---
title: "What’s new in OpenSearch 3.8"
url: https://daily.dev/posts/what-s-new-in-opensearch-3-8-gykn55oja
source_url: https://opensearch.org/blog/whats-new-in-opensearch-3-8
type: article
source: "OpenSearch"
published: 2026-08-23T12:24:08.319Z
updated: 2026-08-23T12:51:12.494Z
tags: ["llm", "observability", "mcp", "vector-search", "opensearch"]
reading_time: 10
upvotes: 0
comments: 0
language: en
---

> ## Documentation Index
> Fetch the complete documentation index at: https://daily.dev/llms.txt
> Use this file to discover all available pages before exploring further.

# What’s new in OpenSearch 3.8

**[OpenSearch](https://daily.dev/sources/opensearch)** · 10 min read · 0 upvotes · 0 comments

## Summary

OpenSearch 3.8 brings faster vector ingestion via Base64 encoding (up to 4.16x throughput gain), a redesigned radial search algorithm delivering 2.1x higher query throughput and better recall, and expanded MCP support across all four agent types. LLM-as-a-Judge now works with any ML Commons connector instead of just OpenAI, and ML Commons streaming inference gains gRPC transport for lower latency. Observability gets a visual PPL query builder, SQL support in Discover logs, an onboarding canvas, new PPL commands (makeresults, foreach, xyseries, timewrap), a PPL lint engine, a Grok Debugger, and one-click alert creation from Prometheus metric exploration. Amazon Linux 2 support is being deprecated as a CI build image and supported OS in a future version.

## Full article

daily.dev links to this article rather than hosting it. Read it at the original source: <https://opensearch.org/blog/whats-new-in-opensearch-3-8>

## Questions this post answers

### How much faster is vector ingestion in OpenSearch 3.8 with Base64 encoding?

OpenSearch 3.8 delivers up to 4.16x higher bulk vector ingestion throughput using Base64-encoded knn_vector fields, with 83% lower median latency. A 768-dimensional float vector shrinks from about 16 KB as a JSON array to 4 KB in Base64, cutting network payload by 74%. It works transparently across all supported k-NN engines with no mapping changes required.

_Teams tuning vector search pipelines can track performance-focused releases like this one on daily.dev._

### Does OpenSearch 3.8 support MCP for all agent types?

Yes, OpenSearch 3.8 extends Model Context Protocol support to flow and conversational flow agents, meaning all four agent types (conversational, plan-execute-reflect, flow, and conversational flow) can now connect to external MCP-compliant tool servers using a consistent connector configuration. Previously only conversational and plan-execute-reflect agents supported MCP integrations.

_Engineers building agentic search workflows can follow MCP integration updates like this on daily.dev._

### When is Amazon Linux 2 support being deprecated in OpenSearch?

OpenSearch will deprecate support for Amazon Linux 2 as a continuous integration build image and supported operating system in a future version, though no exact version was specified. Amazon Linux 2 itself reached end of support from AWS on June 30, 2026, prompting the change.

_Ops teams planning OS migrations can watch for deprecation timelines like this on daily.dev._

## Similar posts on daily.dev

- [Inside OpenSearch’s bid to become the default AI data layer](https://daily.dev/posts/inside-opensearch-s-bid-to-become-the-default-ai-data-layer-2uzzh37ue) · The New Stack · 2 upvotes · 0 comments
- [Amazon OpenSearch Service now supports OpenSearch version 3.7](https://daily.dev/posts/amazon-opensearch-service-now-supports-opensearch-version-3-7-wkqtg7wcc) · AWS · 0 upvotes · 0 comments
- [OpenSearch 3.2 Delivers Hybrid Search, Enhanced Observability Tools](https://daily.dev/posts/opensearch-3-2-delivers-hybrid-search-enhanced-observability-tools-s3mdiz6on) · The New Stack · 2 upvotes · 0 comments

---

Tags: [#llm](https://daily.dev/tags/llm), [#observability](https://daily.dev/tags/observability), [#mcp](https://daily.dev/tags/mcp), [#vector-search](https://daily.dev/tags/vector-search), [#opensearch](https://daily.dev/tags/opensearch)

[View this post on daily.dev](https://daily.dev/posts/what-s-new-in-opensearch-3-8-gykn55oja)