GemDB has launched GemDB Code free Visual Studio Code extension that delivers database where code is schema when developer or AI coding agent creates or modifies object and commits it object persists as-is with full ACID transactional guarantees no translation layer no separate migration step no second production release to coordinate significant improvement for both experienced engineering teams shipping production software and growing number of builders using AI coding assistants.
AI coding agents are rewriting application logic faster than traditional databases can absorb changes recent analyst reports found AI can accelerate coding by 30-40% yet overall team productivity often rises less than 10% when downstream steps remain manual because bottlenecks simply move those bottlenecks increasingly center on database.
"The object database category has been largely dormant for a decade, but the conditions that held it back have changed," said Brad Shimmin, Vice President & Practice Lead, Data Intelligence, Analytics, & Infrastructure at Futurum. "AI coding agents are exposing the schema migration bottleneck in ways that were theoretical even two years ago. GemDB is entering this moment with an in-process object database that provides full ACID guarantees and a production track record in financial services spanning three decades."
"Everything you can think of in a life insurance company that we could digitize and automate we put into GemDB," said Massimo Arnoldi, Founder, Member of the Board at Lifeware. "Policy administration, claims processing, underwriting workflows, agent compensation. All of it runs on objects that map directly to how our business actually works. We never had to flatten a life insurance contract into rows and columns, so our developers spent their time building insurance logic, not fighting with the database. When we need to change a product or add a rider, the code change is the only change."
"We've spent decades accepting a separation between code and data that was not inevitable," said Sandeep Parikh, Chief Product Officer, GemDB. "Any builder working with a coding agent eventually hits the same wall, where the agent writes application logic in minutes, but the database layer still expects manual coordination, migration scripts, and scheduled downtime. GemDB removes that wall entirely. When your objects are the database's objects, schema changes become code changes, and code changes are what AI agents do best."
Extension ships with built-in Jupyter Notebook kernel for interactive development against live database and MCP server that enables natural-language queries through any chat-based AI agent so developers can ask questions of data conversationally without writing formal queries. Also includes Brain Freeze Insurance guided sample application using simulated insurance scenario policyholders claims quotes for ice-cream-induced brain freeze to walk through object persistence querying schema evolution point of exercise what doesn't happen no migration script no production database to take down no join tables agent updates code schema already changed.
"AI coding agents are changing application code faster than any team can coordinate database updates to keep pace," said Kit Merker, CEO, GemDB and Operating Partner, Emergence. "Other approaches only give you better coordination. GemDB eliminates this need altogether by ensuring that when your agent changes the code, it has already changed the schema. There is no second step."
Availability
GemDB Code available today free download on VS Code Marketplace bundles scale-limited version of GemDB engine within extension everything needed to build run locally supports Python at launch additional language support planned licensed standalone editions GemDB Advanced Enterprise available for production workloads in 2027.
