Set up Memory Bank

Before you work with Vertex AI Agent Engine Memory Bank, you must set up your environment. Note that although Memory Bank is part of Agent Engine, you don't need to deploy your code to Agent Engine Runtime to use Memory Bank.

Set up your Google Cloud project

Every project can be identified in two ways: the project number or the project ID. The PROJECT_NUMBER is automatically created when you create the project, whereas the PROJECT_ID is created by you, or whoever created the project. To set up a project:

Sign in to your Google Cloud account. If you're new to Google Cloud, create an account to evaluate how our products perform in real-world scenarios. New customers also get $300 in free credits to run, test, and deploy workloads.

In the Google Cloud console, on the project selector page, select or create a Google Cloud project.

Go to project selector

Verify that billing is enabled for your Google Cloud project.

Enable the Vertex AI API.

Enable the API

In the Google Cloud console, on the project selector page, select or create a Google Cloud project.

Go to project selector

Verify that billing is enabled for your Google Cloud project.

Enable the Vertex AI API.

Enable the API

Get the required roles

To get the permissions that you need to use Vertex AI Agent Engine, ask your administrator to grant you the Vertex AI User (roles/aiplatform.user) IAM role on your project. For more information about granting roles, see Manage access to projects, folders, and organizations.

You might also be able to get the required permissions through custom roles or other predefined roles.

If you're making requests to Memory Bank from an agent deployed on Google Kubernetes Engine or Cloud Run, make sure that your service account has the necessary permissions. The Reasoning Engine Service Agent already has the necessary permissions to read and write memories, so outbound requests from Agent Engine Runtime should already have permission to access Memory Bank.

Set up your environment

This section assumes that you have set up a Python development environment, or are using a runtime with a Python development environment (such as Colab).

Install libraries

Install the Vertex AI SDK:

  pip install google-cloud-aiplatform>=1.104.0

Authentication

Authentication instructions depend on whether you're using Vertex AI in express mode:

• If you're not using Vertex AI in express mode, follow the instructions at Authenticate to Vertex AI.

• If you're using Vertex AI in express mode, set up authentication by setting the API key in the environment:

    os.environ["GOOGLE_API_KEY"] = "API_KEY"
  

Set up a Vertex AI SDK client

Run the following code to set up a Vertex AI SDK client:

import vertexai

client = vertexai.Client(
    project="PROJECT_ID",
    location="LOCATION",
)

where

• PROJECT_ID is your project ID.
• LOCATION is one of the supported regions for Memory Bank.

Configure your Agent Engine instance for Memory Bank

To get started with Memory Bank, you first need an Agent Engine instance.

You can do one of the following:

• Use an existing instance

• Create or update an Agent Engine instance: When you create or update an instance, you can override Agent Engine's defaults to make the following modifications to the instance:

  • Set the configuration for how Memory Bank generates and manages memories.

  • Deploy your agent to Agent Engine Runtime.

Use an existing instance

If you don't need to modify an existing Agent Engine instance, run the following to configure the instance for Memory Bank:

agent_engine = client.agent_engines.get(name="AGENT_ENGINE_NAME")

Replace the following:

• AGENT_ENGINE_NAME: The name of the Agent Engine. It should be in the format projects/.../locations/.../reasoningEngines/.... See the supported regions for Memory Bank.

You can use the instance in any environment, including Google Kubernetes Engine and Cloud Run. To get started, you need the Agent Engine name that identifies the Memory Bank and sufficient permission to call Memory Bank.

Create or update an instance

  agent_engine = client.agent_engines.create()

  agent_engine = client.agent_engines.update(
        # If you have an existing AgentEngine, you can access the name using `agent_engine.api_resource.name`.
        name="AGENT_ENGINE_NAME",
        # Optional. Set this argument if you want to deploy to Agent Engine Runtime.
        agent_engine=...,
        # Optional. Set this argument if you want to change the Memory Bank configuration.
        config=...
  )

Set your Memory Bank configuration

You can configure your Memory Bank to customize how memories are generated and managed. If the configuration is not provided, then Memory Bank uses the default settings for each type of configuration.

The Memory Bank configuration is set when creating or updating your Agent Engine instance:

client.agent_engines.create(
      ...,
      config={
            "context_spec": {
                  "memory_bank_config": memory_bank_config
            }
      }
)

# Alternatively, update an existing Agent Engine's Memory Bank config.
agent_engine = client.agent_engines.update(
      name=agent_engine.api_resource.name,
      config={
          "context_spec": {
                "memory_bank_config": memory_bank_config
          }
      }
)

You can configure the following settings for your instance:

• Similarity search configuration: Configures which embedding model is used for similarity search. Defaults to text-embedding-005.
• Generation configuration: Configures which LLM is used for memory generation. Defaults to gemini-2.0-flash-001.
• TTL configuration: Configures how TTL is automatically set for created or updated memories. Defaults to no TTL.

Similarity search configuration

The similarity search configuration controls which embedding model is used by your instance for similarity search. Similarity search is used for identifying which memories should be candidates for consolidation and for similarity search-based memory retrieval. If this configuration is not provided, Memory Bank uses text-embedding-005 as the default model.

If you expect user conversations to be in non-English languages, use a model that supports multiple languages, such as gemini-embedding-001 or text-multilingual-embedding-002, to improve retrieval quality.

memory_bank_config = {
    "similarity_search_config": {
        "embedding_model": "EMBEDDING_MODEL",
    }
}

from vertexai.types import ReasoningEngineContextSpecMemoryBankConfig as MemoryBankConfig
from vertexai.types import ReasoningEngineContextSpecMemoryBankConfigSimilaritySearchConfig as SimilaritySearchConfig

memory_bank_config = MemoryBankConfig(
    similarity_search_config=SimilaritySearchConfig(
        embedding_model="EMBEDDING_MODEL"
    )
)

Replace the following:

• EMBEDDING_MODEL: The Google text embedding model to use for similarity search, in the format projects/{project}/locations/{location}/publishers/google/models/{model}.

Generation configuration

The generation configuration controls which LLM is used for generating memories, including extracting memories and consolidating new memories with existing memories.

Memory Bank uses gemini-2.0-flash-001 as the default model.

memory_bank_config = {
      "generation_config": {
            "model": "LLM_MODEL",
      }
}

from vertexai.types import ReasoningEngineContextSpecMemoryBankConfig as MemoryBankConfig
from vertexai.types import ReasoningEngineContextSpecMemoryBankConfigGenerationConfig as GenerationConfig

memory_bank_config = MemoryBankConfig(
    generation_config=GenerationConfig(
      model="LLM_MODEL"
    )
)

Replace the following:

• LLM_MODEL: The Google LLM model to use for extracting and consolidating memories, in the format projects/{project}/locations/{location}/publishers/google/models/{model}.

Time to live (TTL) configuration

The TTL configuration controls how Memory Bank should dynamically set memories' expiration time. After their expiration time elapses, memories won't be available for retrieval and will be deleted.

If the configuration is not provided, expiration time won't be dynamically set for created or updated memories, so memories won't expire unless their expiration time is manually set.

There are two options for the TTL configuration:

• Default TTL: The TTL will be applied to all operations that create or update a memory, including UpdateMemory, CreateMemory, and GenerateMemories.

  Dictionary

  memory_bank_config = {
      "ttl_config": {
          "default_ttl": f"TTLs"
      }
  }
  

  Class-based

  from vertexai.types import ReasoningEngineContextSpecMemoryBankConfig as MemoryBankConfig
  from vertexai.types import ReasoningEngineContextSpecMemoryBankConfigTtlConfig as TtlConfig
  
  memory_bank_config = MemoryBankConfig(
      ttl_config=TtlConfig(
          default_ttl=f"TTLs"
      )
  )
  

  Replace the following:

  • TTL: The duration in seconds for the TTL. For updated memories, the newly calculated expiration time (now + TTL) will overwrite the Memory's previous expiration time.

• Granular (per-operation) TTL: The TTL is calculated based on which operation created or updated the Memory. If not set for a given operation, then the operation won't update the Memory's expiration time.

  Dictionary

  memory_bank_config = {
      "ttl_config": {
          "granular_ttl": {
              "create_ttl": f"CREATE_TTLs",
              "generate_created_ttl": f"GENERATE_CREATED_TTLs",
              "generate_updated_ttl": f"GENERATE_UPDATED_TTLs"
          }
      }
  }
  

  Class-based

  from vertexai.types import ReasoningEngineContextSpecMemoryBankConfig as MemoryBankConfig
  from vertexai.types import ReasoningEngineContextSpecMemoryBankConfigTtlConfig as TtlConfig
  from vertexai.types import ReasoningEngineContextSpecMemoryBankConfigTtlConfigGranularTtlConfig as GranularTtlConfig
  
  memory_bank_config = MemoryBankConfig(
      ttl_config=TtlConfig(
          granular_ttl_config=GranularTtlConfig(
              create_ttl=f"CREATE_TTLs",
              generate_created_ttl=f"GENERATE_CREATED_TTLs",
              generate_updated_ttl=f"GENERATE_UPDATED_TTLs",
          )
      )
  )
  

  Replace the following:

  • CREATE_TTL: The duration in seconds for the TTL for memories created using CreateMemory.
  • GENERATE_CREATED_TTL: The duration in seconds for the TTL for memories created using GeneratedMemories.
  • GENERATE_UPDATED_TTL: The duration in seconds for the TTL for memories updated using GeneratedMemories. The newly calculated expiration time (now + TTL) will overwrite the Memory's previous expiration time.

Deploy your agent with memory to Agent Engine

Although Memory Bank can be used in any runtime, you can also use Memory Bank with Agent Engine Runtime to read and write memories from your deployed agent.

To deploy an agent with Memory Bank on Vertex AI Agent Engine Runtime, first set up your environment for Agent Engine runtime. Then, prepare your agent to be deployed on Agent Engine Runtime with memory integration. Your deployed agent should make calls to read and write memories as needed.

from google.adk.agents import Agent
from vertexai.preview.reasoning_engines import AdkApp

# Develop an agent using the ADK template.
agent = Agent(...)

adk_app = AdkApp(
      agent=adk_agent,
      ...
)

# Deploy the agent to Agent Engine Runtime.
agent_engine = client.agent_engines.create(
      agent_engine=adk_app,
      config={
            "staging_bucket": "STAGING_BUCKET",
            "requirements": ["google-cloud-aiplatform[agent_engines,adk]"],
            # Optional.
            **context_spec
      }
)

# Update an existing Agent Engine to add or modify the Runtime.
agent_engine = client.agent_engines.update(
      name=agent_engine.api_resource.name,
      agent_engine=adk_app,
      config={
            "staging_bucket": "STAGING_BUCKET",
            "requirements": ["google-cloud-aiplatform[agent_engines,adk]"],
            # Optional.
            **context_spec
      }
)

project = os.environ.get("GOOGLE_CLOUD_PROJECT")
location = os.environ.get("GOOGLE_CLOUD_LOCATION")
agent_engine_id = os.environ.get("GOOGLE_CLOUD_AGENT_ENGINE_ID")

agent_engine_name = f"projects/{project}/locations/{location}/reasoningEngines/{agent_engine_id}"

What's next

• Quickstart with Vertex AI Agent Engine SDK.
• Quickstart with Agent Development Kit.