Vertex AI Memory Bank

https://docs.cloud.google.com/agent-builder/agent-engine/memory-bank/quickstart-adk

Google Cloud managed memory service (Preview). Used by ADK's VertexAIMemoryBankService for cross-session persistent memory. Intelligently stores and retrieves memories from past user interactions.

At a glance

Type
Managed Vertex memory service
Tier
T2
Created
2025-07-08 (public preview announced)
Latest release
not applicable — not OSS
License
not applicable — not OSS
GitHub
not applicable — no GitHub repo
Pricing
Pay-per-use
Funding
Google/Alphabet public (GOOGL); market cap ~$2T

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

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

    Mounts memory as files on a managed filesystem; Claude reads and writes via the same bash/code-execution tools used for agentic tasks. Unit of storage is a file — inspectable, editable, exportable by developers. Full audit log per session. Memory beta launched April 23, 2026, two weeks after Managed Agents itself launched April 8.

  • Cloudflare Agent Memory T2

    Managed persistent memory service for AI agents on Cloudflare's edge. Beta-launched April 2026. Sits alongside Workers AI / Vectorize as the memory tier of the Cloudflare agent stack.

  • Gemini Enterprise Agent Platform Memory Bank (rebrand of Vertex AI Memory Bank) T1

    GA at Google Cloud Next 2026 (2026-04-22). Vertex AI rebranded as Gemini Enterprise Agent Platform; Memory Bank now "Agent Platform Memory Bank" with new continuous event-streaming + automated memory generation triggered by configurable criteria (event count or idle time). Backed by Agent Runtime that supports long-running agents that maintain state for days. Note: separate "Memory Profiles" feature reported in TheNextWeb but not surfaced in official Google Cloud release notes — treated here as unconfirmed.

  • Google Gemini Memory T1

    Personal Context setting + Personal Intelligence packing. Memory import from ChatGPT/Claude (Mar 2026).

Row last verified 2026-05-14. Catalog data is CC-BY-4.0 — see how to read this.