# OpenSearch version 3.6 release—smart agents and fast search
[Blog](/blog/)>[Technology](/blog/category/technical/)>OpenSearch version 3.6 release—smart agents and fast search
OpenSearch version 3.6 release—smart agents and fast search
===========================================================
April 10, 2026 | By [ Kassian Wren](https://www.instaclustr.com/blog/author/kassian-wren/)
[ ](https://x.com/intent/tweet?text=OpenSearch%20version%203.6%20release%E2%80%94smart%20agents%20and%20fast%20search&url=https://www.instaclustr.com/blog/opensearch-version-3-6-release-smart-agents-and-fast-search/) [ ](https://www.linkedin.com/shareArticle?mini=true&url=https://www.instaclustr.com/blog/opensearch-version-3-6-release-smart-agents-and-fast-search/&title=&summary=OpenSearch%20version%203.6%20release%E2%80%94smart%20agents%20and%20fast%20search&source=)
OpenSearch 3.6 is a major release that advances machine learning, vector search, neural search, and application performance monitoring. Key highlights include transparent token tracking for AI agents, 32x default vector compression via Lucene BBQ, a rebuilt AI chat experience in Dashboards, and a new APM solution built on OpenTelemetry.
**Quick Summary:** OpenSearch 3.6 makes AI-powered search more cost-transparent, memory-efficient, and production-ready—with significant upgrades to ML Commons, k-NN vector search, neural search, and OpenSearch Dashboards.
What Is OpenSearch 3.6?
-----------------------
OpenSearch 3.6 is the latest release of the open-source search and analytics engine maintained by the OpenSearch community. This release focuses on three primary areas:
- **AI agent capabilities** — token tracking, V2 Chat Agent, and semantic memory APIs
- **Vector search performance** — Lucene BBQ integration delivering 32x compression
- **Observability and dashboards** — a new APM solution and rebuilt AI chat interface
What’s New in OpenSearch 3.6? (Full Feature Breakdown)
------------------------------------------------------
### ML Commons: AI Agent Improvements
ML Commons is OpenSearch’s framework for integrating large language models (LLMs) and machine learning models directly within OpenSearch clusters. OpenSearch 3.6 delivers four major ML Commons upgrades.
**Agent Token Usage Tracking**
What it does: OpenSearch 3.6 adds transparent token usage tracking to the ML Commons agent framework—one of the most requested features from the community.
Previously, there was no visibility into how many tokens each agent execution consumed, making cost monitoring, performance debugging, and model comparison effectively impossible.
How it works in 3.6:
- Every LLM call during agent execution is instrumented to extract and aggregate token counts
- Works across all agent types in both streaming and non-streaming modes
- Gracefully handles providers that don’t return usage data
Token data is returned in two views:
ViewDescriptionPer-turn usageRecords for each LLM call (turn) within a single agent execution. Multiple turns for when an agent uses reason, tools, and then generates a final response.Per-model aggregationTotals per model ID including call countSupported LLM providers:
- Amazon Bedrock Converse
- OpenAI v1
- Gemini v1beta
Each provider’s fields are normalized into a unified TokenUsage model.
**Planned future enhancements:** Persistent token data storage, configurable per-agent token budgets, and extended tracking to non-agent model predict responses.
**Asynchronous Encryption Handling**
The `EncryptorImpl` class—responsible for encrypting and decrypting text using tenant-specific master keys—has been refactored for scalability.
The problem with the previous implementation:
- Used a blocking `CountDownLatch` with a strict 3-second timeout
- Caused thread contention under high concurrency
- Triggered unnecessary failures during cluster initialization delays
The new implementation (contributed by Muneer Kolarkunnu, Senior Engineer at NetApp Instaclustr):
- Replaces blocking behavior with a fully asynchronous, ActionListener-based approach
- Encryption and decryption requests are queued while the master key initializes
- Fixes a race condition where concurrent requests for the same tenant could trigger duplicate master key generation
**V2 Chat Agent**
OpenSearch 3.6 introduces the V2 Chat Agent, a next-generation agent type designed to simplify conversational AI workflows within ML Commons.
The V2 Chat Agent builds on the existing Conversational (ReAct) and PER agent types, providing a more streamlined interface for chat-based interactions while retaining the flexibility to integrate tools and memory.
**Semantic and Hybrid Search APIs for Long-Term Memory**
A new set of APIs brings semantic and hybrid search capabilities to long-term memory retrieval. Agents can now search stored memory using:
- Vector similarity (semantic search)
- Keyword matching (lexical search)
- Hybrid combinations of both
This enables more accurate and context-aware memory recall during multi-turn conversations—a foundational capability for agents that reason over large conversation histories.
### k-NN Vector Search: Compression, Speed, and Efficiency
**What Is Lucene Better Binary Quantization (BBQ)?**
Lucene Better Binary Quantization (BBQ) is a vector compression technique that encodes high-dimensional float vectors into compact binary representations using advanced quantization methods inspired by RaBitQ.
BBQ is now integrated into OpenSearch 3.6’s k-NN plugin and delivers a 32x compression ratio with significantly better recall than existing Faiss Binary Quantization.
**BBQ vs. Faiss Binary Quantization — Recall Comparison:**
DatasetLucene BBQ Recall@100Faiss BQ Recall@100Sift-1280.320.18Cohere-768-1M0.630.30With oversampling (rescoring), BBQ achieves recall above 0.95 at an oversample factor of 3 on the Cohere-10M dataset.
**How to configure BBQ in OpenSearch:**
Specify `"encoder": {"name": "binary"}` within the HNSW method parameters on the Lucene engine in your field mapping. Lucene’s built-in rescoring mechanism handles the two-phase search automatically:
- Fast candidate retrieval via binary quantized vectors
- Precise scoring using original FP32 vectors
**BBQ Flat Index Support**
OpenSearch 3.6 also introduces BBQ in flat mode—brute-force BBQ vector search for workloads where ingest efficiency, filtered search with high selectivity, and exact recall are priorities.
Configure flat mode by specifying `"method": {"name": "flat"}` with `"compression_level": "32x"` in your mapping.
**32x Compression as the Default**
OpenSearch 3.6 is working toward making **32x vector compression the default for the vector engine**. This initiative spans both Lucene and Faiss engines and includes:
- BQ-based indexing
- SIMD-optimized bulk operations
- Backward-compatible migration paths
The goal: dramatically reduce memory footprint out of the box without requiring manual compression tuning.
### Neural Search: Flexible Agentic Query Translation
**Embedding Model ID in the Agentic Query Translator Processor**
OpenSearch 3.6 decouples the embedding model from agent registration in agentic neural search workflows.
**The previous limitation:** The `embedding_model_id` was tightly coupled to the agent definition—requiring users to re-register agents whenever they switched embedding models.
**What’s changed in 3.6:** `embedding_model_id` can now be specified as an optional parameter directly in the `agentic_query_translator` search processor within the search pipeline configuration:
{ "request\_processors":\[ { "agentic\_query\_translator": { "agent\_id":"my-agent-id", "embedding\_model\_id":"my-embedding-model-id" } } \] }
1
2
3
4
5
6
7
8
9
10
{
"request\_processors":\[
{
"agentic\_query\_translator": {
"agent\_id":"my-agent-id",
"embedding\_model\_id":"my-embedding-model-id"
}
}
\]
}
This enables the same agent to be reused across different use cases with different embedding models—a meaningful improvement for teams managing multiple search pipelines.
### OpenSearch APM: Application Performance Monitoring
OpenSearch 3.6 introduces a comprehensive Application Performance Monitoring (APM) solution built on open-source technologies and OpenTelemetry standards.
CapabilityDescriptionRED MetricsRate, Errors, and Duration metrics for services and operationsService MapsInteractive topology visualization showing service dependenciesService-Level MonitoringDetailed performance metrics at service and operation levelsSLO TrackingService Level Objective definition and monitoringTrace ExpansionDeep-dive into distributed traces with log correlation**OpenSearch APM architecture**
ComponentRoleOpenSearchStores service topology, relationships, and trace dataPrometheusHandles time-series metrics (RED metrics)Data PrepperProcesses OpenTelemetry data and routes to appropriate backendsOpenSearch DashboardProvides visualization and analysis interfaceThis hybrid architecture routes each data type to the system optimized for it, achieving better performance and lower costs than a single-storage approach.
### OpenSearch Dashboards 3.6: AI Chat, Explore, and GenAI Observability
OpenSearch Dashboards 3.6 is one of the most feature-dense Dashboards releases to date, with three primary themes.
**AI Chat: Persistent Conversations and Agentic Memory**
The Dashboards chatbot interface has been rebuilt around a single-window architecture. New capabilities include:
- **Conversation history** — Browse, restore, and resume past conversations from a history panel
- **Agentic memory provider** — Chat sessions backed by ML Commons Agent Memory APIs, with long-term memory that persists across sessions
- **Screenshot capture** — Attach a screenshot of the current dashboard page to a chat message, giving the AI visual context alongside text (auto-scaled to stay under the 8K pixel limit)
**Explore Plugin: ECharts Migration and PPL Enhancements**
The Explore plugin—OpenSearch Dashboards’ next-generation data exploration experience—receives major investment in 3.6:
- **ECharts migration** — Histogram charts migrated from elastic-charts to ECharts; all Vega-based visualizations replaced with ECharts
- **In-context visualization editor** — Create and edit visualizations directly within a dashboard without navigating away
- **PPL search result highlighting** — Matching terms highlighted in PPL query results
- **Backend PPL grammar for autocomplete** — Autocomplete now uses the backend PPL grammar bundle as its source of truth
- **`fetch_size` API for PPL** — Row limits enforced at the OpenSearch level rather than truncated client-side
- **Performance improvements** — Raw hits cached at module level; redundant saved object requests eliminated; large query result rendering bottlenecks addressed
- **Data table controls** — Toggle for cell text wrapping in the Explore data table
**GenAI Agent Traces**
A new agent\_traces plugin brings GenAI agent trace visualization into the observability workspace. The agent traces view includes:
- A metrics bar
- Discover-style data table
- Sorting controls
- Workspace support
This makes it practical to debug multi-step agent executions directly from the Dashboards UI
**Security: CSP Strict Mode**
OpenSearch Dashboards 3.6 adds support for Content Security Policy (CSP) strict enforcement mode, configurable via the csp.enable flag. The console worker was also updated to load from a URL rather than a blob to comply with strict CSP policies.
OpenSearch 3.6: Feature Summary Table
-------------------------------------
CapabilityDescriptionRED MetricsRate, Errors, and Duration metrics for services and operationsService MapsInteractive topology visualization showing service dependenciesService-Level MonitoringDetailed performance metrics at service and operation levelsSLO TrackingService Level Objective definition and monitoringTrace ExpansionDeep-dive into distributed traces with log correlation**OpenSearch APM architecture**
CategoryFeatureImpactML CommonsAgent token usage trackingCost monitoring and model comparisonML CommonsAsync encryption handlingScalability under high concurrencyML CommonsV2 Chat AgentSimplified conversational AI workflowsML CommonsSemantic/hybrid memory APIsContext-aware multi-turn conversationsK-NNLucene BBQ integration32x compression, better recall than Faiss BQk-NNBBQ flat index supportHigh-selectivity filtered searchk-NN32x default compressionReduced memory footprint out of the boxNeural SearchEmbedding model ID in processorReuse agents across multiple embedding modelsObservabilityOpenSearch APMEnd-to-end distributed system visibilityDashboardsPersistent AI chat + agentic memoryLong-term conversational contextDashboardsECharts migration + PPL enhancementsFaster, more consistent data explorationDashboardsGenAI agent tracesDebug multi-step agent executions in UIDashboardsCSP strict modeImproved security postureFrequently Asked Questions About OpenSearch 3.6
-----------------------------------------------
- What is the biggest new feature in OpenSearch 3.6? The most impactful features are Lucene Better? +
Binary Quantization (BBQ) for 32x vector compression and transparent agent token usage tracking in ML Commons—both directly addressing production-scale cost and performance challenges.
- Does OpenSearch 3.6 support token tracking for LLM agents? +
Yes. OpenSearch 3.6 introduces zero-configuration token usage tracking for all agent types in ML Commons, supporting Amazon Bedrock Converse, OpenAI v1, and Gemini v1beta out of the box.
- What compression ratio does OpenSearch 3.6 achieve for vector search? +
OpenSearch 3.6 achieves a 32x compression ratio using Lucene Better Binary Quantization (BBQ), with recall above 0.95 achievable via oversampling on large datasets like Cohere-10M.
- Is OpenSearch 3.6 available on the Instaclustr Platform? +
Instaclustr will be rolling out access to OpenSearch 3.6 on the Instaclustr Platform soon.
- What observability features does OpenSearch 3.6 add? +
OpenSearch 3.6 introduces a full Application Performance Monitoring (APM) solution built on OpenTelemetry, including RED metrics, service maps, SLO tracking, and distributed trace exploration.
### About the author
**[Kassian Wren](https://www.instaclustr.com/blog/author/kassian-wren/)** | Open Source Technology Advocate
Kassian specializes in open source technologies like OpenSearch and Cassandra. With over a decade of experience, they excel in creating impactful educational content across various formats and actively engage with the developer community through events, online platforms, and live presentations. Passionate about fostering knowledge-sharing, Kassian combines technical expertise with community-focused outreach to support and inspire developers worldwide.
![mail icon]()#### Get the latest articles for open sourceIn your inbox
### Related content
[ AI Search for OpenSearch is now generally available on the NetApp Instaclustr Managed Platform
Discover the latest OpenSearch AI feature release! Explore new capabilities, enhanced performance, and real-world applications. ...
](https://www.instaclustr.com/blog/ai-search-for-opensearch-is-now-generally-available-on-the-netapp-instaclustr-managed-platform/)
[ AI Search for OpenSearch®: Unlocking next-generation search
Unlock next-gen semantic and multimodal AI search with OpenSearch. Our managed platform simplifies AI-powered search for smarter, ...
](https://www.instaclustr.com/blog/ai-search-for-opensearch-unlocking-next-generation-search/)
[ Introducing AI Cluster Health: Smarter monitoring made simple
Simplify your cluster metrics analysis. Our AI-powered tool translates complex data into clear cluster health scores. Monitor ...
](https://www.instaclustr.com/blog/introducing-ai-cluster-health-smarter-monitoring-made-simple/)
×Sign upto ourNewsletter
-----------------------