Kore: Binary File Format Optimized for Modern Data Systems (Open Source)

KORE is an open-source columnar binary file format and distributed data processing engine written in Rust that significantly outperforms existing systems, achieving 59x faster query speeds than DuckDB and 84x faster than Apache Spark on benchmarked workloads. The format offers zero dependencies, CRC32 integrity checking, SDKs for 8 programming languages, and uses 57% less memory than Spark while eliminating JVM startup overhead. KORE is designed as a modern alternative to Parquet and Arrow, with particular advantages for aggregation and filtering operations on large datasets.