What it is
Schema-free document database. Stores JSON-like BSON, scales horizontally with sharding, supports rich aggregation pipelines and now Atlas Vector Search for embeddings.
How Vaaani uses it
- Conversation history with arbitrary nested metadata
- RAG corpus storage with per-document permissions
- Atlas Vector Search to do RAG without a separate vector DB
- Event logs and audit trails for AI worker actions
Why it makes the cut
AI workloads are full of irregular, evolving JSON. Mongo lets you ship today and refactor schemas tomorrow without migrations.
Sample code
const { MongoClient } = require("mongodb"); const client = new MongoClient(uri); const chats = client.db("vaaani").collection("chats"); await chats.insertOne({ user, messages, created: new Date() });
Related in the Vaaani stack
Have a project that needs MongoDB?
30-min discovery call. You describe the busywork; I map it to an AI worker and a budget.