Skip to content

Add memory

The chatbot can now use tools to answer user questions, but it does not remember the context of previous interactions. This limits its ability to have coherent, multi-turn conversations.

LangGraph solves this problem through persistent checkpointing. If you provide a checkpointer when compiling the graph and a thread_id when calling your graph, LangGraph automatically saves the state after each step. When you invoke the graph again using the same thread_id, the graph loads its saved state, allowing the chatbot to pick up where it left off.

We will see later that checkpointing is much more powerful than simple chat memory - it lets you save and resume complex state at any time for error recovery, human-in-the-loop workflows, time travel interactions, and more. But first, let's add checkpointing to enable multi-turn conversations.

Note

This tutorial builds on Add tools.

1. Create a MemorySaver checkpointer

Create a MemorySaver checkpointer:

from langgraph.checkpoint.memory import MemorySaver

memory = MemorySaver()

This is in-memory checkpointer, which is convenient for the tutorial. However, in a production application, you would likely change this to use SqliteSaver or PostgresSaver and connect a database.

2. Compile the graph

Compile the graph with the provided checkpointer, which will checkpoint the State as the graph works through each node:

graph = graph_builder.compile(checkpointer=memory)

from IPython.display import Image, display

try:
    display(Image(graph.get_graph().draw_mermaid_png()))
except Exception:
    # This requires some extra dependencies and is optional
    pass

3. Interact with your chatbot

Now you can interact with your bot!

  1. Pick a thread to use as the key for this conversation.

    config = {"configurable": {"thread_id": "1"}}

  2. Call your chatbot:

    user_input = "Hi there! My name is Will."

# The config is the **second positional argument** to stream() or invoke()!
events = graph.stream(
    {"messages": [{"role": "user", "content": user_input}]},
    config,
    stream_mode="values",
)
for event in events:
    event["messages"][-1].pretty_print()

    ================================ Human Message =================================

Hi there! My name is Will.
================================== Ai Message ==================================

Hello Will! It's nice to meet you. How can I assist you today? Is there anything specific you'd like to know or discuss?

    Note

    The config was provided as the second positional argument when calling our graph. It importantly is not nested within the graph inputs ({'messages': []}).

4. Ask a follow up question

Ask a follow up question:

user_input = "Remember my name?"

# The config is the **second positional argument** to stream() or invoke()!
events = graph.stream(
    {"messages": [{"role": "user", "content": user_input}]},
    config,
    stream_mode="values",
)
for event in events:
    event["messages"][-1].pretty_print()

================================ Human Message =================================

Remember my name?
================================== Ai Message ==================================

Of course, I remember your name, Will. I always try to pay attention to important details that users share with me. Is there anything else you'd like to talk about or any questions you have? I'm here to help with a wide range of topics or tasks.

Notice that we aren't using an external list for memory: it's all handled by the checkpointer! You can inspect the full execution in this LangSmith trace to see what's going on.

Don't believe me? Try this using a different config.

# The only difference is we change the `thread_id` here to "2" instead of "1"
events = graph.stream(
    {"messages": [{"role": "user", "content": user_input}]},
    {"configurable": {"thread_id": "2"}},
    stream_mode="values",
)
for event in events:
    event["messages"][-1].pretty_print()

================================ Human Message =================================

Remember my name?
================================== Ai Message ==================================

I apologize, but I don't have any previous context or memory of your name. As an AI assistant, I don't retain information from past conversations. Each interaction starts fresh. Could you please tell me your name so I can address you properly in this conversation?

Notice that the only change we've made is to modify the thread_id in the config. See this call's LangSmith trace for comparison.

5. Inspect the state

By now, we have made a few checkpoints across two different threads. But what goes into a checkpoint? To inspect a graph's state for a given config at any time, call get_state(config).

snapshot = graph.get_state(config)
snapshot

StateSnapshot(values={'messages': [HumanMessage(content='Hi there! My name is Will.', additional_kwargs={}, response_metadata={}, id='8c1ca919-c553-4ebf-95d4-b59a2d61e078'), AIMessage(content="Hello Will! It's nice to meet you. How can I assist you today? Is there anything specific you'd like to know or discuss?", additional_kwargs={}, response_metadata={'id': 'msg_01WTQebPhNwmMrmmWojJ9KXJ', 'model': 'claude-3-5-sonnet-20240620', 'stop_reason': 'end_turn', 'stop_sequence': None, 'usage': {'input_tokens': 405, 'output_tokens': 32}}, id='run-58587b77-8c82-41e6-8a90-d62c444a261d-0', usage_metadata={'input_tokens': 405, 'output_tokens': 32, 'total_tokens': 437}), HumanMessage(content='Remember my name?', additional_kwargs={}, response_metadata={}, id='daba7df6-ad75-4d6b-8057-745881cea1ca'), AIMessage(content="Of course, I remember your name, Will. I always try to pay attention to important details that users share with me. Is there anything else you'd like to talk about or any questions you have? I'm here to help with a wide range of topics or tasks.", additional_kwargs={}, response_metadata={'id': 'msg_01E41KitY74HpENRgXx94vag', 'model': 'claude-3-5-sonnet-20240620', 'stop_reason': 'end_turn', 'stop_sequence': None, 'usage': {'input_tokens': 444, 'output_tokens': 58}}, id='run-ffeaae5c-4d2d-4ddb-bd59-5d5cbf2a5af8-0', usage_metadata={'input_tokens': 444, 'output_tokens': 58, 'total_tokens': 502})]}, next=(), config={'configurable': {'thread_id': '1', 'checkpoint_ns': '', 'checkpoint_id': '1ef7d06e-93e0-6acc-8004-f2ac846575d2'}}, metadata={'source': 'loop', 'writes': {'chatbot': {'messages': [AIMessage(content="Of course, I remember your name, Will. I always try to pay attention to important details that users share with me. Is there anything else you'd like to talk about or any questions you have? I'm here to help with a wide range of topics or tasks.", additional_kwargs={}, response_metadata={'id': 'msg_01E41KitY74HpENRgXx94vag', 'model': 'claude-3-5-sonnet-20240620', 'stop_reason': 'end_turn', 'stop_sequence': None, 'usage': {'input_tokens': 444, 'output_tokens': 58}}, id='run-ffeaae5c-4d2d-4ddb-bd59-5d5cbf2a5af8-0', usage_metadata={'input_tokens': 444, 'output_tokens': 58, 'total_tokens': 502})]}}, 'step': 4, 'parents': {}}, created_at='2024-09-27T19:30:10.820758+00:00', parent_config={'configurable': {'thread_id': '1', 'checkpoint_ns': '', 'checkpoint_id': '1ef7d06e-859f-6206-8003-e1bd3c264b8f'}}, tasks=())

snapshot.next  # (since the graph ended this turn, `next` is empty. If you fetch a state from within a graph invocation, next tells which node will execute next)

The snapshot above contains the current state values, corresponding config, and the next node to process. In our case, the graph has reached an END state, so next is empty.

Congratulations! Your chatbot can now maintain conversation state across sessions thanks to LangGraph's checkpointing system. This opens up exciting possibilities for more natural, contextual interactions. LangGraph's checkpointing even handles arbitrarily complex graph states, which is much more expressive and powerful than simple chat memory.

Check out the code snippet below to review the graph from this tutorial:

pip install -U "langchain[openai]"

import os
from langchain.chat_models import init_chat_model

os.environ["OPENAI_API_KEY"] = "sk-..."

llm = init_chat_model("openai:gpt-4.1")


pip install -U "langchain[anthropic]"

import os
from langchain.chat_models import init_chat_model

os.environ["ANTHROPIC_API_KEY"] = "sk-..."

llm = init_chat_model("anthropic:claude-3-5-sonnet-latest")


pip install -U "langchain[openai]"

import os
from langchain.chat_models import init_chat_model

os.environ["AZURE_OPENAI_API_KEY"] = "..."
os.environ["AZURE_OPENAI_ENDPOINT"] = "..."
os.environ["OPENAI_API_VERSION"] = "2025-03-01-preview"

llm = init_chat_model(
    "azure_openai:gpt-4.1",
    azure_deployment=os.environ["AZURE_OPENAI_DEPLOYMENT_NAME"],
)


pip install -U "langchain[google-genai]"

import os
from langchain.chat_models import init_chat_model

os.environ["GOOGLE_API_KEY"] = "..."

llm = init_chat_model("google_genai:gemini-2.0-flash")


pip install -U "langchain[aws]"

from langchain.chat_models import init_chat_model

# Follow the steps here to configure your credentials:
# https://docs.aws.amazon.com/bedrock/latest/userguide/getting-started.html

llm = init_chat_model(
    "anthropic.claude-3-5-sonnet-20240620-v1:0",
    model_provider="bedrock_converse",
)

API Reference: init_chat_model | TavilySearch | BaseMessage | MemorySaver | StateGraph | add_messages | ToolNode | tools_condition

from typing import Annotated

from langchain.chat_models import init_chat_model
from langchain_tavily import TavilySearch
from langchain_core.messages import BaseMessage
from typing_extensions import TypedDict

from langgraph.checkpoint.memory import MemorySaver
from langgraph.graph import StateGraph
from langgraph.graph.message import add_messages
from langgraph.prebuilt import ToolNode, tools_condition

class State(TypedDict):
    messages: Annotated[list, add_messages]

graph_builder = StateGraph(State)

tool = TavilySearch(max_results=2)
tools = [tool]
llm_with_tools = llm.bind_tools(tools)

def chatbot(state: State):
    return {"messages": [llm_with_tools.invoke(state["messages"])]}

graph_builder.add_node("chatbot", chatbot)

tool_node = ToolNode(tools=[tool])
graph_builder.add_node("tools", tool_node)

graph_builder.add_conditional_edges(
    "chatbot",
    tools_condition,
)
graph_builder.add_edge("tools", "chatbot")
graph_builder.set_entry_point("chatbot")
memory = MemorySaver()
graph = graph_builder.compile(checkpointer=memory)

Next steps

In the next tutorial, you will add human-in-the-loop to the chatbot to handle situations where it may need guidance or verification before proceeding.