Loading post…
MongoDBAnnouncement
The Intelligent Data Platform for the AI Era
Summary
MongoDB announced the largest platform expansion yet, including MongoDB 9.0, Atlas Infinite, and Atlas Agent Engine. MongoDB 9.0 delivers up to 2x higher throughput, 35% faster reads, and 30% faster updates over version 8.0. Atlas Infinite is a new deployment option that allows storage and compute to scale independently, with time to scale more than 96% faster and each shard holding 10x more storage. Atlas Agent Engine provides built-in memory, retrieval, identity, and governance for production agents, operating on the same data platform as operational data. The company argues that as AI moves from generating answers to taking actions, the data layer must provide live, fresh, and retrievable operational data rather than separate AI infrastructure.
Context
The post argues that AI is moving from generating answers to taking actions, requiring agents to operate on live, fresh operational data rather than stale copies. Agentic workloads are bursty and stateful, demanding infrastructure that can scale compute and storage independently and provide memory, retrieval, and governance close to the data. MongoDB positions its platform to converge operational data and AI context, avoiding separate data architectures for AI.
Approach / What changed
MongoDB announced three major platform expansions: MongoDB 9.0 with up to 2x higher throughput, 35% faster reads, and 30% faster updates; Atlas Infinite, a new deployment option that allows storage and compute to scale independently with 96% faster time to scale and 10x more storage per shard; and Atlas Agent Engine, which provides built-in memory, retrieval, identity, and governance for production agents on the same data platform as operational data, open to any model, framework, or cloud.
Takeaways
MongoDB 9.0 offers up to 2x higher throughput on large instances, 35% faster reads, and 30% faster updates compared to MongoDB 8.0.
Atlas Infinite allows storage and compute to scale independently, with time to scale more than 96% faster and each shard holding 10x more storage.
Atlas Agent Engine provides built-in memory, retrieval, identity, and governance for agents, and is open to any model, framework, or cloud.
FAQ
What is Atlas Infinite?
Atlas Infinite is a new deployment option for MongoDB Atlas that allows storage and compute to scale independently, designed for highly elastic workloads. It offers more than 96% faster time to scale and each shard can hold 10x more storage, and customers can choose it alongside Atlas Core without rewriting applications.
How does Atlas Agent Engine help with agent state?
Atlas Agent Engine provides built-in memory and retrieval so agents can access relevant real-time context, and a unified control plane for identity and governance over agent actions. It operates on the same data platform as operational data and is open to any model, framework, or cloud.
What performance improvements does MongoDB 9.0 offer?
MongoDB 9.0 delivers up to 2x higher throughput on large instances, 35% faster reads, and 30% faster updates compared to MongoDB 8.0, significantly improving price-performance at scale.
Source and freshness
- Source
- mongodb.com
- Published
- Added to Yomu
Summaries are generated from the original by a language model. Check the original before relying on it.
Keep reading
Related reading
The Good Stuff
Paid picks we use ourselves. Links carry a referral code — a subscription through one earns us a commission at no extra cost to you.
The best engineering reads, once a week
One useful email. Unsubscribe anytime.