If you are serious about transactionality, data consistency, and isolation levels, this sounds different from how you want to go. Both Firestore and Realm have shortcomings here. Fauna (where I work at, btw) and Surreal with FoundationDB on the backend, and Spanner are the only ones that can guarantee strict serializability in a distributed environment. I could argue that Fauna is the most turnkey (least pain to try, test, implement). With those "strict serializable" db's it is much easier to avoid data anomalies, as the ones mentioned in this thread.
Yup! I doubt this project will naturally evolve into whatever you're describing. And that's ok! This project might help people who want to use SQLite like Firebase, with a similar API and experience but without letting network requests increase latency (see: https://news.ycombinator.com/item?id=31318708).
Addressing main points like implementing atomic transactions (read and write operation on a doc) seems warranted since it exists in Firebase as well.
