1. Architecture - XTDB is designed to work with Kafka, but it also works with typical JDBC databases as a datastore. Datomic can use SQL databases, DynamoDB or Cassandra if you want distribution. I personally would think long and hard before I introduced a distributed database to my organisation "because it scales".

Part of the value proposition of Datomic is it easily scales read workloads horizontally and by isolating read and writes into separate processes it improves write performance significantly. The metric usually thrown around is 75% of CPU cycles in a traditional RDBMS are concurrency coordination, which is avoided by the Datomic model. That number is quite old now so I don't know if it's still accurate as of 2023.

2. Query language - both use Datalog and support the Datomic `pull` syntax. XTDB also supports SQL.

3. Datomic's EAVT quadruplets are a compelling feature because they are so generic and can be used/re-used in many contexts. A document database would have to fit your use case pretty directly.

4. Datomic has a single transactor process. Do you need distributed transactions? Does Datomic need distributed transactions? You'd have to find someone from say, Nubank, and ask them for war stories. :-)

5. Datomic is now free-as-in-beer.

In my unqualified opinion XTDB is appropriate to choose in the following situations:

- You need to model "valid time" as part of your domain.

- Do you want a document database and are happy with everything that entails?

- You need access to the source code of your database.

- Do you have existing analysts who know SQL but don't know or can't learn Datalog?