MongoDB has introduced a suite of new capabilities at its MongoDB local London 2026 event, aimed at simplifying the deployment of AI agents in production environments. By integrating a real-time database, full-text and vector search, memory, and embeddings into a single unified AI data platform, the company seeks to eliminate the need for enterprises to manage fragmented systems. This strategic move addresses the complexities of the data layer, which remains a primary challenge for scaling reliable AI agents.
MongoDB announces a unified AI data platform to support agentic workflows in production.
Automated Voyage AI Embeddings enter public preview to provide real-time context for vector search.
LangGraph.js Long-Term Memory Store is now generally available for JavaScript and TypeScript developers.
MongoDB 8.3 delivers significant performance gains, including up to 45% faster reads and 35% more writes.
New cross-region connectivity for AWS PrivateLink enhances security and data residency compliance.
The platform ranks #1 on the Retrieval Embedding Benchmark (RTEB) for search accuracy.
A core focus of the update is the accuracy of information retrieval. With the public preview of Automated Voyage AI Embeddings in MongoDB Vector Search, embeddings are generated automatically as data is modified. This automation removes the manual infrastructure hurdles that typically delay the implementation of semantic search. According to the company, these models currently lead the Retrieval Embedding Benchmark (RTEB), ensuring agents can access the most relevant context at machine speed.
Furthermore, the general availability of the LangGraph.js Long-Term Memory Store allows developers using JavaScript and TypeScript to maintain persistent memory across conversations. This parity with Python development environments ensures that agents can learn and improve over time without requiring additional database backends.
"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. That's why AI-native companies like ElevenLabs build voice agents on MongoDB, and why institutions like Lloyds Banking Group trust it for mission-critical workloads."
The launch of MongoDB 8.3 introduces substantial performance improvements without requiring changes to existing application code. The update boasts a 45% increase in read performance and a 30% increase in complex operations compared to version 8.0. These enhancements are designed to meet the sub-100ms retrieval requirements of high-scale users such as Adobe.
"When AI tools and agents produce a wrong answer, the instinct is to blame the model," said Pablo Stern, Chief Product Officer, AI and Emerging Products at MongoDB. "But the data platform is what enables the agent with the right context and memory to act correctly. With MongoDB, we've made this easy. Developers no longer have to build and maintain data infrastructure, wire up embeddings, or manage syncing between systems. They can focus on business outcomes rather than the plumbing."
To address the stringent data residency and security needs of the banking and healthcare sectors, MongoDB has expanded its deployment options. The general availability of cross-region connectivity for AWS PrivateLink ensures that traffic between MongoDB Atlas clusters remains within the AWS private network. This feature allows global organizations to scale their architectures while maintaining high security standards and avoiding the public internet.
Ben Cefalo, Chief Product Officer, Core Products at MongoDB, noted: "The requirements of enterprises running AI at scale are what we build for. MongoDB 8.3 makes agent workloads faster and cheaper to run on infrastructure customers already have. We've moved common data transformations into the database itself, so teams no longer have to maintain external pipelines just to feed their agents. Production AI doesn't wait, and neither do we."
The announcement solidifies MongoDB's position as a comprehensive solution for enterprises looking to move AI agents from experimental phases into mission-critical production environments across cloud and hybrid infrastructures.
About MongoDB
Headquartered in New York, MongoDB's mission is to empower innovators to create, transform, and disrupt industries with software. MongoDB's unified database platform was built to power the next generation of applications, and MongoDB is the most widely available, globally distributed database on the market. With integrated capabilities for operational data, search, real-time analytics, and AI-powered data retrieval, MongoDB helps organizations everywhere move faster, innovate more efficiently, and simplify complex architectures. Millions of developers and more than 65,200+ customers across industries – including ~75% of the Fortune 100 – rely on MongoDB for their most important applications.
TechIntelPro empowers B2B technology decision-makers with the latest industry trends, deep insights, leadership perspectives and actionable intelligence to drive both organizational and professional milestones—and thrive on the tech pulse.