长期记忆

为 LangChain 智能体添加长期记忆，实现跨对话和会话的数据存储与回忆

长期记忆使您的智能体能够跨不同对话和会话存储并回忆信息。 与仅限于单个线程的短期记忆不同，长期记忆可跨线程持久保存，并可在任意时刻被回忆。

长期记忆构建于 LangGraph 存储之上，该存储将数据保存为按命名空间和键组织的 JSON 文档。

使用方法

要为智能体添加长期记忆，请创建一个存储并将其传递给 create_agent：

InMemoryStore

from langchain.agents import create_agent
from langchain_core.runnables import Runnable
from langgraph.store.memory import InMemoryStore

# InMemoryStore 将数据存储到内存字典中。在生产环境中请使用基于数据库的存储。
store = InMemoryStore()

agent: Runnable = create_agent(
    "claude-sonnet-4-6",
    tools=[],
    store=store,
)

PostgreSQL

pip install langgraph-checkpoint-postgres

from langchain.agents import create_agent
from langchain_core.runnables import Runnable
from langgraph.store.postgres import PostgresStore  # type: ignore[import-not-found]

DB_URI = "postgresql://postgres:postgres@localhost:5442/postgres?sslmode=disable"

with PostgresStore.from_conn_string(DB_URI) as store:
    store.setup()
    agent: Runnable = create_agent(
        "claude-sonnet-4-6",
        tools=[],
        store=store,
    )

随后，工具可通过 runtime.store 参数从存储中读取数据或向存储写入数据。具体示例请参阅在工具中读取长期记忆和从工具写入长期记忆。

若需深入了解记忆类型（语义记忆、情景记忆、程序性记忆）及记忆写入策略，请参阅记忆概念指南。

记忆存储

LangGraph 将长期记忆作为 JSON 文档存储在存储中。

每条记忆都组织在自定义的 namespace（类似于文件夹）和唯一的 key（类似于文件名）之下。命名空间通常包含用户或组织 ID 或其他便于信息组织的标签。

这种结构支持记忆的层次化组织。跨命名空间的搜索则通过内容过滤器实现。

InMemoryStore

from collections.abc import Sequence

from langgraph.store.base import IndexConfig
from langgraph.store.memory import InMemoryStore


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


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

PostgreSQL

from collections.abc import Sequence

from langgraph.store.base import IndexConfig
from langgraph.store.postgres import PostgresStore  # type: ignore[import-not-found]


def embed(texts: Sequence[str]) -> list[list[float]]:
    # 替换为实际的嵌入函数或 LangChain 嵌入对象
    return [[1.0, 2.0] for _ in texts]


DB_URI = "postgresql://postgres:postgres@localhost:5442/postgres?sslmode=disable"

with PostgresStore.from_conn_string(
    DB_URI,
    index=IndexConfig(embed=embed, dims=2),  # type: ignore[arg-type]
) as store:
    store.setup()
    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",
        },
    )
    item = store.get(namespace, "a-memory")
    items = store.search(
        namespace, filter={"my-key": "my-value"}, query="language preferences"
    )

有关记忆存储的更多信息，请参阅持久化指南。

在工具中读取长期记忆

InMemoryStore

from dataclasses import dataclass

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


@dataclass
class Context:
    user_id: str


# InMemoryStore 将数据保存到内存字典中。在生产环境中请使用基于数据库的存储。
store = InMemoryStore()

# 使用 put 方法向存储写入示例数据
store.put(
    (
        "users",
    ),  # 用于分组相关数据的命名空间（用户数据的 users 命名空间）
    "user_123",  # 命名空间内的键（以用户 ID 为键）
    {
        "name": "John Smith",
        "language": "English",
    },  # 要存储的给定用户的数据
)


@tool
def get_user_info(runtime: ToolRuntime[Context]) -> str:
    """查找用户信息。"""
    # 访问存储 - 与提供给 `create_agent` 的相同
    assert runtime.store is not None
    user_id = runtime.context.user_id
    # 从存储检索数据 - 返回包含值和元数据的 StoreValue 对象
    user_info = runtime.store.get(("users",), user_id)
    return str(user_info.value) if user_info else "Unknown user"


agent: Runnable = create_agent(
    model="claude-sonnet-4-6",
    tools=[get_user_info],
    # 将存储传递给代理 - 使代理在运行工具时能够访问存储
    store=store,
    context_schema=Context,
)

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

PostgreSQL

from dataclasses import dataclass

from langchain.agents import create_agent
from langchain.tools import ToolRuntime, tool
from langchain_core.runnables import Runnable
from langgraph.store.postgres import PostgresStore  # type: ignore[import-not-found]


@dataclass
class Context:
    user_id: str


DB_URI = "postgresql://postgres:postgres@localhost:5442/postgres?sslmode=disable"

with PostgresStore.from_conn_string(DB_URI) as store:
    store.setup()
    store.put(("users",), "user_123", {"name": "John Smith", "language": "English"})

    @tool
    def get_user_info(runtime: ToolRuntime[Context]) -> str:
        """Look up user info."""
        assert runtime.store is not None
        user_info = runtime.store.get(("users",), runtime.context.user_id)
        return str(user_info.value) if user_info else "Unknown user"

    agent: Runnable = create_agent(
        "claude-sonnet-4-6",
        tools=[get_user_info],
        store=store,
        context_schema=Context,
    )

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

从工具写入长期记忆

InMemoryStore

from dataclasses import dataclass

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

# InMemoryStore 将数据保存到内存字典中。在生产环境中请使用基于数据库的存储。
store = InMemoryStore()


@dataclass
class Context:
    user_id: str


# TypedDict 定义了 LLM 的用户信息结构
class UserInfo(TypedDict):
    name: str


# 允许代理更新用户信息的工具（适用于聊天应用程序）
@tool
def save_user_info(user_info: UserInfo, runtime: ToolRuntime[Context]) -> str:
    """保存用户信息。"""
    # 访问存储 - 与提供给 `create_agent` 的相同
    assert runtime.store is not None
    store = runtime.store
    user_id = runtime.context.user_id
    # 在存储中存储数据（命名空间，键，数据）
    store.put(("users",), user_id, dict(user_info))
    return "Successfully saved user info."


agent: Runnable = create_agent(
    model="claude-sonnet-4-6",
    tools=[save_user_info],
    store=store,
    context_schema=Context,
)

# 运行代理
agent.invoke(
    {"messages": [{"role": "user", "content": "My name is John Smith"}]},
    # 通过上下文传递的 user_id 用于标识正在更新谁的信息
    context=Context(user_id="user_123"),
)

# 您可以直接访问存储以获取值
item = store.get(("users",), "user_123")

PostgreSQL

from dataclasses import dataclass

from langchain.agents import create_agent
from langchain.tools import ToolRuntime, tool
from langchain_core.runnables import Runnable
from langgraph.store.postgres import PostgresStore  # type: ignore[import-not-found]
from typing_extensions import TypedDict


@dataclass
class Context:
    user_id: str


class UserInfo(TypedDict):
    name: str


@tool
def save_user_info(user_info: UserInfo, runtime: ToolRuntime[Context]) -> str:
    """Save user info."""
    assert runtime.store is not None
    runtime.store.put(("users",), runtime.context.user_id, dict(user_info))
    return "Successfully saved user info."


DB_URI = "postgresql://postgres:postgres@localhost:5442/postgres?sslmode=disable"

with PostgresStore.from_conn_string(DB_URI) as store:
    store.setup()
    agent: Runnable = create_agent(
        "claude-sonnet-4-6",
        tools=[save_user_info],
        store=store,
        context_schema=Context,
    )

    agent.invoke(
        {"messages": [{"role": "user", "content": "My name is John Smith"}]},
        context=Context(user_id="user_123"),
    )

---

Edit this page on GitHub or file an issue.

Connect these docs to Claude, VSCode, and more via MCP for real-time answers.