What it is: Adaptive Capacity helps keep MongoDB Atlas clusters available during cloud provider capacity shortages by automatically using qualified fallback instance families when standard hardware is unavailable. It is designed to keep critical operations such as new cluster provisioning, and cluster tier scaling from being blocked by out-of-capacity errors, and it automatically returns clusters to standard hardware once capacity recovers.Who it’s for: This update is for DBA engineers, database practitioners, and cloud architects who need Atlas M30+ clusters on Azure to stay scalable and available even when regional cloud capacity is constrained.Why it matters: Cloud provider capacity shortages can block provisioning and scaling for days or even weeks, which customers experience as an Atlas availability problem. Adaptive Capacity reduces that risk by automatically using available fallback hardware instead of forcing teams to wait, rework infrastructure plans, or manually troubleshoot around cloud provider constraints. Atlas also applies workload health checks before moving to fallback hardware and avoids transitions when the active workload is too heavy, helping protect workload stability while still prioritizing availability during capacity events.How to get started: Adaptive Capacity is enabled by default for all existing and new M30 or higher Atlas clusters on Azure starting June 17, 2026 to reduce the impact of cloud provider shortages during supported Atlas provisioning and scaling workflows. Customers can opt-out through both the Atlas UI, Atlas CLI and Atlas Admin API. Terraform support is available on June 30, 2026.For more details, see Adaptive Capacity.

What it is: LangGraph.js now supports MongoDB as the backend for long-term agent memory, adding to the short-term memory (Checkpointers) already available. The MongoDB Memory Store keeps and retrieves cross-session data, with support for semantic memory search powered by either an client-side embeddings provider or MongoDB Atlas Automated Embeddings, which generates and indexes vector embeddings server-side via Voyage AI models.Who it's for: JavaScript and TypeScript developers building LangGraph agents and want a unified database for conversation history, long-term memory, and semantic search.Why it matters: MongoDB is now a first-class option at every layer of LangGraph.js memory. Teams already running on MongoDB can now keep agent memory in the same database as their operational data: no additional infrastructure for conversation state, long-term storage, or vector search. Semantic memory search lets agents retrieve memories based on meaning, surfacing past context that matches the current conversation. Automated Embeddings removes the last piece of friction: instead of provisioning and calling a separate embedding service, MongoDB handles vectorization server-side, keeping application code focused on agent logic.How to get started: See LangGraph.js Memory documentation for step-by-step examples covering MongoDB checkpointers, stores, and semantic search or head directly to our official tutorial.

What it is: The latest MongoDB version with security hardening, availability, and performance improvements, and expanded query expressions for native type coercion and string manipulations.Who it's for: Users looking for enhanced price-performance.Why it matters: MongoDB 8.3 delivers compounding efficiency gains: better performance per dollar, lower operational friction, and faster app development by optimizing core database fundamentals while adding new search, vector search, and query capabilities.How to get started: Upgrade your Atlas clusters to the latest version with Auto Upgrade or download the Enterprise Advanced and Community versions of MongoDB 8.3 from the MongoDB download center. Please check MongoDB 8.3 release notes for more details.