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

https://docs.cloud.google.com/gemini-enterprise-agent-platform/release-notes

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.

At a glance

Type
Long-running agent memory with continuous event-streaming consolidation
Tier
T1
Created
2025-07 (Vertex Memory Bank Preview); 2026-04-22 (GA + rebrand to Gemini Enterprise Agent Platform)
Latest release
not applicable — not OSS
License
not applicable — not OSS
GitHub
not applicable — no GitHub repo (managed cloud service)
Pricing
Pay-per-use (Vertex/Gemini Enterprise consumption-based)
Funding
Google/Alphabet public (GOOGL); ~$2T+ market cap

Taxonomy

storage
vector
retrieval
similarity
persistence
long-term
update
consolidation
unit
fact
governance
user-controllable
conflict
llm

When to use

Optimised for: long-running enterprise agents with continuous event-streaming consolidation; days-long state persistence; deep GCP IAM/CMEK/A2A integration

Anti-fit: not for non-GCP stacks; not for OSS/self-host requirements; not for users requiring full memory transparency (managed service)

Pros & cons

Pros

GA at Next 2026 with hardened operational story (event-streaming consolidation; long-running agents over days; A2A v1.2 in production); deep ecosystem integrations (Box/Workday/Salesforce/ServiceNow); first-class OTel + Cloud Trace observability.

Cons

GCP-only; Memory Profiles feature reported in TheNextWeb but not surfaced in official release notes (treated here as unconfirmed); pricing tied to Vertex consumption; smaller mind-share than AWS / Anthropic memory in OSS communities.

Claims & capabilities

Continuous event streaming with configurable consolidation triggers; agents maintain state for days

Technical surface

API surface
REST, gRPC, SDK: Python, Java, Node.js, Go
Backend storage
custom (Google-managed; Spanner-class backend)
Deployment
Managed cloud (GCP); on-prem option via open-source Gemma 4
Embedding model
multiple supported (Gemini text-embedding-004 + customer-supplied)
Multi-tenancy
hard-isolation (per-tenant + per-project)
MCP
via official adapter (ADK + managed MCP servers for Maps/BigQuery/Compute Engine/Kubernetes; Apigee bridge)
A2A
supported — A2A v1.2 production at 150 organizations; built into ADK/LangGraph/CrewAI/LlamaIndex
OpenTelemetry
first-class — Cloud Trace / OTel

Compare Gemini Enterprise Agent Platform Memory Bank (rebrand of Vertex AI Memory Bank) with…

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.

  • Google Gemini Memory T1

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

  • 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.

Related systems

References (2)

  • Google Gemini 3 family depends on at runtime — adjacent-infrastructure cell: requires GCP (Vertex AI / Gemini Enterprise); on-prem option via open-source Gemma 4; managed MCP servers; Pub/Sub + Cloud Trace + IAM
  • Model Context Protocol (MCP spec) depends on at runtime — adjacent-infrastructure cell: requires GCP (Vertex AI / Gemini Enterprise); on-prem option via open-source Gemma 4; managed MCP servers; Pub/Sub + Cloud Trace + IAM

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