Vertex AI Memory Bank (now Agent Platform Memory Bank)
https://docs.cloud.google.com/gemini-enterprise-agent-platform/scale/memory-bank
Google Cloud managed memory service, now 'Agent Platform Memory Bank' in Gemini Enterprise Agent Platform. LLM-based memory extraction/consolidation from sessions (background, multimodal, custom topics), per-identity isolation, similarity search, TTL, revisions; used from ADK via VertexAiMemoryBankService.
Renamed · Verified 2026-10-29 · fresh as of 2026-10-29 · 72 cited facts, 7 with a third-party source · 1 recorded change · Suggest a correction
At a glance
- Type
- Managed Vertex memory service vendor fix
- Tier
- T2
- Section
- Platform-provider memory
- Created
- 2025-07-08 (public preview announced) vendor fix
- Latest release
- not applicable — not OSS fix
- License
- not applicable — not OSS fix
- GitHub
- not applicable — no GitHub repo fix
- Pricing
- Pay-per-use vendor fix
- Funding
- Google/Alphabet public (GOOGL); market cap ~$2T vendor fix
- Freshness
- 2026-10-29 fix
- Layer
- agent-infra repo fix
- Licensing
- commercial vendor fix
- SDK languages
- python, rest vendor fix
Memory taxonomy
- storage
- vector
- retrieval
- similarity
- persistence
- cross-session
- update
- extraction
- unit
- fact
- governance
- opaque
- conflict
- none
When to use
Optimised for: GCP Vertex-native managed memory
Anti-fit: not for non-GCP stacks; Preview maturity
Pros & cons
Pros
Google Cloud-native managed memory with strong RAG integrations and enterprise governance posture.
Cons
GCP-only; pricing tied to Vertex; smaller mind-share than AWS / Anthropic memory.
Claims & capabilities
Google Cloud managed memory service (Public Preview 2025-07-08); used by ADK's VertexAIMemoryBankService for cross-session persistent memory; intelligently stores and retrieves memories from past user interactions; rebranded as Gemini Enterprise Agent Platform Memory Bank at Google Cloud Next 2026 (GA 2026-04-22)
Technical surface
- API surface
- REST, gRPC, SDK: Python, Java, Node.js, Go
- Backend storage
- custom (Google-managed)
- Deployment
- Managed-only
- Embedding model
- multiple supported
- Multi-tenancy
- hard-isolation
- MCP
- via official adapter (ADK)
- A2A
- supported — A2A native
- OpenTelemetry
- first-class — Cloud Trace / OTel
Alternatives to Vertex AI Memory Bank (now Agent Platform Memory Bank) → live options ranked by shared design, licence, hosting and MCP support
Similar systems
Other platform-provider memory in the catalog, ranked by inbound references.
- AWS Bedrock AgentCore Memory T2
AWS managed memory service for agents running on Bedrock AgentCore. Native integrations with LangChain/LangGraph and Strands. Drives long-running MCP servers + agent workloads.
- Anthropic Claude Memory T1
Memory tool API + consumer "Memory" feature + Auto Dream consolidation. Document-as-memory rather than extracted-fact-as-memory.
- Anthropic Managed Agents — Memory T3
Public-beta memory stores for Claude Managed Agents: workspace-scoped collections of text documents mounted into the session sandbox as a directory the agent reads and writes with its file tools; every change is versioned for audit and point-in-time restore, and memories can also be managed via API/Console.
- Cloudflare Agent Memory T2
Managed persistent memory service for AI agents on Cloudflare's edge. Private beta announced 2026-04-17. Sits alongside Workers AI / Vectorize as the memory tier of the Cloudflare agent stack.
- Google Gemini Memory T1
Gemini app learns from past chats via the Personal context setting (on by default, can be disabled; temporary chats excluded). Users can import memories and full chat history from ChatGPT, Claude and other assistants (18+, personal accounts, not EEA/CH/UK).
- Grok Memory (xAI) T1
Extracts and persists facts from past conversations; applies them to future responses. Per-memory deletion UI; user can also clear all. Announced by xAI's official Grok account on 2025-04-17 ('Grok now remembers your conversations').
Sources (71 cited facts, 7 third-party)
Each fact links to the page it came from; the badge says who published it (how to read sources).
- What it is Managed Vertex memory service vendor
- What it does & what's distinct Google Cloud managed memory service, now 'Agent Platform Memory Bank' in Gemini Enterpri… vendor
- Claims / benefits Google Cloud managed memory service (Public Preview 2025-07-08); used by ADK's VertexAIM… vendor
- Modalities text vendor
- Created 2025-07-08 (public preview announced) vendor
- Mindshare Google Cloud blog launch + Medium / VirtualizationReview / SiliconANGLE / techENT covera… vendor
- Funding Google/Alphabet public (GOOGL); market cap ~$2T vendor
- Customers / scale Payhawk (financial AI; 50%+ reduction in submission time), Gurunavi (UMAME! restaurant a… vendor
- Pricing Pay-per-use vendor
- Compliance SOC 2 Type II; ISO 27001; FedRAMP; HIPAA; GDPR-compliant vendor
- Data handling Never trains on customer data (Google Cloud commits no customer data training) vendor
- Deployment Managed-only vendor
- HQ US vendor
- Founders / pedigree Google DeepMind / Google Cloud corporate product (Sundar Pichai CEO; Thomas Kurian Googl… vendor
- Memory volume / scale no scale claim vendor
- Performance Customer case studies only (Danfoss 80% automation; Suzano 95% query reduction); no publ… third-party
- API surface REST, gRPC, SDK: Python, Java, Node.js, Go vendor
- Backend storage custom (Google-managed) vendor
- Multi-tenancy hard-isolation vendor
- Encryption at-rest + in-transit vendor
- SSO / RBAC SSO + RBAC (IAM) vendor
- Embedding model multiple supported vendor
- Versioning Audit-logged (Cloud Audit Logs) vendor
- Tombstoning hard-delete supported vendor
- Schema evolution schema with migration vendor
- Namespace primitives per-tenant vendor
- Contradiction handling LLM resolves and overwrites vendor
- Forgetting policy consolidation/summarization (event-count or idle-time triggered) vendor
- MCP support via official adapter (ADK) vendor
- A2A support supported — A2A native vendor
- OTel first-class — Cloud Trace / OTel vendor
- Webhooks / events event stream — Pub/Sub integration vendor
- Import / export JSON via REST; Vertex AI export vendor
- Orchestration both (long-running single agents; A2A v1.2 multi-agent in production at 150 organization… vendor
- Validated verticals Google Cloud enterprise vendor
- Time to running <1day (GCP project + Vertex AI Agent Engine) vendor
- Anti-fit not for non-GCP stacks; Preview maturity vendor
- Optimised for GCP Vertex-native managed memory vendor
- Adjacent infrastructure requires Vertex AI Agent Engine vendor
- Pros Google Cloud-native managed memory with strong RAG integrations and enterprise governanc… vendor
- Cons GCP-only; pricing tied to Vertex; smaller mind-share than AWS / Anthropic memory. vendor
- Project & sources Memory Bank quickstart vendor
- obs-langsmith yes third-party
- obs-opentelemetry yes vendor
- obs-datadog yes third-party
- obs-helicone yes third-party
- obs-weave yes third-party
- obs-langfuse yes third-party
- obs-arize yes third-party
- obs-custom Cloud Logging / Cloud Trace native for Vertex AI Agent Builder vendor
- cost-token-budget yes vendor
- cost-prompt-caching yes vendor
- cost-semantic-caching no vendor
- cost-batching yes vendor
- cost-model-routing no vendor
- cost-streaming-only yes vendor
- cost-observability-cost-attribution yes vendor
- eval-langsmith-evals no vendor
- eval-braintrust no vendor
- eval-weights-and-biases-agent no vendor
- eval-helicone-evals no vendor
- eval-custom-test-harness yes vendor
- eval-human-loop no vendor
- eval-production-traffic-replay no vendor
- cost-pricing-model subscription vendor
- cost-last-verified 2026-06-29 vendor
- architecture-deployment-locus cloud vendor
- licensing-bucket commercial vendor
- positioning-platform-vs-product platform vendor
- taxonomy-three-layer-rollup agent-infra repo
- sdk-languages python,rest 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
- Name “Vertex AI Memory Bank” → “Vertex AI Memory Bank (now Agent Platform Memory Bank)”
- Homepage “https://docs.cloud.google.com/agent-builder/agent-engine/memory-bank/quickstart-adk” → “https://docs.cloud.google.com/gemini-enterprise-agent-platform/scale/memory-bank”
Related systems
Referenced by (1)
- Google ADK Memory integrates with — ADK memory docs document VertexAiMemoryBankService, a memory service backed by Vertex AI Memory Bank. (verified 2026-10-29)