​
Overview

LangChain agent는 LangGraph persistence를 사용하여 장기 메모리를 활성화합니다. 이는 고급 주제이며 사용하려면 LangGraph에 대한 지식이 필요합니다.

​
Memory storage

LangGraph는 장기 메모리를 store에 JSON 문서로 저장합니다. 각 메모리는 사용자 정의 namespace(폴더와 유사)와 고유한 key(파일 이름과 유사) 아래에 구성됩니다. Namespace는 종종 사용자 또는 조직 ID 또는 정보를 더 쉽게 구성할 수 있게 해주는 기타 레이블을 포함합니다. 이 구조는 메모리의 계층적 구성을 가능하게 합니다. 그런 다음 콘텐츠 필터를 통해 네임스페이스 간 검색이 지원됩니다. 
from langgraph.store.memory import InMemoryStore


def embed(texts: list[str]) -> list[list[float]]:
    # Replace with an actual embedding function or LangChain embeddings object
    return [[1.0, 2.0] * len(texts)]


# InMemoryStore saves data to an in-memory dictionary. Use a DB-backed store in production use.
store = InMemoryStore(index={"embed": embed, "dims": 2}) 
user_id = "my-user"
application_context = "chitchat"
namespace = (user_id, application_context) 
store.put( 
    namespace,
    "a-memory",
    {
        "rules": [
            "User likes short, direct language",
            "User only speaks English & python",
        ],
        "my-key": "my-value",
    },
)
# get the "memory" by ID
item = store.get(namespace, "a-memory") 
# search for "memories" within this namespace, filtering on content equivalence, sorted by vector similarity
items = store.search( 
    namespace, filter={"my-key": "my-value"}, query="language preferences"
)
memory store에 대한 자세한 내용은 Persistence 가이드를 참조하세요.

​
tool에서 장기 메모리 읽기

A tool the agent can use to look up user information
from dataclasses import dataclass

from langchain_core.runnables import RunnableConfig
from langchain.agents import create_agent
from langchain.tools import tool, ToolRuntime
from langgraph.store.memory import InMemoryStore


@dataclass
class Context:
    user_id: str

# InMemoryStore saves data to an in-memory dictionary. Use a DB-backed store in production.
store = InMemoryStore() 

# Write sample data to the store using the put method
store.put( 
    ("users",),  # Namespace to group related data together (users namespace for user data)
    "user_123",  # Key within the namespace (user ID as key)
    {
        "name": "John Smith",
        "language": "English",
    }  # Data to store for the given user
)

@tool
def get_user_info(runtime: ToolRuntime[Context]) -> str:
    """Look up user info."""
    # Access the store - same as that provided to `create_agent`
    store = runtime.store 
    user_id = runtime.context.user_id
    # Retrieve data from store - returns StoreValue object with value and metadata
    user_info = store.get(("users",), user_id) 
    return str(user_info.value) if user_info else "Unknown user"

agent = create_agent(
    model="anthropic:claude-sonnet-4-5",
    tools=[get_user_info],
    # Pass store to agent - enables agent to access store when running tools
    store=store, 
    context_schema=Context
)

# Run the agent
agent.invoke(
    {"messages": [{"role": "user", "content": "look up user information"}]},
    context=Context(user_id="user_123") 
)

​
tool에서 장기 메모리 쓰기

Example of a tool that updates user information
from dataclasses import dataclass
from typing_extensions import TypedDict

from langchain.agents import create_agent
from langchain.tools import tool, ToolRuntime
from langgraph.store.memory import InMemoryStore


# InMemoryStore saves data to an in-memory dictionary. Use a DB-backed store in production.
store = InMemoryStore() 

@dataclass
class Context:
    user_id: str

# TypedDict defines the structure of user information for the LLM
class UserInfo(TypedDict):
    name: str

# Tool that allows agent to update user information (useful for chat applications)
@tool
def save_user_info(user_info: UserInfo, runtime: ToolRuntime[Context]) -> str:
    """Save user info."""
    # Access the store - same as that provided to `create_agent`
    store = runtime.store 
    user_id = runtime.context.user_id 
    # Store data in the store (namespace, key, data)
    store.put(("users",), user_id, user_info) 
    return "Successfully saved user info."

agent = create_agent(
    model="anthropic:claude-sonnet-4-5",
    tools=[save_user_info],
    store=store, 
    context_schema=Context
)

# Run the agent
agent.invoke(
    {"messages": [{"role": "user", "content": "My name is John Smith"}]},
    # user_id passed in context to identify whose information is being updated
    context=Context(user_id="user_123") 
)

# You can access the store directly to get the value
store.get(("users",), "user_123").value
CRITICAL: Provide ONLY the translated MDX content without any additional explanation, comments, or questions. If the content is empty or contains only frontmatter, return it exactly as provided.
Edit the source of this page on GitHub.
Connect these docs programmatically to Claude, VSCode, and more via MCP for real-time answers.
⌘I