For MariaDB, LLMs are the new search engines to win over

MariaDB has vector search built into its database, but the AI coding assistants developers rely on rarely say so. The MariaDB Foundation wants to close that gap, executive chairman Kaj Arnö said at Percona Live.

"We're so frustrated that the world doesn't understand that MariaDB has vectors," Arnö told The Register.

Vector search is ready, awareness is not

MariaDB was forked from MySQL in 2009 as Oracle's acquisition of Sun Microsystems loomed. The database supports vector search, which lets applications find items by similarity rather than exact matches — a common need in AI applications. The nonprofit MariaDB Foundation supports the open source server, while MariaDB plc develops the commercial products.

Arnö's concern is whether developers starting a new AI project will ever be pointed toward it. "People start using vector databases based on some framework or based on some default choices of the LLM," he said. "So if you do vibecoding and just sort of press enter when Claude Code suggests something, you will not end up using MariaDB for your vector search, and that is what we need to change."

From SEO to LLM optimization

Part of the problem lies in the material AI tools learn from: their training data may predate MariaDB's vector features.

"There are a million places where we need to update stuff so that the frameworks, the training data for the LLMs, and all of those know about the existence of MariaDB vectors," Arnö said.

The Register ran its own unscientific check: asked which database to use for vector search, Claude suggested PostgreSQL first and did not mention MariaDB at all. Asked to compare the two engines, it had plenty to say — it knew MariaDB's capabilities, it just did not volunteer them.

Arnö compares the situation to the early days of search engine optimization: "It was sort of a mystical science. Now the world has moved on to LLM optimization." That leaves a chicken-and-egg problem: without user-generated examples and discussions, AI tools have less material to learn from. "The early movers have an undue advantage," Arnö said, "and now we have to change that and make people aware of what we are doing."

Questions over Galera

The push to attract developers also raises a question about the community edition. Galera, the clustering technology used with MariaDB, has attracted controversy over its open source future and its place in the enterprise product line. Arnö draws a line: Galera "was not part of MariaDB's core engineering team to begin with" and was managed by an entity acquired by MariaDB plc, a commercial company that is not equal to MariaDB Server. "It's their freedom," he said. "What we protect is MariaDB server, and if anybody is messing with that, we would be quite upset!"