Journal
Notes from building LakehouseBox: what we measured, what we decided, and why. Every number here traces to a recorded run; roadmap is labelled as roadmap.
Why the world needs LakehouseBox
Agents already have compute and tools. What they lack is a shared place to keep analytical data between sessions. Why we built that as a managed Apache Iceberg service, and why we ended up running the storage ourselves, in Germany.
Does your agent need a data warehouse?
Start with the compute you already have. An agent running DuckDB and a set of shared Apache Iceberg tables are often enough to begin, and a managed warehouse remains the right choice for the workloads that need one.