memory-management

Memory Management

Implement three tiers of agent memory -- short-term (context window), medium-term (checkpointer), and long-term (store) -- to enable persistent learning and state management.

When to Use

• Agent needs to resume work after interruption
• Agent should learn from past executions and avoid repeating mistakes
• Persisting state between nodes in a LangGraph workflow
• Storing and retrieving patterns learned across multiple demands
• Implementing memory decay to remove stale or low-confidence knowledge

Available Operations

1. Configure short-term memory via context window
2. Set up medium-term memory with LangGraph checkpointer
3. Implement long-term memory with LangGraph Store
4. Integrate memory into Deep Agent configuration
5. Implement memory cleanup and decay policies

Multi-Step Workflow

Step 1: Set Up Short-Term Memory (Context Window)

Short-term memory is automatic -- LangGraph accumulates messages within a session.

from typing import TypedDict, Annotated
from langgraph.graph.message import add_messages

class AgentState(TypedDict):
    messages: Annotated[list, add_messages]  # Accumulates automatically

No additional setup needed. Messages persist for the duration of a single invocation chain.

Step 2: Set Up Medium-Term Memory (Checkpointer)

Persists graph state between invocations of the same demand. Enables resume after failure.

pip install langgraph-checkpoint-postgres psycopg

from langgraph.checkpoint.postgres.aio import AsyncPostgresSaver
from langgraph.graph import StateGraph

checkpointer = AsyncPostgresSaver.from_conn_string(DATABASE_URL)

graph = StateGraph(OrchestratorState)
# ... define nodes and edges ...
app = graph.compile(checkpointer=checkpointer)

# Use consistent thread_id per demand
config = {"configurable": {"thread_id": f"demand-{demand_id}"}}
result = await app.ainvoke({"messages": [...]}, config=config)

# Next invocation with same thread_id resumes from saved state
result2 = await app.ainvoke({"messages": [new_msg]}, config=config)