ShannonBase
A database for AI workloads built on MySQL, wire-protocol compatible, with ML training, LLMs, vector search, and RAG pipelines available in SQL.
ShannonBase aims to replace a stack of ETL pipelines, vector databases, and inference servers with one database, letting you train ML models, run LLMs, search vectors, and build RAG pipelines in SQL. It’s wire-protocol compatible with MySQL, so existing drivers, ORMs, and tools keep working.
It’s released under GPLv2, consistent with MySQL Community Server.
Community feedback
This space is for grounded, evaluable experience — versions used, environments, what you measured or observed, and how it behaves alongside other software. General impressions without supporting detail may be removed. Sign in to write one; posts are tied to a verified identity, not anonymous.