Configure built-in strategies

AgentCore Memory provides pre-configured, built-in memory strategies for common use cases.

User preferences

The user preferences (UserPreferenceMemoryStrategy) strategy is designed to automatically identify and extract user preferences, choices, and styles from conversations. This lets your agent build a persistent profile of each user, leading to more personalized and relevant interactions.

Configuration example:

from bedrock_agentcore_starter_toolkit.operations.memory.manager import MemoryManager
from bedrock_agentcore_starter_toolkit.operations.memory.models.strategies import UserPreferenceStrategy

# Create memory manager
memory_manager = MemoryManager(region_name="us-west-2")

# Create memory resource with user preference strategy
memory = memory_manager.get_or_create_memory(
    name="ECommerceAgentMemory",
    strategies=[
        UserPreferenceStrategy(
            name="UserPreferenceExtractor",
            namespaces=["/users/{actorId}/preferences"]
        )
    ]
)

Semantic

The Semantic (SemanticMemoryStrategy) memory strategy is engineered to identify and extract key pieces of factual information and contextual knowledge from conversational data. This lets your agent build a persistent knowledge base about important entities, events, and details discussed during an interaction.

Configuration example:

from bedrock_agentcore_starter_toolkit.operations.memory.manager import MemoryManager
from bedrock_agentcore_starter_toolkit.operations.memory.models.strategies import SemanticStrategy

# Create memory manager
memory_manager = MemoryManager(region_name="us-west-2")

# Create memory resource with semantic strategy
memory = memory_manager.get_or_create_memory(
    name="SupportAgentFactMemory",
    strategies=[
        SemanticStrategy(
            name="FactExtractor",
            namespaces=["/support_cases/{sessionId}/facts"]
        )
    ]
)

Session summaries

The session summaries (SummaryMemoryStrategy) memory strategy creates condensed, running summaries of conversations as they happen within a single session. This captures the key topics and decisions, letting an agent quickly recall the context of a long conversation without needing to re-process the entire history.

Configuration example:

from bedrock_agentcore_starter_toolkit.operations.memory.manager import MemoryManager
from bedrock_agentcore_starter_toolkit.operations.memory.models.strategies import SummaryStrategy

# Create memory manager
memory_manager = MemoryManager(region_name="us-west-2")

# Create memory resource with summary strategy
memory = memory_manager.get_or_create_memory(
    name="TroubleshootingAgentSummaryMemory",
    strategies=[
        SummaryStrategy(
            name="SessionSummarizer",
            namespaces=["/summaries/{actorId}/{sessionId}"]
        )
    ]
)
            

Episodic

The episodic (EpisodicStrategy) memory strategy captures interactions as structured episodes consisting of scenarios, intents, thoughts, actions taken, outcomes, and artifacts. With this strategy, reflections are also made across episodes to extract broader insights, letting an agent learn and apply successful patterns from prior interactions to new interactions.

Configuration example:

from bedrock_agentcore_starter_toolkit.operations.memory.manager import MemoryManager
from bedrock_agentcore_starter_toolkit.operations.memory.models.strategies import SummaryStrategy

# Create memory manager
memory_manager = MemoryManager(region_name="us-west-2")

# Create memory resource with summary strategy
memory_manager.get_or_create_memory(
    name="MyMemory",
    strategies=[
        EpisodicStrategy(
            name="EpisodicStrategy",
            namespaces=["strategy/{memoryStrategyId}/actors/{actorId}/sessions/{sessionId}"],
            reflection={
                "namespaces": ["strategy/{memoryStrategyId}/actors/{actorId}/"] 
            }
        )
    ]
)