Google ADK Memory
https://google.github.io/adk-docs/sessions/memory/
Google's Agent Development Kit. Session services: InMemory / Database / VertexAI. Long-term: InMemoryMemoryService or VertexAIMemoryBankService (uses Vertex AI Memory Bank Preview for persistent cross-session memory).
Active · Verified 2026-10-22 · fresh as of 2026-10-22 · 58 cited facts, 2 with a third-party source · 2 recorded changes · Suggest a correction
At a glance
- Type
- SessionService tiers + VertexAIMemoryBank vendor fix
- Tier
- T2
- Section
- Framework-embedded memory
- Created
- 2025-04 (launched at Google Cloud NEXT, April 9 2025) third-party fix
- Latest release
- v2.6.3 (2026-08-07) repo fix
- License
- Apache-2.0 repo fix
- Pricing
- ADK OSS free; Vertex AI Memory Bank and Agent Engine: consumption-based pay-per-use cloud pricing (serverless) vendor fix
- Funding
- Google (subsidiary of Alphabet); no independent funding vendor fix
- Freshness
- 2026-10-22 fix
- Layer
- agent-infra repo fix
- Licensing
- open-source repo fix
- SDK languages
- go, java, kotlin, python, typescript repo fix
- Protocols
- a2a, mcp-client vendor fix
- Developer activity
- OpenRank 39 (12-mo avg 56.21) · 235 participants — 2026-09 third-party fix
Memory taxonomy
- storage
- kv
- retrieval
- injection
- persistence
- cross-session
- update
- overwrite
- unit
- episode
- governance
- inspectable
- conflict
- overwrite
When to use
Optimised for: Google Cloud / Vertex AI integration
Anti-fit: not for non-GCP stacks
Pros & cons
Pros
Google's Agent Development Kit with memory built in; integrates cleanly with Vertex AI Memory Bank.
Cons
Google-cloud-tilted; less idiomatic outside GCP.
Claims & capabilities
Two MemoryService implementations: InMemoryMemoryService (keyword search, dev/test) and VertexAiMemoryBankService (managed Google Cloud Memory Bank; default for Agent Platform Runtime). Memory Bank intelligently extracts and stores conversation events as long-term "memories" retrievable by semantic query
Technical surface
- API surface
- SDK: Python + Java (MemoryService, SessionService interfaces)
- Backend storage
- pluggable (Vertex AI Memory Bank)
- Deployment
- Both (ADK OSS self-hosted; one-command deploy to Google Cloud Agent Engine / Cloud Run / GKE)
- Embedding model
- multiple supported
- Multi-tenancy
- namespace
- MCP
- native (first-party) — ADK MCP integration
- A2A
- supported (native) — ADK is A2A reference impl
- OpenTelemetry
- first-class — Cloud Trace / OTel
Alternatives to Google ADK Memory → live options ranked by shared design, licence, hosting and MCP support
Similar systems
Other framework-embedded memory in the catalog, ranked by inbound references.
- Spring AI ChatMemory T3
Wraps conversation memory behind an Advisor abstraction. MessageWindowChatMemory default 20-msg sliding window (preserves system messages); pluggable ChatMemoryRepository backends (in-memory, JDBC, Cassandra, Neo4j). Memory injected as cross-cutting concern at the ChatClient level.
- Flowise Memory T1
Discontinued: Flowise (acquired by Workday, Aug 2025) was sunset in 2026 — code freeze 2026-07-29, GitHub repo archived 2026-08-13, end of life 2026-08-31. Was a visual LangChain canvas with LangChain-native memory nodes (Buffer, Buffer Window, Conversation Summary Buffer) backed by an internal chat_message DB table; Buffer Window kept the last K interactions, Summary Buffer compressed older turns while keeping recent ones verbatim.
- LangGraph Persistence T2
Distinct from LangMem. Built-in checkpointer saves graph state per super-step (short-term, thread-scoped). Store System adds long-term hierarchical key-value memory across threads with optional vector search + TTL. Postgres / Mongo / Redis stores for production.
- AutoGen Memory T2
AutoGen's memory layer: ListMemory chronological context plus teachable agents that vectorise corrections; integrates with Mem0/Zep rather than building deep memory natively. Microsoft AutoGen is in maintenance mode (community managed, bug and security fixes only), and Microsoft points new projects to Microsoft Agent Framework.
- CrewAI Memory T2
Memory subsystem inside the CrewAI orchestration framework; integrates with Mem0 for the long-term tier.
- Hermes Agent memory (Nous Research) T3
Nous Research's open-source self-improving agent keeps an agent-curated MEMORY.md/USER.md notebook injected at session start, full-text (FTS5) search over past sessions that returns raw messages without LLM summarisation, and optional Honcho user modelling. one of the most-starred agent projects of 2026.
Sources (57 cited facts, 2 third-party)
Each fact links to the page it came from; the badge says who published it (how to read sources).
- What it is SessionService tiers + VertexAIMemoryBank vendor
- What it does & what's distinct Google's Agent Development Kit. Session services: InMemory / Database / VertexAI. Long-t… vendor
- Claims / benefits Two MemoryService implementations: InMemoryMemoryService (keyword search, dev/test) and … vendor
- Modalities text vendor
- Created 2025-04 (launched at Google Cloud NEXT, April 9 2025) third-party
- Latest release v2.6.3 (2026-08-07) repo
- License Apache-2.0 repo
- GitHub google/adk-python — ~21.1k stars, last commit 2026-08 repo
- Funding Google (subsidiary of Alphabet); no independent funding vendor
- Customers / scale Google enterprise customer base; no ADK-specific customer disclosures vendor
- Pricing ADK OSS free; Vertex AI Memory Bank and Agent Engine: consumption-based pay-per-use clou… vendor
- Compliance Inherits Google Cloud compliance: SOC 2, SOC 3, ISO 27001, HIPAA, PCI DSS, GDPR; IAM int… vendor
- Data handling Google Cloud data handling: end-to-end encryption; Vertex AI Memory Bank data stored in … vendor
- Deployment Both (ADK OSS self-hosted; one-command deploy to Google Cloud Agent Engine / Cloud Run /… vendor
- HQ US (Mountain View, CA — Google/Alphabet HQ) vendor
- Founders / pedigree Google DeepMind; corporate product vendor
- Memory volume / scale no scale claim vendor
- API surface SDK: Python + Java (MemoryService, SessionService interfaces) vendor
- Backend storage pluggable (Vertex AI Memory Bank) vendor
- Multi-tenancy namespace vendor
- Embedding model multiple supported vendor
- Namespace primitives per-tenant vendor
- Contradiction handling always overwrite (last-write-wins) vendor
- MCP support native (first-party) — ADK MCP integration vendor
- A2A support supported (native) — ADK is A2A reference impl vendor
- OTel first-class — Cloud Trace / OTel vendor
- Import / export JSON; Vertex AI Memory Bank backend vendor
- Integration count 1 vendor
- Orchestration both (single agent + multi-agent sub-agents/parallel flows) vendor
- Programmatic control full CRUD via Python SDK + REST vendor
- Pricing specifics ADK OSS free; Vertex AI Memory Bank + Agent Engine consumption-based pay-per-use (per-AP… vendor
- Agent abstraction multi-agent supervisor + ReAct vendor
- Memory primitives multiple (Session InMemory/Database/VertexAI + MemoryBank long-term) vendor
- LLM lock multi-vendor (Vertex/Anthropic/OpenAI via plugins) vendor
- Runtimes Python, Java vendor
- Session handling persistent thread (Memory Bank) vendor
- Validated verticals Google Cloud enterprise, Vertex AI agent developers vendor
- Time to running <10min (pip install google-adk + GCP key) vendor
- Anti-fit not for non-GCP stacks vendor
- Optimised for Google Cloud / Vertex AI integration vendor
- Adjacent infrastructure requires Google ADK; Vertex AI Memory Bank vendor
- Pros Google's Agent Development Kit with memory built in; integrates cleanly with Vertex AI M… vendor
- Cons Google-cloud-tilted; less idiomatic outside GCP. vendor
- Project & sources ADK memory docs Google Cloud blog Memory Bank quickstart vendor
- download-trajectory [{"ym":"2025-11","monthly":1021488,"cum":1021488},{"ym":"2025-12","monthly":2135648,"cum… registry
- cost-input-usd-per-mtok 0 vendor
- cost-output-usd-per-mtok 0 vendor
- cost-tier free vendor
- cost-pricing-model free-tier vendor
- cost-last-verified 2026-06-29 vendor
- architecture-deployment-locus hybrid vendor
- licensing-bucket open-source repo
- positioning-platform-vs-product platform vendor
- taxonomy-three-layer-rollup agent-infra repo
- developer-activity-opendigger {"activity":505.65,"as_of":"2026-09","openrank_12mo":56.21,"openrank_current":39,"partic… third-party
- sdk-languages go,java,kotlin,python,typescript repo
- protocol-support a2a,mcp-client vendor
What changed
Changes to this record's lifecycle, licence, release, pricing and hosting facts, from the catalog's git history. Subscribe (Atom)
- 2026-10-23
- Pricing “ADK OSS free; Vertex AI Memory Bank and Agent Engine: consumption-based pay-per-use cloud pricing (serverless); sta…” → “ADK OSS free; Vertex AI Memory Bank and Agent Engine: consumption-based pay-per-use cloud pricing (serverless)” source
- Compliance “Inherits Google Cloud compliance: SOC 2, SOC 3, ISO 27001, HIPAA, PCI DSS, GDPR; IAM integration, encryption in tra…” → “Inherits Google Cloud compliance: SOC 2, SOC 3, ISO 27001, HIPAA, PCI DSS, GDPR; IAM integration” source
- 2026-10-22
- License “not applicable — not OSS” → “Apache-2.0” source
- Latest release “not applicable — not OSS” → “v2.6.3 (2026-08-07)” source
Related systems
References (1)
- Vertex AI Memory Bank (now Agent Platform Memory Bank) integrates with — ADK memory docs document VertexAiMemoryBankService, a memory service backed by Vertex AI Memory Bank. (verified 2026-10-29)