---
title: "Discussion on \"Introducing Iceberg DB: India's Serverless Vector Database & AI Agent Memory Engine (<20ms Latency)\" | Hashnode"
description: "Discussion on \"Introducing Iceberg DB: India's Serverless Vector Database & AI Agent Memory Engine (<20ms Latency)\". While building RAG pipelines and autonomous AI agents in India, I kept hitting the same three walls with US-hosted vector databases:\n\n200ms+ Network Latency: Every vector search from India to us-east-"
url: "https://hashnode.com/posts/introducing-iceberg-db-india-s-serverless-vector-database-ai-agent-memory-engine-20ms-latency/6ad830279d113e0cb5f9c9a9"
---

[Feed](https://hashnode.com/feed) /

Discussion

# [Introducing Iceberg DB: India's Serverless Vector Database & AI Agent Memory Engine (<20ms Latency)](https://icebergdb.hashnode.dev/introducing-iceberg-db-india-s-serverless-vector-database-ai-agent-memory-engine-20ms-latency?utm_source=hashnode&utm_medium=feed)

While building RAG pipelines and autonomous AI agents in India, I kept hitting the same three walls with US-hosted vector databases: 200ms+ Network Latency: Every vector search from India to us-east-

Oct 21 · 2 min read · icebergdb.hashnode.dev  
Read the article

-   [#ai](https://hashnode.com/tag/ai)
-   [#python](https://hashnode.com/tag/python)
-   [#database](https://hashnode.com/tag/database)
-   [#vector-database](https://hashnode.com/tag/vector-database)

## Written by

[iceberg](https://hashnode.com/@icebergdb)

@icebergdb · Mumbai, India

  
[View profile](https://hashnode.com/@icebergdb)

India's Serverless Vector Database & 4-Tier AI Agent Memory Engine (<20ms latency) — https://icebergdb.in

Iceberg DB is India's Serverless Vector Database &amp; 4-Tier AI Agent Memory Engine hosted in Mumbai (ap-south-1) with sub-20ms query latency. Try it free at https://icebergdb.in

## Responses

Markdown supported · ⌘↵ to post

No responses yet.