MongoDB introduces AI features for production agents in Atlas

MongoDB has introduced new artificial intelligence features aimed at helping companies run AI agents in live production systems. [1] These additions combine data retrieval, memory and infrastructure updates on its database platform. [1] The rollout includes a long-term memory store for LangGraph.js, performance updates in MongoDB 8.3 and cross-region connectivity support for AWS PrivateLink. [1]

At the centre of the announcement is an effort to reduce the amount of separate infrastructure companies need to assemble when building AI applications. [1] Many businesses still rely on multiple systems to manage search, data updates, memory and operational workloads, making it harder to deploy AI agents at scale. [1] The updates are intended for organisations running AI workloads across public cloud, on-premises and hybrid environments. [1]

As part of the rollout, Automated Voyage AI Embeddings in MongoDB Vector Search is entering public preview. [1] The feature generates embeddings automatically when data is written or updated, helping AI systems retrieve more current information without requiring developers to build separate embedding pipelines. [1] Embeddings turn data into vectors so systems can find related information based on meaning rather than exact wording. [1]

Additionally, the LangGraph.js Long-Term Memory Store is now generally available. [1] It gives JavaScript and TypeScript developers persistent memory across conversations using MongoDB Atlas as the backend. [1]