✋ Stop juggling API keys for AI apps. An AI gateway gives you one API for all the models your AI applications need, including chat, speech, embeddings, rerankers, and more. Voyage AI by MongoDB state-of-the-art embedding models and rerankers are now on major AI gateways such as OpenRouter, LiteLLM AI Gateway, and Vercel AI gateway. So now you can embed, rerank, and generate LLM responses using one API.
MongoDB
Software Development
New York, NY 947,370 followers
MongoDB is the intelligent data platform for the AI era.
About us
Headquartered in New York, MongoDB's mission is to empower innovators to create, transform, and disrupt industries by unleashing the power of software and data. Built by developers, for developers, our modern database platform is a database with an integrated set of related services that allow development teams to address the growing requirements for today's wide variety of modern applications, all in a unified and consistent user experience. MongoDB has tens of thousands of customers in over 100 countries. The MongoDB database platform has been downloaded hundreds of millions of times since 2007, and there have been millions of builders trained through MongoDB University courses. To learn more, visit mongodb.com.
- Website
-
http://www.mongodb.com
External link for MongoDB
- Industry
- Software Development
- Company size
- 5,001-10,000 employees
- Headquarters
- New York, NY
- Type
- Public Company
- Founded
- 2007
- Specialties
- open source, databases, mongodb, and software developer
Products
![Click here to view MongoDB]()
MongoDB
NoSQL Database Software
MongoDB’s modern database platform integrates all of the data services you need to build modern applications in a unified developer experience. It handles transactional workloads, app-driven analytics, full-text search, AI-enhanced experiences, stream data processing, and more, all while reducing data infrastructure sprawl and complexity.
Locations
Employees at MongoDB
Updates
-
This DB was all about Diwali Bash! 🪔 From diyas and decorations to mithai and masti, the MongoDB India team came together to celebrate the festival the desi way. A little festive sparkle, a lot of laughter, and the people who make it all worthwhile. Happy Diwali from MongoDB 💚 #LifeAtMongoDB
-
-
-
-
-
+2
-
-
Shopping is shifting from clicks and filters to conversations that AI agents have on a customer’s behalf. 🛍️🤖 Ask an AI assistant for “a carry-on that fits a 16-inch laptop and has strong sustainability credentials,” and it will pick products it can retrieve systematically, understand through rich context, and verify for consistency across surfaces. Bain estimates 30–45% of U.S. consumers already use AI answer engines to research products. For retailers, discoverability is now a product-data challenge. Ronan Conlon breaks down three priorities for an agent-ready catalog: 🛒 Enrich products with the context agents reason over: use cases, FAQs, substitutes, policies, and embeddings 💳 Treat every discovery surface (feeds, APIs/MCP, PDP structured data) as a projection of one live catalog 🧑💻 Combine keyword, vector, and hybrid retrieval to serve intent-based queries at agentic scale A catalog that’s rich in one channel but stale in another will lose to a simpler one that’s accurate everywhere. Read the blog: https://lnkd.in/eFWNAhj4
-
-
Developers can use MongoDB as the persistent memory store for applications and agents built with the Vercel AI SDK. ▲ The MongoDB Vercel AI SDK integration allows MongoDB to store the following types of memories: → Semantic: Agents can recall conversations, user preferences, and past events across sessions and restarts. → Episodic: Key events and outcomes, so an application can recall what happened before. Kept for one year of inactivity by default. → Scratchpad: Temporary notes that agents use for work in progress. These memories expire after an hour and can be promoted to episodic memory if needed. Developers can also retrieve relevant memories by meaning with MongoDB Vector Search, customize retention policies, and manage application data, all on MongoDB. Open source and generally available on npm. Blog, docs, and repo in the comments
-
-
MongoDB.local Mumbai brought together the people shaping what’s next in technology. 💚 From conversations on moving agents from pilot to production, to the unveiling of MongoDB 9.0, Atlas Infinite and Atlas Agent Engine, the event was packed with ideas, insights and innovation. We heard from customers including Kotak811, Piramal Finance, TATA AIG General Insurance Company Limited, IDBI Bank and NABARD - National Bank for Agriculture and Rural Development, got hands-on with the latest technologies, and connected with builders, partners and technology leaders from across the ecosystem. Thank you to everyone who was part of MongoDB.local Mumbai. Until we meet again!
-
MongoDB has been named a Leader in the IDC MarketScape: Worldwide Operational Databases 2026 Vendor Assessment. As agentic AI moves into production, IDC’s Devin Pratt describes the operational database as “the control point for enterprise AI,” where agents access and act on live business data. Learn how we're building with MongoDB Atlas Agent Engine: https://lnkd.in/eZuWFE24
-
-
MongoDB reposted this
MongoDB head of AI platform Chirag Shah explains why giving AI agents more memory can actually make them worse if they don't know what to forget: "Models are getting better every passing day. So if a model starts to struggle, it's because of data. Collectively, that's what context is." "Everything an agent does starts to become a memory, almost like a human memory. You move to another place, you have to decay that memory. If the agent retrieves an old memory, there's a very high chance the output is gonna be slop." "Zoom out further and the context is your institutional knowledge. Your files, your folders, your data in systems like SAP or Oracle."
-
"Last week I was at MongoDB Australia Developer Days, spending time with customers and the developers who build on the platform every day. Their questions were sharper, and more honest, than anything I hear in a roadmap meeting. A few of those conversations changed how I think about this new world of AI and data. What stayed with me: 1. The best insight came from listening, not presenting. 2. Developers care about what works at 2 a.m., not what looks good in a demo. 3. Showing up in person builds a trust that a call, however well-muted, does not. 4. Wherever you go, developers today have similar concerns and questions. Thank you to the team in Sydney for making a first trip feel easy and fun, and for sending me to stunning places I would not have found on my own." ✨Sejal Khanna, Senior Developer Advocate #LifeAtMongoDB
-
-
Markdown files are great for a second brain… until they aren’t. 👀 Joseph Morais caught up with Linda Haviv at MongoDB.local NYC on why a database is a must for agent memory and scalability.
-
Millions of AI agents. Billions of transactions. One connected internet-native payment ecosystem. Coinbase is building towards a future where AI agents can discover services and transact autonomously across the internet. Powered by MongoDB's multi-region architecture, hybrid search, and MongoDB 9.0's operational resilience, Coinbase can scale agentic payments while keeping its engineering team focused on what matters most: building. Coinbase and MongoDB are helping bring agentic payments to the mainstream. 💚 Andrew Reder Lincoln Murr
