MongoDB has announced a set of capabilities that add benchmark-leading retrieval directly into MongoDB's intelligent data platform. Today's capabilities include a new model in voyage-code-4, purpose-built for agentic code retrieval, now available through a standalone API to power any application.
MongoDB Atlas launches Automated Embeddings powered by Voyage AI models.
voyage-code-4 purpose-built for agentic code retrieval with lower cost.
Atlas Embedding and Reranking API available for any application.
Vector search in Atlas Stream Processing for real-time streaming data.
Financial Times and Eve using the platform for improved retrieval.
MongoDB serves ~75% of Fortune 100 and 67,000+ customers.
Retrieval accuracy determines what an AI application or Agent decides and what it costs to host. MongoDB is the memory and context layer that agents are built on. High-precision retrieval runs in the same platform as real-time operational data, not bolted on as a separate system that adds cost and synchronization overhead. An agent searches live data for context, including records written seconds earlier, so what it retrieves reflects the current state of the business rather than a stale copy.
Automated Embeddings in MongoDB Atlas powered by Voyage AI keep context current, embedding new documents as they are written and re-embedding existing ones when they change. The Atlas Embedding and Reranking API gives any application direct access to MongoDB's top-ranked embedding and reranking models. voyage-code-4 is a retrieval model tuned specifically for coding agents, matching information to code with higher precision and lower cost. Vector search in Atlas Stream Processing brings that same retrieval accuracy to data in motion.
"Too many organizations are running AI in production with an operational database, a vector store, a search engine, and embedding and reranking models, all from different vendors, bolted together instead of built for it," said Jim Scharf, Chief Technology Officer at MongoDB. "That's where stale data and errors creep in, and it's usually where teams spend their time babysitting instead of building. Agents raise the bar. They need to retrieve live context continuously and cannot wait on overnight batch jobs. MongoDB was built as an operational platform from the start, so retrieval and memory run on the same live data, nothing to sync, and agents act on what's happening instantly."
About MongoDB
Headquartered in New York, MongoDB's mission is to empower innovators to create, transform, and disrupt industries with software. MongoDB's unified database platform was built to power the next generation of applications, and MongoDB is the most widely available, globally distributed database on the market. With integrated capabilities for operational data, search, real-time analytics, and AI-powered data retrieval, MongoDB helps organizations everywhere move faster, innovate more efficiently, and simplify complex architectures. Millions of developers and more than 67,000 customers across industries—including ~75% of the Fortune 100—rely on MongoDB for their most important applications.
TechIntelPro empowers B2B technology decision-makers with the latest industry trends, deep insights, leadership perspectives and actionable intelligence to drive both organizational and professional milestones, and thrive on the tech pulse.
