MongoDB has unveiled new AI-focused capabilities designed to help enterprises run AI agents in production more efficiently and securely through its unified AI data platform. Announced at MongoDB local London 2026, the updates introduce native embeddings generation, persistent agent memory, real-time operational data handling, and enhanced database performance within a single platform. The company aims to eliminate the complexity of stitching together multiple AI infrastructure tools by combining vector search, memory, embeddings, reranker models, and operational databases into one environment.
Also Read: Blend Launches Mexico Hub, Expands AWS AI Partnership
New features include Automated Voyage AI Embeddings for real-time semantic search, the LangGraph.js Long-Term Memory Store for persistent cross-conversation memory, and MongoDB 8.3, which delivers significant performance improvements without requiring application changes. “The hardest part of running agents in production isn’t the model. It’s the data layer underneath it,” said CJ Desai, President and Chief Executive Officer of MongoDB. “To trust an agent at scale, it has to retrieve the right context, hold memory across sessions, and operate at machine speed, wherever the enterprise needs it.” MongoDB also reinforced its hybrid and multi-cloud deployment strategy to support regulated industries with stringent compliance and data residency requirements.