We're using steemd to query the endpoints listed with condenser_api namespace. With hivemind, a sync process listens to the blockchain events and syncs related data into an RDBMS.
Which makes it a good alternative to use instead of steemd, directly. Also, since it's a relational database, there is a lot of potential for interesting SQL queries.
Currently, new endpoints are limited. They're listed on hive namespace on the root post. In the future, hive namespace may get bigger. (communities, extra calls, etc.)
Do you see a lot of progress is beeing made (as you probably checked out the github project) ?
The last touch to the indexer code related to communities was 6 months ago and the recent git history tells that the community features are not the focus at the moment.
Considering recent posts of @steemitblog, looks like they're focusing on moving away tag and follow api endpoints from steemd to hivemind. (Probably targeting a cost reduction on official RPC nodes.)
However, I have to add, this is just an educated guess from my side. The roadmap and plans may be different in Steemit inc.