Get started with AgentCore Memory

Amazon Bedrock AgentCore Memory lets you create and manage AgentCore Memory resources that store conversation context for your AI agents. This getting started guides you through installing dependencies and implementing both short-term and long-term memory features. The instructions use the AgentCore CLI.

The steps are as follows:

1. Create an AgentCore Memory containing a semantic strategy

2. Write events (conversation history) to the memory resource

3. Retrieve memory records from long term memory

For other examples, see Amazon Bedrock AgentCore Memory examples.

Prerequisites

Before starting, make sure you have:

• AWS Account with credentials configured ( aws configure )

• Python 3.10+ installed

• Node.js 20.12 or later installed (for the AgentCore CLI)

To get started with Amazon Bedrock AgentCore Memory, install the dependencies, create an AgentCore CLI project, and set up a virtual environment. The following commands can be run directly in the terminal.

npm install -g @aws/agentcore

agentcore create --name MemoryQuickstart --template empty

cd MemoryQuickstart

python -m venv .venv

source .venv/bin/activate

pip install bedrock-agentcore

The AgentCore CLI provides commands for creating and inspecting memory resources. Use agentcore add memory to declare a memory, agentcore deploy to provision it, and agentcore memory to inspect deployed memories. Use the AgentCore Python SDK (bedrock-agentcore) to write events.

Note

The AgentCore CLI helps you create, deploy, and inspect memory resources. For direct service API operations, see the Boto3 documentation: bedrock-agentcore-control and bedrock-agentcore.

Full example: See the Amazon Bedrock AgentCore samples that demonstrate steps 1-3.

Step 1: Create an AgentCore Memory

You need an AgentCore Memory to start storing information for your agent. By default, memory events (which we refer to as short-term memory) can be written to an AgentCore Memory. For insights to be extracted and placed into long term memory records, the resource requires a memory strategy which is a configuration that defines how conversational data should be processed, and what information to extract (such as facts, preferences, or summaries).

In this step, you create an AgentCore Memory with a semantic strategy so that both short term and long term memory can be utilized. This will take 2-3 minutes. You can also create AgentCore Memory resources in the AWS console.

Create memory with semantic strategy:

Example

AgentCore CLI

1. agentcore add memory --name CustomerSupportSemantic --strategies SEMANTIC
   
   agentcore deploy

Interactive

1. Run agentcore add memory to open the Memory wizard.

2. Enter the memory name, such as CustomerSupportSemantic.

3. Use the arrow keys and Space to select SEMANTIC, then press Enter.

4. Keep the default event retention of 30 days, review the configuration, and press Enter to add the memory.

   

5. Press Ctrl+C to exit the TUI, then run agentcore deploy to provision the memory in AWS.

After deployment, run agentcore status --json and copy the 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>

Step 2: Write events to memory

You can write events to an AgentCore Memory as short-term memory and extracts insights for long-term memory.

Writing events to memory has multiple purposes. First, event contents (most commonly conversation history) are stored as short-term memory. Second, relevant insights are pulled from events and written into memory records as a part of long-term memory.

The memory resource id, actor id, and session id are required to create an event. In this step, you create three events, simulating messages between an end user and a chat bot. Replace <your-memory-id> with the memory ID from Step 1.

from bedrock_agentcore.memory import MemorySessionManager
from bedrock_agentcore.memory.constants import ConversationalMessage, MessageRole

# The memory ID from Step 1
memory_id = "<your-memory-id>"

# Create a session to store memory events
session_manager = MemorySessionManager(
    memory_id=memory_id,
    region_name="us-west-2")

session = session_manager.create_memory_session(
    actor_id="User1",
    session_id="OrderSupportSession1"
)

# Write memory events (conversation turns)
session.add_turns(
    messages=[
        ConversationalMessage(
            "Hi, how can I help you today?",
            MessageRole.ASSISTANT)],
)

session.add_turns(
    messages=[
        ConversationalMessage(
            "Hi, I am a new customer. I just made an order, but it hasn't arrived. The Order number is #35476",
            MessageRole.USER)],
)

session.add_turns(
    messages=[
        ConversationalMessage(
            "I'm sorry to hear that. Let me look up your order.",
            MessageRole.ASSISTANT)],
)

You can get events (turns) for a specific actor after they’ve been written.

# Get the last k turns in the session
turns = session.get_last_k_turns(k=5)

for turn in turns:
    print(f"Turn: {turn}")

In this case, you can see the last three events for the actor and session.

Step 3: Retrieve records from long term memory

After the events were written to the memory resource, they were analyzed and useful information was sent to long term memory. Since the memory contains a semantic long term memory strategy, the system extracts and stores factual information.

You can list all memory records with:

# List all memory records
memory_records = session.list_long_term_memory_records(
    namespace_path="/"
)

for record in memory_records:
    print(f"Memory record: {record}")
    print("--------------------------------------------------------------------")

Or ask for the most relevant information as part of a semantic search:

# Perform a semantic search
memory_records = session.search_long_term_memories(
    query="can you summarize the support issue",
    namespace_path="/",
    top_k=3
)

Important information about the user is likely stored is long term memory. Agents can use long term memory rather than a full conversation history to make sure that LLMs are not overloaded with context.

Adding memory to an existing agent

A Python Strands project that you scaffold with agentcore create --name MyProject --template agent-python-strands includes app/agent/memory/session.py, and its main.py already uses it. The module reads the MEMORY_AGENTMEMORY_ID environment variable, which belongs to the agentMemory memory that the template adds. If the project has no memory with that name, for example because you removed it, add it with the strategies that the template uses by default, and deploy:

agentcore add memory --name agentMemory --strategies SEMANTIC,USER_PREFERENCE,SUMMARIZATION,EPISODIC
agentcore deploy

For a Strands agent that the AgentCore CLI did not scaffold with memory, follow these steps:

1. Add a memory resource to your project:

   agentcore add memory --name MyMemory --strategies SEMANTIC,SUMMARIZATION
   agentcore deploy

2. Create the memory/ directory in your agent:

   mkdir -p app/MyAgent/memory

3. Create app/MyAgent/memory/session.py :

   import os
   from typing import Optional
   from bedrock_agentcore.memory.integrations.strands.config import AgentCoreMemoryConfig, RetrievalConfig
   from bedrock_agentcore.memory.integrations.strands.session_manager import AgentCoreMemorySessionManager
   
   MEMORY_ID = os.getenv("MEMORY_MYMEMORY_ID")
   REGION = os.getenv("AWS_REGION")
   
   def get_memory_session_manager(session_id: str, actor_id: str) -> Optional[AgentCoreMemorySessionManager]:
       if not MEMORY_ID:
           return None
   
       retrieval_config = {
           f"/users/{actor_id}/facts": RetrievalConfig(top_k=3, relevance_score=0.5),
           f"/summaries/{actor_id}/{session_id}": RetrievalConfig(top_k=3, relevance_score=0.5)
       }
   
       return AgentCoreMemorySessionManager(
           AgentCoreMemoryConfig(
               memory_id=MEMORY_ID,
               session_id=session_id,
               actor_id=actor_id,
               retrieval_config=retrieval_config,
           ),
           REGION
       )

4. Update your main.py to use the session manager:

   from memory.session import get_memory_session_manager
   
   @app.entrypoint
   async def invoke(payload, context):
       session_id = getattr(context, 'session_id', 'default-session')
       user_id = getattr(context, 'user_id', 'default-user')
   
       agent = Agent(
           model=load_model(),
           session_manager=get_memory_session_manager(session_id, user_id),
           system_prompt="You are a helpful assistant.",
       )
   
       response = agent(str(payload.get("prompt", "")))
       return response

5. Deploy the updated project:

   agentcore deploy

Note

Each memory resource gets the environment variables MEMORY_<NAME>_ID and MEMORY_<NAME>_ARN, where <NAME> is the memory name in uppercase. They are available in your agent’s runtime environment after deployment.

Cleanup

When you’re done with the memory resource, you can delete it:

agentcore remove memory --name CustomerSupportSemantic
agentcore deploy

Next steps

Consider the following:

• Add another strategy to your memory resource.

• Enable observability for more visibility into how memory is working

• Look at further examples.