Introducing memory retention for agentic memory in OpenSearch
OpenSearch

Introducing memory retention for agentic memory in OpenSearch


Summary

OpenSearch 3.8 introduces an experimental memory retention feature for agentic memory containers, allowing users to set age-based or count-based limits to automatically delete stale sessions, long-term memory, and history. This functionality helps reduce storage costs and maintains agent performance by preventing context degradation from outdated data. Additionally, the feature supports pinning important memories to prevent deletion and allows for configuring cluster-wide defaults for easier management across multiple containers.
Read the Original Article

This article originally appeared on OpenSearch.

Read Full Article on Original Site

Related Articles

NVIDIA Nemotron embeddings for agentic search in OpenSearch
NVIDIA Nemotron embeddings for agentic search in OpenSearch

Yuxuan Zong • Oct 21, 2026 • 2 shared categories

Climbing the ladder: Understanding OpenSearch’s Contribution Ladder policy
Climbing the ladder: Understanding OpenSearch’s Contribution Ladder policy

Andrew Ross • Oct 20, 2026 • 2 shared categories

Beyond Top-K: Building search-confidence guardrails for agentic AI with OpenSearch
Beyond Top-K: Building search-confidence guardrails for agentic AI with OpenSearch

Chanpreet Singh • Oct 16, 2026 • 2 shared categories

Explore OpenSearch logs in Perses with the new data source plugin
Explore OpenSearch logs in Perses with the new data source plugin

Akshay Iyyadurai Balasundaram • Oct 14, 2026 • 2 shared categories

Managing resource access from a plugin page in OpenSearch Dashboards
Managing resource access from a plugin page in OpenSearch Dashboards

Darshit Chanpura • Oct 2, 2026 • 2 shared categories

Popular from OpenSearch

1
Introducing the 2026-2027 OpenSearch Ambassadors
Introducing the 2026-2027 OpenSearch Ambassadors

Kylie Wagar-Dirks • Mar 31, 2026 • 243 views

4
Search modernization with OpenSearch: From Vector Search to Agentic AI
Search modernization with OpenSearch: From Vector Search to Agentic AI

Pallavi Priyadarshini • Mar 13, 2026 • 167 views

5
OpenSearch, Hybrid Vectors, and AI
OpenSearch, Hybrid Vectors, and AI

OpenSearch • Apr 1, 2026 • 165 views