My favorite one that I've had the chance to use professionally is the Marisa trie[0].
Context is a data scientist had written a service that essentially was just lookups on a trie. He'd left and the service was starting to have memory problems so I dug in and swapped the implementation. Iirc swapping the trie implementation changed memory usage from 8gb to 100mb and sped everything up as well.
The actual data structure is equivalent to a trie, but cannot be modified once it's been built (I think it may be the same as a LOUDS trie, I don't remember the specifics)
Context is a data scientist had written a service that essentially was just lookups on a trie. He'd left and the service was starting to have memory problems so I dug in and swapped the implementation. Iirc swapping the trie implementation changed memory usage from 8gb to 100mb and sped everything up as well.
The actual data structure is equivalent to a trie, but cannot be modified once it's been built (I think it may be the same as a LOUDS trie, I don't remember the specifics)
[0] https://github.com/s-yata/marisa-trie