--- title: Introducing the MongoDB Google ADK Integration: Durable... description: MongoDB has released an integration with Google's Agent Development Kit (ADK) to give AI agents durable session and memory storage. It adds... canonical: https://daily.dev/posts/introducing-the-mongodb-google-adk-integration-durable-memory-for-agent-state-uacsoeofh twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: Introducing the MongoDB Google ADK Integration: Durable Memory for Agent State | daily.dev og:description: MongoDB has released an integration with Google's Agent Development Kit (ADK) to give AI agents durable session and memory storage. It adds... og:url: https://daily.dev/posts/introducing-the-mongodb-google-adk-integration-durable-memory-for-agent-state-uacsoeofh og:image: https://api.daily.dev/og/posts/UaCsOeofH.png og:image:alt: Introducing the MongoDB Google ADK Integration: Durable Memory for Agent State og:image:width: 1200 og:image:height: 630 og:locale: 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. # Introducing the MongoDB Google ADK Integration: Durable Memory for Agent State **[MongoDB](https://daily.dev/sources/mongo)** · 6 min read · 0 upvotes · 0 comments ## Summary MongoDB has released an integration with Google's Agent Development Kit (ADK) to give AI agents durable session and memory storage. It adds MongoDbSessionService for persisting sessions, events, and state, and MongoDbMemoryService for long-term memory with idempotent ingestion. A MongoDbToolset lets agents run vector and hybrid search over operational data, and MongoDB Vector Search leverages Voyage AI's embedding models, with hybrid search using the $rankFusion aggregation stage. The integration supports MongoDB Atlas and self-managed MongoDB 8.0+ for vector and hybrid search, and installs via 'pip install google-adk[mongodb]'. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Questions this post answers ### How do I give a Google ADK agent persistent memory across sessions using MongoDB? Use the MongoDbSessionService and MongoDbMemoryService classes from google.adk.integrations.mongodb. MongoDbSessionService persists sessions, events, and app/user/session-scoped state, with optimistic concurrency control for safe concurrent updates. MongoDbMemoryService ingests session events into MongoDB collections and recalls relevant memories via keyword matching, with idempotent ingestion to avoid duplicates. Install with 'pip install google-adk[mongodb]'. _daily.dev surfaces integration guides like this for developers wiring durable memory into AI agents._ ### Which MongoDB versions support vector and hybrid search for AI agent tools? MongoDB Atlas and self-managed MongoDB 8.0+ deployments support vector and hybrid search for the Google ADK integration. Hybrid search combines vector search with full-text search using the $rankFusion aggregation stage, and configuration options like index names, embedding fields, limits, and candidate counts are set through MongoDbToolSettings. _Developers picking a search stack for agent retrieval can track MongoDB version requirements on daily.dev._ ### What embedding models does MongoDB's agent memory and search integration use? The integration uses Voyage AI's embedding models, the same engine that powers MemoryService's semantic retrieval. These models back MongoDB Vector Search, which agents can combine with full-text search for hybrid retrieval over operational data like product catalogs and documents. _daily.dev helps developers comparing embedding providers for agent retrieval stay current._ ## Similar posts on daily.dev - [MongoDB as a Vector Database for AI Agents-MongoDB](https://daily.dev/posts/mongodb-as-a-vector-database-for-ai-agents-mongodb-jj4bzmqm1) · Foojay.io · 1 upvotes · 1 comments - [Build a Database Memory Agent with MongoDB and Voyage](https://daily.dev/posts/build-a-database-memory-agent-with-mongodb-and-voyage-exrhtavef) · Daily Dose of Data Science \| Avi Chawla \| Substack · 1 upvotes · 0 comments - [MongoDB targets AI’s retrieval problem](https://daily.dev/posts/mongodb-targets-ai-s-retrieval-problem-fdiya16um) · InfoWorld · 0 upvotes · 0 comments - [Production-Ready Agents Need A Production-Ready Data Platform](https://daily.dev/posts/production-ready-agents-need-a-production-ready-data-platform-dc0scxrvt) · MongoDB · 1 upvotes · 0 comments - [MongoDB Launches Atlas Agent Engine to Put AI Agents in Production Without a New Stack](https://daily.dev/posts/mongodb-launches-atlas-agent-engine-to-put-ai-agents-in-production-without-a-new-stack-b9cahnswn) · SD Times · 0 upvotes · 0 comments --- Tags: [#python](https://daily.dev/tags/python), [#ai-agents](https://daily.dev/tags/ai-agents), [#mongodb](https://daily.dev/tags/mongodb), [#vector-search](https://daily.dev/tags/vector-search) [View this post on daily.dev](https://daily.dev/posts/introducing-the-mongodb-google-adk-integration-durable-memory-for-agent-state-uacsoeofh) ```json {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]} {"@context":"https://schema.org","@type":"TechArticle","headline":"Introducing the MongoDB Google ADK Integration: Durable Memory for Agent State","url":"https://daily.dev/posts/introducing-the-mongodb-google-adk-integration-durable-memory-for-agent-state-uacsoeofh","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/introducing-the-mongodb-google-adk-integration-durable-memory-for-agent-state-uacsoeofh"},"datePublished":"2026-11-04T15:30:10.151Z","dateModified":"2026-11-04T15:30:40.698Z","description":"MongoDB has released an integration with Google's Agent Development Kit (ADK) to give AI agents durable session and memory storage. It adds...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/3334c91bd8eaf519d58c82578c1eed52?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/3334c91bd8eaf519d58c82578c1eed52?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"MongoDB","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"MongoDB","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/90cb2b5f385a4e56b48181293e6d12e5","url":"https://daily.dev/sources/mongo"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/introducing-the-mongodb-google-adk-integration-durable-memory-for-agent-state-uacsoeofh","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"python,ai-agents,mongodb,vector-search","timeRequired":"PT6M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"MongoDB","item":"https://daily.dev/sources/mongo"},{"@type":"ListItem","position":3,"name":"Introducing the MongoDB Google ADK Integration: Durable Memory for Agent State"}]} {"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/introducing-the-mongodb-google-adk-integration-durable-memory-for-agent-state-uacsoeofh#faq","mainEntity":[{"@type":"Question","name":"How do I give a Google ADK agent persistent memory across sessions using MongoDB?","acceptedAnswer":{"@type":"Answer","text":"Use the MongoDbSessionService and MongoDbMemoryService classes from google.adk.integrations.mongodb. MongoDbSessionService persists sessions, events, and app/user/session-scoped state, with optimistic concurrency control for safe concurrent updates. MongoDbMemoryService ingests session events into MongoDB collections and recalls relevant memories via keyword matching, with idempotent ingestion to avoid duplicates. Install with 'pip install google-adk[mongodb]'. daily.dev surfaces integration guides like this for developers wiring durable memory into AI agents."}},{"@type":"Question","name":"Which MongoDB versions support vector and hybrid search for AI agent tools?","acceptedAnswer":{"@type":"Answer","text":"MongoDB Atlas and self-managed MongoDB 8.0+ deployments support vector and hybrid search for the Google ADK integration. Hybrid search combines vector search with full-text search using the $rankFusion aggregation stage, and configuration options like index names, embedding fields, limits, and candidate counts are set through MongoDbToolSettings. Developers picking a search stack for agent retrieval can track MongoDB version requirements on daily.dev."}},{"@type":"Question","name":"What embedding models does MongoDB's agent memory and search integration use?","acceptedAnswer":{"@type":"Answer","text":"The integration uses Voyage AI's embedding models, the same engine that powers MemoryService's semantic retrieval. These models back MongoDB Vector Search, which agents can combine with full-text search for hybrid retrieval over operational data like product catalogs and documents. daily.dev helps developers comparing embedding providers for agent retrieval stay current."}}]} ```