Create an AgentCore Memory

You can create an AgentCore Memory with the AgentCore CLI, the AWS console, or with the CreateMemory AWS SDK operation. When creating a memory, you can configure settings such as name, description, encryption settings, expiration timestamp for raw events, and memory strategies if you want to extract long-term memory.

When creating an AgentCore Memory, consider the following factors to maintain it meets your application’s needs:

Event retention – Choose how long raw events are retained (up to 365 days) for short-term memory.

Note

eventExpiryDuration is applied per event at write time. Updating it affects only events created after the change. Previously stored events keep their original expiration and cannot be extended, and expired events cannot be recovered.

Long-term memory record retention (time-to-live) – Optionally choose how long extracted long-term memory records are retained before they expire. You configure this per strategy with recordExpiryDurationDays (minimum 31 days) inside the strategy’s recordExpirySpecification. If you do not set it, records generated by that strategy do not expire. Configuring or removing a record time-to-live requires the bedrock-agentcore:UpdateMemoryRecordExpirySpecification permission. For more information, see Set a time-to-live for long-term memory records.

Security requirements – If your application handles sensitive information, consider using a customer managed AWS KMS key for encryption. The service still encrypts data using a service managed key, even if you don’t provide a customer-managed AWS KMS key.

Memory strategies – Define how events are processed into meaningful long-term memories using built-in or built-in with overrides strategies. If you do not define any strategy, only short-term memory containing raw events are stored. For more information, see Use long-term memory.

Naming conventions – Use clear, descriptive names that help identify the purpose of each AgentCore Memory, especially if your application uses multiple stores.

Example

AgentCore CLI

The AgentCore CLI memory commands must be run inside an existing AgentCore project. If you don’t have one yet, create a project first:
```
agentcore create --name MemoryProject --template empty
cd MemoryProject
```
Create a basic memory (short-term only):
```
agentcore add memory --name my_agent_memory
agentcore deploy
```
Create memory with long-term strategies:
```
agentcore add memory --name ShoppingSupportAgentMemory \
  --strategies SUMMARIZATION,USER_PREFERENCE
agentcore deploy
```
Check memory status. Run agentcore status --json to find the deployed memory arn. The memory ID is the part of the ARN after memory/. Then check that the memory status is ACTIVE:
```
agentcore status --json
agentcore memory get --id <memory-id>
```

Interactive

Run agentcore add memory from the project directory to open the Memory wizard.
Enter the memory name.
Choose memory strategies for long-term memory extraction. Use the arrow keys and Space to select any of SEMANTIC, SUMMARIZATION, USER_PREFERENCE, and EPISODIC, then press Enter. Select none to keep only short-term memory.
Enter how long to keep raw events, from 3 to 365 days. The default is 30 days.
Review the configuration and press Enter to add the memory to agentcore/agentcore.json.
Press Ctrl+C to exit the TUI, then deploy the project to create the memory:
```
agentcore deploy
```
Run agentcore status --json to find the deployed memory arn. The memory ID is the part of the ARN after memory/. Then check that the memory status is ACTIVE:
```
agentcore status --json
agentcore memory get --id <memory-id>
```

AWS SDK

For more information, see AWS SDK.


import boto3
import time

# Initialize the Boto3 clients for control plane and data plane operations
control_client = boto3.client('bedrock-agentcore-control')
data_client = boto3.client('bedrock-agentcore')

print("Creating a new memory resource...")

# Create the memory resource with defined strategies
response = control_client.create_memory(
    name="ShoppingSupportAgentMemory",
    description="Memory for a customer support agent.",
    eventExpiryDuration=30,
    memoryStrategies=[
        {
            'summaryMemoryStrategy': {
                'name': 'SessionSummarizer',
                'namespaceTemplates': ['/summaries/{actorId}/{sessionId}/']
            }
        },
        {
            'userPreferenceMemoryStrategy': {
                'name': 'UserPreferenceExtractor',
                'namespaceTemplates': ['/users/{actorId}/preferences/']
            }
        }
    ]
)

memory_id = response['memory']['id']
print(f"Memory resource created with ID: {memory_id}")

# Poll the memory status until it becomes ACTIVE
while True:
    mem_status_response = control_client.get_memory(memoryId=memory_id)
    status = mem_status_response.get('memory', {}).get('status')
    if status == 'ACTIVE':
        print("Memory resource is now ACTIVE.")
        break
    elif status == 'FAILED':
        raise Exception("Memory resource creation FAILED.")
    print("Waiting for memory to become active...")
    time.sleep(10)

Console

====== To create an AgentCore memory
Open the Amazon Bedrock AgentCore console.
In the left navigation pane, under Resources, choose Memory.
Choose Create memory.
For Memory name enter a name for the AgentCore Memory.
(Optional) For Short-term memory (raw event) expiration set the duration (days), for which the AgentCore Memory will store events.
(Optional) In Additional configurations set the following:
1. For Memory description , enter a description for the AgentCore Memory.
2. If you want to use your own AWS KMS key to encrypt your data, do the following:
  1. In KMS key , choose Customize encryption settings (advanced).
  2. In Choose an AWS KMS key choose or enter the ARN of an existing AWS KMS key. Alternatively, choose Create an AWS KMS to create a new AWS KMS key.
(Optional) For Long-term memory extraction strategies choose one or more memory strategies . For more information:
Choose Create memory to create the AgentCore Memory.

Topics

Encrypt your Amazon Bedrock AgentCore Memory

Warning Javascript is disabled or is unavailable in your browser.

To use the Amazon Web Services Documentation, Javascript must be enabled. Please refer to your browser's Help pages for instructions.

Document Conventions

Get started with AgentCore Memory

Encrypt your Amazon Bedrock AgentCore Memory