having a self explanatory markdown & flat file, now I have to start learning about the schema & making specific tools (in my preferred language) for manipulating Joplin's schema.
Suddenly I'm digging through 20 different technic specs to decode what data is where, how it works, and what I can do to it. Want to edit history? This is the best help you'll get, pray it's adequately technical to expedite you to your purpose: https://github.com/laurent22/joplin/blob/dev/readme/dev/spec...
As I began with, I struggle to imagine anything that generates anywhere near as much user agency as flat files and markdown. Having boring common data & systems lets me apply portable skills I already have, rather than having to skill up in some particular product's own ecosystem.