Currently testing out Shiori. I have tried both it and Readeck on my Raspberry Pi 3B running 32-bit Raspbian ‘Bullseye’. From an installation and performance perspective, Shiori is easier: 32-bit binaries are available and its web interface is a bit more responsive. If you are not running a 64-bit version of the Raspberry Pi OS, you have to build Readeck yourself (which I successfully did).
The main attraction of Shiori over Readeck is that it has both a readable and archive view. The main downside for me is it lacks the read/unread feature of Readeck and Pocket (although that’s apparently something planned for future and in the meantime, it’s possible to workaround using tags).
Both have a browser extension to enable capturing pages that contain Javascript and do not gracefully degrade. Both also have an export-to-ebook function that may suit your e-reader.
Bottom line: if you have an RPi4 or later, then Readeck is probably want you want. If you’re running an older Pi, though, Shiori may be a better option.
Interesting, I hadn’t seen news about that Apple feature before… There seems to be a lot more press around Recall, which in turn amps up the amount of consumer attention and backlash.
That said (and I wouldn’t want Apple’s “semantic search” even if I had an Apple device), I’d still trust Apple more to manage the dataset securely compared to Microsoft. The Apple ecosystem is far more strictly controlled, whereas in Windows it’s more of a free-for-all (most people just used XP as an administrator, the UAC could be easily disabled on Windows Vista and 7, etc.). Especially with Microsoft’s move to put advertising in Windows 11 and complete lack of security measures in the initial version of Recall, it is very hard to trust Microsoft in this regard.