KiviDB debuts: a Redis-compatible in-memory and vector database
What happened
On October 19, 2026, Hacker News featured KiviDB, an open-source multithreaded in-memory database written in Rust. It is compatible with the Redis protocol and has built-in full-text and vector search. The project published KiviDB 1.1.0 benchmarks on a 32-core machine: pipelined GET throughput reached 21.2M ops/s, about 9x Redis 8 and 2.3x Dragonfly. The report notes these results depend on the specific environment and workload, and the comparisons match the project's published test conditions.
Written by AI from the coverage · updated 2 hours ago
Coverage
Follow the reports to see the story from different sides.
- Hacker News front pageShow HN: KiviDB, a faster Redis-compatible memory database and vector cache
KiviDB 是用 Rust 编写的开源多线程内存数据库，兼容 Redis 协议并内置全文与向量搜索。项目公布的 32 核测试中，KiviDB 1.1.0 的流水线 GET 吞吐为 21.2M ops/s，约为 Redis 8 的 9×、Dragonfly 的 2.3×，测试结果依赖环境与工作负载。
Heat over time
Not enough continuous observations to draw a trend yet.