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
- Section
- Platform-provider memory
- 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…
- Gemini Enterprise Agent Platform Memory Bank (rebrand of Vertex AI Memory Bank) vs Anthropic Claude Memory
- Gemini Enterprise Agent Platform Memory Bank (rebrand of Vertex AI Memory Bank) vs Google Gemini Memory
- Gemini Enterprise Agent Platform Memory Bank (rebrand of Vertex AI Memory Bank) vs Grok Memory (xAI)
- Gemini Enterprise Agent Platform Memory Bank (rebrand of Vertex AI Memory Bank) vs LinkedIn Cognitive Memory Agent
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