New Delhi, September 30: MongoDB, Inc. today launched Atlas Agent Engine, a unified execution, memory, and governance layer for production AI agents, at its Investor Day at the Nasdaq MarketSite in New York City. While AI agents prove their value quickly in proof-of-concept testing, bringing them into production remains a major bottleneck. Doing so requires accurate retrieval, persistent memory, and enterprise-grade security and governance. Without a single platform, engineering teams must stitch together disparate tools that break every time underlying models or frameworks evolve. That’s what Atlas Agent Engine is designed to solve for.
At the center of this launch is MongoDB’s rapidly expanding Indian research and development (R&D) team, which has grown to approximately 110 engineers since launching 18 months ago. Working closely with colleagues in the U.S., Europe and Australia, the India engineering team has emerged as a primary center for the development of Atlas Agent Engine, as well as other core capabilities within MongoDB’s intelligent data platform for the AI era, including key pieces of MongoDB 9.0, which was also launched today.
Atlas Agent Engine is available today in public preview. New and existing Atlas customers can get started at agentengine.mongodb.com.
Atlas Agent Engine gives teams a modular way to put agents into production. Retrieval is powered by MongoDB Voyage AI, whose embedding and reranking models rank among the top performers on RTEB, a benchmark built to reflect real enterprise retrieval instead of academic datasets. Customers can adopt the memory and governance layers independently or with the runtime, using existing models and frameworks they know. Atlas Agent Engine is available today in public preview, with consumption-based pricing for Atlas Agent Runtime and Atlas Agent Memory. Usage draws on customers’ existing Atlas commitments, so adoption extends infrastructure already in place rather than requiring a new contract.
“Organizations that want to put agents in production are being forced into a false tradeoff: either adopt one vendor’s runtime and accept being locked into a model and cloud, or piece together a framework and manage governance and memory on their own,” said Pablo Stern-Plaza, Chief Product Officer, AI and Emerging Products, MongoDB. “With the launch of Atlas Agent Engine, that false tradeoff ends today. Enterprises get the real-time context their agents need, with governance and security built in from the start, and the freedom to run any model, any framework, and on any cloud. We didn’t want to ask customers to predict the future. We wanted to build something that works no matter what they choose.”
MongoDB’s Expanding Presence in India
MongoDB’s commitment to India represents a major long-term investment, with an overall regional footprint that has grown to more than 750 employees across Gurugram, Bangalore and Mumbai offices. While India has long been a critical hub for MongoDB’s regional business operations, last year the company launched a local engineering team to take advantage of the large talent pool in the market. The team has quickly evolved into a strategic global R&D engine, owning many critical pieces of MongoDB’s platform end-to-end and contributing in a co-ownership model to many other parts of the platform.
For example, three critical pieces of MongoDB’s global product strategy that the India team works on include:
- MongoDB Atlas Agent Engine: For the launch of Atlas Agent Engine, the India organization is taking on end-to-end product ownership of critical architectural components—working directly alongside U.S. and global peers.
- MongoDB 9.0 & Enterprise Resilience: Indian teams delivered key Enterprise Advanced capabilities for MongoDB 9.0, including mission-critical backup features.
- AI-Enabled Application Modernization Tooling: Indian teams are developing automated migration tools, AI-assisted code translation frameworks, and schema transformation utilities. These tools are designed to help global enterprises break free from rigid legacy relational databases, reduce technical debt, and accelerate their transition to MongoDB.
The expansion of the local engineering team mirrors MongoDB’s expanding enterprise presence in India, which includes 50 of the top 100 Indian companies by market capitalization. India’s fast-growing start ups, including more than 50 local unicorn companies, rely on the MongoDB platform. Additionally, the company plans to upskill another two million students by 2030.
Nitin Aggarwal, director of engineering, MongoDB said: “MongoDB operates at the absolute forefront of data and AI, building solutions for the extremely demanding and complex infrastructure challenges our customers face. The work our talented team does here directly impacts our largest, most mission-critical enterprise customers worldwide. I’m so proud of what we’ve already achieved in such a short time but as the team rapidly expands there’s a huge opportunity ahead for engineers in India to shape the future of software.”
Built to get agents into production
Enterprises building agents often run into the same three challenges: actions nobody can govern, agents that forget, and lock-in to a single model or framework. Atlas Agent Engine solves all three, grounded in the same operational platform that more than 70,000 customers already run on, with enterprises already building toward production.
Governed by default. Most platforms handle identity, audit, guardrails, and cost controls as separate systems teams have to stitch together themselves. Atlas Agent Engine puts it all behind one control plane: every action is logged against a real identity, human or agent, and governed by policy that can’t be quietly switched off. Governance is built in, not bolted on after launch. So when someone asks what an agent did and who authorized it, the answer takes seconds, not weeks. And because governance, memory, and retrieval run as one system instead of stitched-together services, there’s less to secure and fewer places for things to break.
Memory and retrieval built in. Without built-in memory, agents start every conversation from zero, and teams end up rebuilding memory infrastructure for every new agent. Atlas Agent Engine builds memory into the platform itself, using Voyage AI embeddings and MongoDB’s native retrieval, so agents get more accurate while spending fewer tokens.
Open design. Standardizing on one model, cloud, or framework is one of the riskiest infrastructure bets a leader can make in a market that moves this fast. Atlas Agent Engine is neutral across AI models and frameworks. Because it’s built on open standards like MCP and A2A, changing course later only takes a configuration change rather than an expensive rebuild. It will also run across any cloud, self-managed or even a laptop, so the same agent works everywhere without rebuilding cloud by cloud. Atlas Agent Engine adds governed execution, memory, and cost control on top of what teams already run, rather than asking them to replace it.
Atlas Agent Engine, MongoDB 9.0, and Atlas Infinite, also announced today, build on each other: MongoDB 9.0 strengthens the foundation every MongoDB customer already runs on, Atlas Infinite removes the limits on how that foundation can scale, and Atlas Agent Engine puts AI agents to work on top of both, governed and grounded in real-time data. Together with Voyage AI’s industry-leading embedding and retrieval models, already generally available, this extends MongoDB’s intelligent data platform for the AI era. To learn more about all three new launches and everything else MongoDB announced at Investor Day.
