MariaDB on Wednesday said it was adding four new agent-focused capabilities to Enterprise Platform 2027, the latest version of its enterprise database platform, to help developers retrieve enterprise data faster, maintain agent memory across sessions, and reduce the cost and latency of repeated model queries.
These new capabilities include AI Retrieval, AI Plugins, Agent Memory, and Semantic Cache.
While AI Retrieval is designed to help agents access information from enterprise documents and live operational data through a single managed service, AI Plugins are designed to bring MariaDB-specific expertise into coding agents such as Anthropic’s Claude Code and OpenAI’s Codex, helping developers generate database-related code more accurately, the company said in a statement.
AI Retrieval also converts natural-language questions into read-only SQL queries, which MariaDB said would eliminate the need for developers to manually write queries for every request.
Agent Memory, meanwhile, provides agents with a persistent, in-memory store that allows them to retain information across sessions and resume tasks without having to rebuild their context each time, according to the company.
Semantic Cache, the fourth capability, is intended to reduce response times and AI inference costs by identifying semantically similar questions, even when phrased differently, and reusing previously generated answers instead of processing each query from scratch, MariaDB said.
AI retrieval simplifies data access, but raises reliability concerns
For developers, AI Retrieval can increase productivity, said Ashish Chaturvedi, executive research leader at HFS Research.
“Most RAG setups keep documents in a vector store and live records in the transactional database, with glue code deciding which to query and how to merge results. Putting both behind one managed service eliminates a component and a sync step, so agents read operational facts at the moment they are true,” Chaturvedi added.
That consolidation, in turn, for CIOs would mean reducing cost and complexity, particularly for MariaDB-centric enterprises, as it can retire a separate vector database and sync pipeline, shrinking licensing, operations, and the number of places sensitive data lives, Chaturvedi further said.
However, he cautioned that the natural-language-to-SQL capability could face reliability challenges when dealing with complex enterprise databases.
“Reliability is likely to drop with sprawling schemas, cryptic column names, complex joins, and business terms that lack documented definitions. If you ask for ‘active customers’ and the model has to guess what that means, it is likely to produce plausible but different numbers,” Chaturvedi said.
“The capability is likely to become dependable only when paired with curated business definitions and testing against real user questions,” he added.
AI plugins require oversight
Similarly, the AI Plugins capability is likely to boost developers’ productivity, said Michael Leone, principal analyst at Moor Insights and Strategy.
“Coding agents tend to write for the databases they know best, so teaching them MariaDB is smart. General models, typically, know standard SQL but still trip on MariaDB-specific syntax and newer features like vector search,” Leone added.
However, Chaturvedi cautioned that CIOs should not assume that database code generated by AI coding agents is inherently reliable or secure.
“AI-generated code should undergo the same review, testing and security scanning as code written by human developers, with particular attention to SQL injection risks, excessive database permissions and agent-proposed schema changes, which can be difficult to reverse,” he said.
“CIOs should also track which AI tools generate specific pieces of code to help development teams identify recurring errors and address weaknesses in their coding workflows,” he added.
Agent memory and caching bring efficiency, but add risks
Agent Memory and Semantic Cache, too, could also help enterprises improve the efficiency of AI agents, although both capabilities introduce considerations around data management and reliability.
While without Agent Memory, every agent session starts from scratch, wasting tokens and increasing the risk of inconsistent decisions in long-running processes, CIOs need to ensure that the memory is governed through clearly defined ownership, retention policies and access controls, as it could contain personal and commercially sensitive information subject to privacy regulations, Chaturvedi said.
“Outdated memory could also cause agents to act on incorrect information, such as superseded supplier terms or customer preferences. Enterprises would therefore need mechanisms to expire or correct stored information, isolate memory across users and protect it against deliberately planted false entries,” he added.
Similarly, Semantic Cache could
[…]
Content was trimmed to protect the source. Please visit the original article for the full text.
Read the original article:
MariaDB enhances agent development for its next-gen database platform