Unlocking the power of agents requires memory. Just like human memory, a good agentic memory organizes knowledge. It helps agents retrieve the right knowledge based on context and learn to make smarter decisions and take optimized actions over time.
Speaking to investment analysts, he said that while MongoDB had all the elements needed to be the right foundational platform for AI workloads, it was too early to say what might be the platform of choice. However, he said MongoDB had been winning work from AI-native companies, citing a customer that recently "switched from PostgreSQL to MongoDB because PostgreSQL could not just scale."
Autocomplete seems like one of the easiest features to build. You take the user's input, loop through your list of options, and filter anything that starts with the same prefix: const matches = words.filter(w => w.startsWith(prefix)); And that works for small lists of text. But once your dataset gets large, or your completions come from structured text (like user.address.city or $gte), simple loops start to fall short.
Developers can now use search and vector search functionality in MongoDB Community Edition and Enterprise Server. These capabilities were previously only available in the Atlas cloud service. During the MongoDB.local NYC conference, MongoDB announced that search and vector search will be available for local installations. The previews are intended for development and testing. Until now, developers and organizations that wanted to use these features had to rely on the fully managed MongoDB Atlas cloud service.
