OpenSearch Project Blog

Contact center customers shouldn't have to repeat themselves on every call. This post shows how OpenSearch agentic memory provides your AI agent with persistent memory across sessions. In this implementation, semantic and hybrid search retrieve relevant information on demand, so your agent remembers what matters.

The OpenSearch Project introduces a faster, smarter way to optimize your search experience. The OpenSearch Relevance Tuning Agent is designed to automate the heavy lifting for search relevance tuning, allowing you to move from "best guess" tuning to data-driven precision in a fraction of the time. OpenSearch Relevance Agent continuously analyzes user behavior signals and query patterns, generates data-driven hypotheses, and validates improvements through rigorous offline evaluation.

The OpenSearch Hadoop connector 2.0 adds Apache Spark 3.5 and 4 support, OpenSearch 3.x compatibility, Amazon OpenSearch Serverless support, and AWS SDK v2 migration.

Last week at OpenSearchCon Europe in Prague, the OpenSearch Project reached a milestone that many are calling a defining turning point. While the event was filled with news, from CERN joining the foundation to the release of OpenSearch 3.6, the headline that continues to make waves throughout the ecosystem is the official launch of the Long-Term Support (LTS) program.

Documents with tables, charts, and diagrams need more than text-based search. We benchmarked three multimodal document search approaches in OpenSearch on 1,000 report pages. ColPali late interaction reranking achieved the highest search quality (92% recall) but with higher latency, BDA modality-aware embedding offered a balanced middle ground, and text-only chunking was simplest to implement but scored lowest on visually rich content.

Day two of OpenSearchCon Europe in Prague ended the way the best conferences do: with something the community has been waiting for.

What a start to OpenSearchCon Europe in Prague. This morning's keynotes set the tone for what promises to be a great two days, and a few themes emerged that speak directly to where we are headed as a project and as a community.  

The OpenSearch Software Foundation is pleased to announce that CERN has joined as an associate member. The intergovernmental organization operates the world's largest particle accelerator and is responsible for landmark discoveries in particle physics, including the Higgs boson.

The OpenSearch Project introduces The Search Party — a new on-demand, community-driven video series replacing traditional community meetings. Get involved!

Learn how OpenSearch 3.5's new context management feature solves token limit issues for AI agents through intelligent summarization, sliding windows, and smart truncation. Build long-running agents that maintain conversation continuity without context overflow.

The OpenSearch Data Prepper maintainers are happy to announce the release of Data Prepper 2.15. With this version, you can ingest data from Apache Iceberg. This release also extends Prometheus...

At the 23rd Annual Southern California Linux Expo (SCaLE 23x), Navneet Verma and Naveen Taitkonda presented a session titled "OpenSearch: Your Friendly Neighborhood Vector Database." The session highlighted how OpenSearch’s vector search technology is powerful, approachable, and community-driven, making it a practical solution for everyday search challenges.

Modern search is growing rapidly as users demand natural, multimodal, and context-aware retrieval across massive unstructured data. At the same time, search is becoming exponentially more complex, evolving from simple...

Today, we are proud to welcome 10 new ambassadors, expanding the OpenSearch Ambassador Program and building on what this program has already helped us establish.

OpenSearch now offers native gRPC endpoints with Protocol Buffers, featuring an automated conversion pipeline from OpenAPI specifications. Benchmarks show up to 17% throughput improvement for vector search and 22% latency reduction for bulk ingestion compared to REST.

Learn how agentic search in OpenSearch performs across search relevance and execution accuracy benchmarks, achieving 82% query translation accuracy and up to 235% relevance improvements.

At the Linux Foundation Member Summit 2026 in Napa, CA, I had the pleasure of sitting down with James McIntyre, my colleague and chair of the Marketing Outreach Committee for the OpenSearch Software Foundation, for a fireside chat on search modernization and the role of the OpenSearch community in the era of agentic AI.

OpenSearch doc value skip indexes deliver up to 28x faster aggregations on uncorrelated filter and aggregation fields, overcoming key filter rewrite limitations.

Discover why AI agents fail in silence and how OpenSearch Agent Health solves it with open-source trace observability, automated benchmarking, and LLM judge evaluation.