Sub-millisecond extractive summarization with byte-identical Python and Rust implementations. The preprocessor that sits in front of the LLM call.
Standalone ingest-to-pgvector with a built-in chunker × embedder bakeoff. One YAML config = one end-to-end ingest cell. Python + Rust at parity.
Capture, replay, and compare PostgreSQL workloads. Validate config changes, migrations, and capacity plans with confidence.