MongoDB, an intelligent data platform for AI applications, recently launched Atlas Agent Engine, an execution, memory and governance layer for production AI agents. Enterprise companies working to build AI agents are typically challenged by ungovernable actions, forgetful agents and a commitment to a single model or framework. MongoDB’s newest offering is designed to solve each of these issues and is currently available in public preview.
“Atlas Agent Engine offers a secure way of building, deploying and governing AI agents in production,” Deepa Gopinath, MongoDB’s CIO, wrote in a company blog post. “Because it has built-in memory and retrieval, Atlas Agent Engine indexes enterprise data where it lives and delivers precise context in real time, improving accuracy while cutting token costs. It’s also open and flexible by design, which means teams can build with the LLM and framework of their choice.”
The company’s India-based engineering team has been a primary center for developing Atlas Agent Engine, according to reporting by CXO Today. The R&D organization is taking on full product ownership of its critical architectural components and collaborating closely with teams in the U.S., Europe and Australia. The India R&D team was also integral to the development of MongoDB 9.0, the latest iteration of the intelligence engine underpinning MongoDB Atlas, which launched on the same day as the Atlas Agent Engine.
