Cross-Thread Long-Term Memory Stores in LangGraph
Long-term memory across threads in LangGraph: store namespaces, put/get/search, semantic search over memories, deduped writes and Postgres-backed persistence.
This article is published in English.
Sources: Long Term Memory in LangGraph| Part 16| class 24 of LangGraph | cswithshahil
Why short-term thread memory is not enough
Checkpointed chat history covers one thread. Real users bounce across threads—debugging LangChain on Monday, planning travel on Tuesday—so facts about them scatter. Long-term memory (LTM) adds a durable store: an extractor writes personal details out of turns, and later replies query that store before answering. Prefer Python once, ask for Fibonacci later, and the assistant can reuse the preference without being told again.
Stores as the LangGraph memory surface
LangGraph models LTM through stores. BaseStore defines create, search, edit, and delete. Common backends: InMemoryStore for prototypes in RAM; PostgresStore and RedisStore when restarts must not wipe memory.
Standalone store operations
Treat namespaces like folders. They are Python tuples—("users", "U1") or a deeper ("users", "U1", "profile").
Create with put(namespace, key, values). Fetch one item with get when the key is known; list a namespace with search.
from langgraph.store.memory import InMemoryStore
# creating a store
store = InMemoryStore()
# creating a namespace
namespace = ("user", "u1")
Creating memories
# Adding memories
store.put(namespace, "1", {"data": "User likes pizza"})
store.put(namespace, "2", {"data": "User prefers dark mode"})
# another namespace
namespace2 = ("user", "u2")
# Add memories
store.put(namespace2, "1", {"data": "User likes pasta"})
store.put(namespace2, "2", {"data": "User prefers grid style navigation"})
Retrieving one memory
# store.get(namespace, key)
store.get(namespace2, "2")
Item(namespace=['user', 'u2'], key='2', value={'data': 'User prefers grid style navigation'}, created_at='2026-01-06T15:05:16.376069+00:00', updated_at='2026-01-06T15:05:16.376070+00:00')
Retrieving everything in a namespace
items = store.search(namespace2)
for item in items:
print(item.value)
{'data': 'User likes pasta'}
{'data': 'User prefers grid style navigation'}
Semantic search when the bag grows
Dumping a hundred profile facts into the prompt overwhelms the model. Index the store with an embedding model (for example text-embedding-3-small) so search can take a query and limit, returning only vectors close to the current question.
Semantic Search
from langchain_openai import OpenAIEmbeddings
from dotenv import load_dotenv
load_dotenv()
embedding_model = OpenAIEmbeddings(model='text-embedding-3-small')
store = InMemoryStore(index={'embed': embedding_model, 'dims':1536})
namespace = ('users', 'u1')
store.put(namespace, "1", {"data": "User prefers concise answers over long explanations"})
store.put(namespace, "2", {"data": "User likes examples in Python"})
store.put(namespace, "3", {"data": "User usually works late at night"})
store.put(namespace, "4", {"data": "User prefers dark mode in applications"})
store.put(namespace, "5", {"data": "User is learning machine learning"})
store.put(namespace, "6", {"data": "User dislikes overly theoretical explanations"})
store.put(namespace, "7", {"data": "User prefers step-by-step reasoning"})
store.put(namespace, "8", {"data": "User is based in India"})
store.put(namespace, "9", {"data": "User likes real-world analogies"})
store.put(namespace, "10", {"data": "User prefers bullet points over paragraphs"})
items = store.search(namespace, query="what is the user currently learning", limit=1)
for item in items:
print(item.value)
# output :{'data': 'User is learning machine learning'}
items = store.search(namespace, query="what are user's preferences", limit=3)
for item in items:
print(item.value)
# output :
# {'data': 'User prefers dark mode in applications'}
# {'data': 'User prefers bullet points over paragraphs'}
# {'data': 'User prefers concise answers over long explanations'}
Read-only personalization in a chat node
Wire the store into a LangGraph chat node that receives state, config (user or thread id), and store. Build the namespace from the user id, search memories, fold them into the system prompt, and instruct the model to use known names, projects, and tone—plus a few relevant follow-ups.
Chatbot Reading Existing Memories
from dotenv import load_dotenv
load_dotenv()
from langchain_openai import ChatOpenAI
from langchain_core.runnables import RunnableConfig
from langchain_core.messages import SystemMessage
from langgraph.graph import StateGraph, START, END, MessagesState
from langgraph.store.memory import InMemoryStore
from langgraph.store.base import BaseStore
# ----------------------------
# 1) Create LTM store + seed memories (done BEFORE running the graph)
# ----------------------------
store = InMemoryStore()
user_id = "u1"
# Store user details as a single blob (simple for teaching)
# You can also split into multiple records; this keeps it easy.
user_details = ("user", user_id, "details")
store.put(user_details, "profile_1", {"data": "Name: Nitish"})
store.put(user_details, "profile_2", {"data": "Profession: Teaches AI on YouTube"})
store.put(user_details, "preference_1", {"data": "Prefers concise answers"})
store.put(user_details, "preference_2", {"data": "Likes examples in Python"})
store.put(user_details, "project_1", {"data": "Building MCP servers (Python-based project)"})
# ----------------------------
# 2) System prompt template (your prompt)
# ----------------------------
SYSTEM_PROMPT_TEMPLATE = """You are a helpful assistant with memory capabilities.
If user-specific memory is available, use it to personalize
your responses based on what you know about the user.
Your goal is to provide relevant, friendly, and tailored
assistance that reflects the user’s preferences, context, and past interactions.
If the user’s name or relevant personal context is available, always personalize your responses by:
– Always Address the user by name (e.g., "Sure, Nitish...") when appropriate
– Referencing known projects, tools, or preferences (e.g., "your MCP server python based project")
– Adjusting the tone to feel friendly, natural, and directly aimed at the user
Avoid generic phrasing when personalization is possible. For example, instead of "In TypeScript apps..."
say "Since your project is built with TypeScript..."
Use personalization especially in:
– Greetings and transitions
– Help or guidance tailored to tools and frameworks the user uses
– Follow-up messages that continue from past context
Always ensure that personalization is based only on known user details and not assumed.
In the end suggest 3 relevant further questions based on the current response and user profile
The user’s memory (which may be empty) is provided as: {user_details_content}
"""
# ----------------------------
# 3) Build graph: START -> chat -> END (read-only LTM)
# ----------------------------
llm = ChatOpenAI(model="gpt-4o-mini")
def chat_node(state: MessagesState, config: RunnableConfig, store: BaseStore):
user_id = config["configurable"]["user_id"]
# Read-only: fetch user details memory (no writes)
user_details = ("user", user_id, "details")
items = store.search(user_details)
# Convert memory items into a string blob for {user_details_content}
# Keep it dead simple for teaching.
if items:
user_details_content = "\n".join(f"- {it.value.get('data', '')}" for it in items)
else:
user_details_content = "" # prompt says it may be empty
system_prompt = SYSTEM_PROMPT_TEMPLATE.format(
user_details_content=user_details_content
)
system_msg = SystemMessage(content=system_prompt)
response = llm.invoke([system_msg] + state["messages"])
return {"messages": [response]}
builder = StateGraph(MessagesState)
builder.add_node("chat", chat_node)
builder.add_edge(START, "chat")
builder.add_edge("chat", END)
graph = builder.compile(store=store)
graph
# ----------------------------
# 4) Run it (provide user_id in config)
# ----------------------------
config = {"configurable": {"user_id": "u1"}}
result = graph.invoke(
{"messages": [{"role": "user", "content": "Explain gen ai in simple terms."}]},
config,
)
print(result["messages"][-1].content)
# Sure, Nitish! Generative AI, or Gen AI, refers to a type of artificial intelligence that creates new content or data instead of just analyzing existing information. It can generate text, images, music, and more by learning patterns from large sets of data. For example, it can write a story, design an artwork, or compose a song based on the styles of various creators it has learned from.
#If you're considering using examples or applications of Gen AI for your YouTube teaching, there are plenty of interesting case studies you could explore, especially in creative fields.
#Here are a few questions to consider:
#1. Would you like to see specific examples of Gen AI in Python?
#2. Are you interested in exploring tools or libraries for building Gen AI projects?
#3. How would you like to incorporate Gen AI concepts into your teaching materials?
Writing new memories during chat
Chatbot Creating New Memories
from dotenv import load_dotenv
load_dotenv()
import uuid
from typing import List
from pydantic import BaseModel, Field
from langchain_openai import ChatOpenAI
from langchain_core.messages import SystemMessage
from langchain_core.runnables import RunnableConfig
from langgraph.graph import StateGraph, START, END, MessagesState
from langgraph.store.memory import InMemoryStore
from langgraph.store.base import BaseStore
# ----------------------------
# 1) LTM store
# ----------------------------
store = InMemoryStore()
# ----------------------------
# 2) LLM that decides what to remember (structured output)
# ----------------------------
extractor_llm = ChatOpenAI(model="gpt-4o-mini", temperature=0)
class MemoryDecision(BaseModel):
should_write: bool = Field(description="Whether to store any memories")
memories: List[str] = Field(default_factory=list, description="Atomic user memories to store")
memory_extractor = extractor_llm.with_structured_output(MemoryDecision)
# ----------------------------
# 3) Graph: START -> remember -> END
# (Creates memories, but does NOT use them to answer)
# ----------------------------
def remember_only_node(state: MessagesState, config: RunnableConfig, store: BaseStore):
user_id = config["configurable"]["user_id"]
namespace = ("user", user_id, "details")
# take latest user message
last_msg = state["messages"][-1].content
# LLM decides what to store
decision: MemoryDecision = memory_extractor.invoke(
[
SystemMessage(
content=(
"Extract LONG-TERM memories from the user's message.\n"
"Only store stable, user-specific info (identity, preferences, ongoing projects).\n"
"Do NOT store transient info.\n"
"Return should_write=false if nothing is worth storing.\n"
"Each memory should be a short atomic sentence."
)
),
{"role": "user", "content": last_msg},
]
)
# Write to store (LTM)
if decision.should_write:
for mem in decision.memories:
store.put(namespace, str(uuid.uuid4()), {"data": mem})
# IMPORTANT: we are NOT using memory, not even responding with the LLM.
# We just return a fixed acknowledgement.
return {"messages": [{"role": "assistant", "content": "Noted."}]}
builder = StateGraph(MessagesState)
builder.add_node("remember", remember_only_node)
builder.add_edge(START, "remember")
builder.add_edge("remember", END)
graph = builder.compile(store=store)
graph
# ----------------------------
# 4) Demo
# ----------------------------
config = {"configurable": {"user_id": "u1"}}
res = graph.invoke({"messages": [{"role": "user", "content": "Hi my name is nitish"}]},config)
print("Assistant:", res["messages"][-1].content)
#output : Assistant: Noted.
res = graph.invoke({"messages": [{"role": "user", "content": "I teach AI on youtube"}]},config)
print("Assistant:", res["messages"][-1].content)
#output :Assistant: Noted.
res = graph.invoke({"messages": [{"role": "user", "content": "My favorite programming language is Python"}]},config)
print("Assistant:", res["messages"][-1].content)
# output :Assistant: Noted.
items = store.search(("user", "u1", "details"))
for item in items:
print(item.value['data'])
#output:
# User's name is Nitish.
# User teaches AI on YouTube.
# User's favorite programming language is Python.
#User's name is Nitish.
# User teaches AI on YouTube.
# User's favorite programming language is Python.
Automatic writes need a remember node ahead of chat. A dedicated extractor model returns structured MemoryDecision output: whether to write and which items. Without de-duplication, repeating “my name is …” creates clones. Upgrade items with an is_new flag against existing memories and persist only the new ones.
Chatbot Creating New Memories(without Duplication)
from dotenv import load_dotenv
load_dotenv()
import uuid
from typing import List
from pydantic import BaseModel, Field
from langchain_openai import ChatOpenAI
from langchain_core.messages import SystemMessage
from langchain_core.runnables import RunnableConfig
from langgraph.graph import StateGraph, START, END, MessagesState
from langgraph.store.memory import InMemoryStore
from langgraph.store.base import BaseStore
# ----------------------------
# 1) LTM store
# ----------------------------
store = InMemoryStore()
# ----------------------------
# 2) LLMs
# - memory_llm: extracts candidate memories + tells if each is NEW (no duplicate_of needed)
# ----------------------------
memory_llm = ChatOpenAI(model="gpt-4o-mini", temperature=0)
class MemoryItem(BaseModel):
text: str = Field(description="Atomic user memory as a short sentence")
is_new: bool = Field(description="True if this memory is NEW and should be stored. False if duplicate/already known.")
class MemoryDecision(BaseModel):
should_write: bool = Field(description="Whether to store any memories")
memories: List[MemoryItem] = Field(default_factory=list, description="Atomic user memories to store")
memory_extractor = memory_llm.with_structured_output(MemoryDecision)
MEMORY_PROMPT = """You are responsible for updating and maintaining accurate user memory.
CURRENT USER DETAILS (existing memories):
{user_details_content}
TASK:
- Review the user's latest message.
- Extract user-specific info worth storing long-term (identity, stable preferences, ongoing projects/goals).
- For each extracted item, set is_new=true ONLY if it adds NEW information compared to CURRENT USER DETAILS.
- If it is basically the same meaning as something already present, set is_new=false.
- Keep each memory as a short atomic sentence.
- No speculation; only facts stated by the user.
- If there is nothing memory-worthy, return an empty list.
"""
def chat_creates_memory_node(state: MessagesState, config: RunnableConfig, store: BaseStore):
user_id = config["configurable"]["user_id"]
namespace = ("user", user_id, "details")
# A) Load existing memories
existing_items = store.search(namespace)
existing_texts = [it.value.get("data", "") for it in existing_items if it.value.get("data")]
user_details_content = "\n".join(f"- {t}" for t in existing_texts) if existing_texts else "(empty)"
# B) Latest user message
last_text = state["messages"][-1]
# C) LLM extracts memories + marks new vs duplicate
decision: MemoryDecision = memory_extractor.invoke(
[
SystemMessage(content=MEMORY_PROMPT.format(user_details_content=user_details_content)),
{"role": "user", "content": f"USER MESSAGE:\n{last_text}"},
]
)
# D) Store ONLY new memories
if decision.should_write:
for mem in decision.memories:
if mem.is_new:
store.put(namespace, str(uuid.uuid4()), {"data": mem.text})
return {"messages": [{"role": "assistant", "content": "Noted."}]}
# ----------------------------
# 4) Build graph: START -> chat -> END
# ----------------------------
builder = StateGraph(MessagesState)
builder.add_node("chat", chat_creates_memory_node)
builder.add_edge(START, "chat")
builder.add_edge("chat", END)
graph = builder.compile(store=store)
config = {"configurable": {"user_id": "u1"}}
r1 = graph.invoke({"messages": [{"role": "user", "content": "My name is Nitish"}]}, config)
print("Assistant:", r1["messages"][-1].content)
# output: Assistant: Noted.
# Likely duplicate of the first memory -> is_new should be false -> saved=0
r2 = graph.invoke({"messages": [{"role": "user", "content": "I like Python for programming."}]}, config)
print("\nAssistant:", r2["messages"][-1].content)
# output:Assistant: Noted.
for it in store.search(("user", "u1", "details")):
print(it.value['data'])
# output:The user's name is Nitish.
# output:Nitish likes Python for programming.
Merged graph and production persistence
Final shape: start → remember (extract and save) → chat (read and reply) → end. The agent learns mid-conversation and uses the new facts immediately.
Merged Workflow
from dotenv import load_dotenv
load_dotenv()
import uuid
from typing import List
from pydantic import BaseModel, Field
from langchain_openai import ChatOpenAI
from langchain_core.messages import SystemMessage
from langchain_core.runnables import RunnableConfig
from langgraph.graph import StateGraph, START, END, MessagesState
from langgraph.store.memory import InMemoryStore
from langgraph.store.base import BaseStore
# ----------------------------
# 1) LTM store (START EMPTY)
# ----------------------------
store = InMemoryStore()
# ----------------------------
# 2) System prompt
# ----------------------------
SYSTEM_PROMPT_TEMPLATE = """You are a helpful assistant with memory capabilities.
If user-specific memory is available, use it to personalize
your responses based on what you know about the user.
Your goal is to provide relevant, friendly, and tailored
assistance that reflects the user’s preferences, context, and past interactions.
If the user’s name or relevant personal context is available, always personalize your responses by:
– Always Address the user by name (e.g., "Sure, Nitish...") when appropriate
– Referencing known projects, tools, or preferences (e.g., "your MCP server python based project")
– Adjusting the tone to feel friendly, natural, and directly aimed at the user
Avoid generic phrasing when personalization is possible.
Use personalization especially in:
– Greetings and transitions
– Help or guidance tailored to tools and frameworks the user uses
– Follow-up messages that continue from past context
Always ensure that personalization is based only on known user details and not assumed.
In the end suggest 3 relevant further questions based on the current response and user profile
The user’s memory (which may be empty) is provided as: {user_details_content}
"""
# ----------------------------
# 3) Memory extraction LLM
# ----------------------------
memory_llm = ChatOpenAI(model="gpt-4o-mini", temperature=0)
class MemoryItem(BaseModel):
text: str = Field(description="Atomic user memory")
is_new: bool = Field(description="True if new, false if duplicate")
class MemoryDecision(BaseModel):
should_write: bool
memories: List[MemoryItem] = Field(default_factory=list)
memory_extractor = memory_llm.with_structured_output(MemoryDecision)
MEMORY_PROMPT = """You are responsible for updating and maintaining accurate user memory.
CURRENT USER DETAILS (existing memories):
{user_details_content}
TASK:
- Review the user's latest message.
- Extract user-specific info worth storing long-term (identity, stable preferences, ongoing projects/goals).
- For each extracted item, set is_new=true ONLY if it adds NEW information compared to CURRENT USER DETAILS.
- If it is basically the same meaning as something already present, set is_new=false.
- Keep each memory as a short atomic sentence.
- No speculation; only facts stated by the user.
- If there is nothing memory-worthy, return should_write=false and an empty list.
"""
# ----------------------------
# 4) Node 1: remember
# ----------------------------
def remember_node(state: MessagesState, config: RunnableConfig, *, store: BaseStore):
user_id = config["configurable"]["user_id"]
ns = ("user", user_id, "details")
# existing memory
items = store.search(ns)
existing = "\n".join(it.value["data"] for it in items) if items else "(empty)"
# last user message
last_msg = state["messages"][-1].content
decision: MemoryDecision = memory_extractor.invoke(
[
SystemMessage(content=MEMORY_PROMPT.format(user_details_content=existing)),
{"role": "user", "content": last_msg},
]
)
if decision.should_write:
for mem in decision.memories:
if mem.is_new:
store.put(ns, str(uuid.uuid4()), {"data": mem.text})
return {} # no message change
# ----------------------------
# 5) Node 2: chat
# ----------------------------
chat_llm = ChatOpenAI(model="gpt-4o-mini")
def chat_node(state: MessagesState, config: RunnableConfig, *, store: BaseStore):
user_id = config["configurable"]["user_id"]
ns = ("user", user_id, "details")
items = store.search(ns)
user_details = "\n".join(it.value["data"] for it in items) if items else ""
system_msg = SystemMessage(
content=SYSTEM_PROMPT_TEMPLATE.format(
user_details_content=user_details or "(empty)"
)
)
response = chat_llm.invoke([system_msg] + state["messages"])
return {"messages": [response]}
# ----------------------------
# 6) Graph
# ----------------------------
builder = StateGraph(MessagesState)
builder.add_node("remember", remember_node)
builder.add_node("chat", chat_node)
builder.add_edge(START, "remember")
builder.add_edge("remember", "chat")
builder.add_edge("chat", END)
graph = builder.compile(store=store)
graph
# ----------------------------
# 7) Demo
# ----------------------------
config = {"configurable": {"user_id": "u1"}}
result = graph.invoke({"messages": [{"role": "user", "content": "Hi, my name is Nitish"}]}, config)
result['messages'][-1].content
# output:'Hi Nitish! It’s great to meet you. How can I assist you today?'
for it in store.search(("user", "u1", "details")):
print(it.value["data"])
result = graph.invoke({"messages": [{"role": "user", "content": "I teach AI on YouTube"}]}, config)
print(result['messages'][-1].content)
# output:That's great, Nitish! Teaching AI on YouTube must be really fulfilling. What topics do you cover in your videos? Are there any specific projects or concepts you find your audience is particularly interested in?
for it in store.search(("user", "u1", "details")):
print(it.value["data"])
# output:User's name is Nitish.
# output:Nitish teaches AI on YouTube.
result = graph.invoke({"messages": [{"role": "user", "content": "Explain GenAI simply"}]}, config)
print(result['messages'][-1].content)
# output:Sure, Nitish! Generative AI, often referred to as GenAI, is a type of artificial intelligence that can create new content based on the data it's trained on. This includes generating text, images, music, and even video.
# output:Here's a simple breakdown:
# output:1. **Learning from Examples:** GenAI is trained on vast amounts of data, learning the patterns, styles, and structures of the content it sees.
# output:2. **Creating Content:** Once trained, it can generate new content that resembles what it learned. For example, it can write a story in a specific style, create artwork, or compose music.
# output:3. **Applications:** It's used in various fields, from helping writers brainstorm ideas to producing artwork and even customer service chatbots that can engage with users in a conversational manner.
# output:If you're planning to teach this topic on your YouTube channel, emphasizing practical examples and real-world applications could be very engaging for your audience!
Do you want to explore specific applications of GenAI, tools for using it, or perhaps the ethics involved?
for it in store.search(("user", "u1", "details")):
print(it.value["data"])
# output:User's name is Nitish.
# output:Nitish teaches AI on YouTube.
InMemoryStore dies when the process exits. Run Postgres (often via Docker), install the Postgres checkpoint/store packages, and swap the store for a connection-backed implementation. After a full restart, querying the database should still return saved profile facts.
services:
postgres:
image: postgres:16
environment:
POSTGRES_USER: postgres
POSTGRES_PASSWORD: postgres
POSTGRES_DB: postgres
ports:
- "5442:5432"
! pip install -U "psycopg[binary,pool]" langgraph langgraph-checkpoint-postgres
from dotenv import load_dotenv
load_dotenv()
import uuid
from typing import List
from pydantic import BaseModel, Field
from langchain_openai import ChatOpenAI
from langchain_core.messages import SystemMessage
from langchain_core.runnables import RunnableConfig
from langgraph.graph import StateGraph, START, END, MessagesState
from langgraph.store.postgres import PostgresStore
from langgraph.store.base import BaseStore
# ----------------------------
# 2) System prompt
# ----------------------------
SYSTEM_PROMPT_TEMPLATE = """You are a helpful assistant with memory capabilities.
If user-specific memory is available, use it to personalize
your responses based on what you know about the user.
Your goal is to provide relevant, friendly, and tailored
assistance that reflects the user’s preferences, context, and past interactions.
If the user’s name or relevant personal context is available, always personalize your responses by:
– Always Address the user by name (e.g., "Sure, Nitish...") when appropriate
– Referencing known projects, tools, or preferences (e.g., "your MCP server python based project")
– Adjusting the tone to feel friendly, natural, and directly aimed at the user
Avoid generic phrasing when personalization is possible.
Use personalization especially in:
– Greetings and transitions
– Help or guidance tailored to tools and frameworks the user uses
– Follow-up messages that continue from past context
Always ensure that personalization is based only on known user details and not assumed.
In the end suggest 3 relevant further questions based on the current response and user profile
The user’s memory (which may be empty) is provided as: {user_details_content}
"""
# ----------------------------
# 3) Memory extraction LLM
# ----------------------------
memory_llm = ChatOpenAI(model="gpt-4o-mini", temperature=0)
class MemoryItem(BaseModel):
text: str = Field(description="Atomic user memory")
is_new: bool = Field(description="True if new, false if duplicate")
class MemoryDecision(BaseModel):
should_write: bool
memories: List[MemoryItem] = Field(default_factory=list)
memory_extractor = memory_llm.with_structured_output(MemoryDecision)
MEMORY_PROMPT = """You are responsible for updating and maintaining accurate user memory.
CURRENT USER DETAILS (existing memories):
{user_details_content}
TASK:
- Review the user's latest message.
- Extract user-specific info worth storing long-term (identity, stable preferences, ongoing projects/goals).
- For each extracted item, set is_new=true ONLY if it adds NEW information compared to CURRENT USER DETAILS.
- If it is basically the same meaning as something already present, set is_new=false.
- Keep each memory as a short atomic sentence.
- No speculation; only facts stated by the user.
- If there is nothing memory-worthy, return should_write=false and an empty list.
"""
# ----------------------------
# 3) Nodes
# ----------------------------
def remember_node(state: MessagesState, config: RunnableConfig, *, store: BaseStore):
user_id = config["configurable"]["user_id"]
ns = ("user", user_id, "details")
# existing memory (all items under namespace)
items = store.search(ns)
existing = "\n".join(it.value.get("data", "") for it in items) if items else "(empty)"
# latest user message
last_text = state["messages"][-1].content
decision: MemoryDecision = memory_extractor.invoke(
[
SystemMessage(content=MEMORY_PROMPT.format(user_details_content=existing)),
{"role": "user", "content": last_text},
]
)
if decision.should_write:
for mem in decision.memories:
if mem.is_new and mem.text.strip():
store.put(ns, str(uuid.uuid4()), {"data": mem.text.strip()})
return {}
chat_llm = ChatOpenAI(model="gpt-4o-mini")
def chat_node(state: MessagesState, config: RunnableConfig, *, store: BaseStore):
user_id = config["configurable"]["user_id"]
ns = ("user", user_id, "details")
items = store.search(ns)
user_details = "\n".join(it.value.get("data", "") for it in items) if items else ""
system_msg = SystemMessage(
content=SYSTEM_PROMPT_TEMPLATE.format(user_details_content=user_details or "(empty)")
)
response = chat_llm.invoke([system_msg] + state["messages"])
return {"messages": [response]}
# ----------------------------
# 4) Build graph
# ----------------------------
builder = StateGraph(MessagesState)
builder.add_node("remember", remember_node)
builder.add_node("chat", chat_node)
builder.add_edge(START, "remember")
builder.add_edge("remember", "chat")
builder.add_edge("chat", END)
<langgraph.graph.state.StateGraph at 0x110ce4a90>
# ----------------------------
# 5) Use PostgresStore (PERSISTENT LTM)
# ----------------------------
DB_URI = "postgresql://postgres:postgres@localhost:5442/postgres?sslmode=disable"
with PostgresStore.from_conn_string(DB_URI) as store:
# IMPORTANT: run ONCE the first time you use this database
store.setup()
graph = builder.compile(store=store)
config = {"configurable": {"user_id": "u1"}}
graph.invoke({"messages": [{"role": "user", "content": "Hi, my name is Nitish"}]}, config)
graph.invoke({"messages": [{"role": "user", "content": "I teach AI on YouTube"}]}, config)
out = graph.invoke({"messages": [{"role": "user", "content": "Explain GenAI simply"}]}, config)
print(out["messages"][-1].content)
print("\n--- Stored Memories (from Postgres) ---")
for it in store.search(("user", "u1", "details")):
print(it.value["data"])
# output:Sure, Nitish! Generative AI, or GenAI, refers to a type of artificial intelligence that can create new content, like images, text, music, or even code, on its own. It learns from a large dataset and uses patterns it recognizes to generate something that resembles what it has seen before.
# output:For example, if you input a topic or a few words into a generative AI model, it can produce a coherent piece of writing or generate a unique piece of art. Popular examples include models like GPT-3 for text and DALL-E for images.
# output:The key point is that GenAI is designed to take what it has learned and create new, original outputs based on that learning. If you’re discussing this concept in your YouTube teachings, it might be interesting for your audience to see how GenAI can assist in creative processes or even in automating certain tasks.
# output:Would you like to dive deeper into a specific application of GenAI, or perhaps explore its implications for teaching AI?
# output:--- Stored Memories (from Postgres) ---
# output:Nitish teaches AI on YouTube.
# output:User's name is Nitish.
Check Persistence
from langgraph.store.postgres import PostgresStore
DB_URI = "postgresql://postgres:postgres@localhost:5442/postgres?sslmode=disable"
with PostgresStore.from_conn_string(DB_URI) as store:
ns = ("user", "u1", "details")
items = store.search(ns)
for it in items:
print(it.value["data"])
# output: Nitish teaches AI on YouTube.
# output: User's name is Nitish.
Practical pitfalls when wiring LTM
Namespaces look trivial until two features share ("users", user_id) and overwrite each other’s keys. Prefer feature-scoped tuples such as ("users", user_id, "prefs") versus ("users", user_id, "facts"), and document who may write each. Keys should be stable ids, not free-text sentences; put the sentence in the value payload.
Semantic search quality tracks embedding choice and how memories are phrased. Storing “likes Python” and later querying “preferred programming language” works only if the embedding space clusters those phrases. Periodic re-embedding after model upgrades is boring operations work that prevents silent recall regressions.
Write paths need rate limits. An extractor that fires every user utterance can flood Postgres with near-duplicates even after is_new checks, especially when the model hedges. Cap writes per turn, batch end-of-session summaries, and monitor store growth per user. For production, pair the long-term store with a short-term checkpointer so thread-local dialogue and cross-thread profile memory stay conceptually separate even if they share infrastructure.
Read path hygiene
On the read side, never dump the entire namespace into the system prompt once personalization works in demos. Cap retrieved memories, cite which namespace keys contributed, and allow an operator to disable LTM per user when recall feels wrong. A personalization feature that cannot be turned off becomes a support nightmare. Also separate “profile facts” from “conversation summaries” in storage so a bad summary rotation cannot erase durable preferences. When migrating from InMemoryStore to Postgres, rehearse backup and restore of the memory tables the same way you rehearse checkpoint restores—LTM loss is user-visible amnesia, not just infra noise.
Teaching the extractor what “important” means
Prompts that say “save anything useful” produce junk. Prefer a closed checklist: identity, durable preferences, active projects, hard constraints, and explicitly volunteered reminders. Everything else stays in the thread checkpointer. Show the extractor three few-shot pairs of noisy dialogue versus the minimal memory JSON you want, and re-run those fixtures in CI when prompts change. Long-term memory quality is a prompt+schema product; treat it like one.
Operators should also rehearse “wrong memory” remediation: delete by key, re-extract from a corrected utterance, and confirm the chat node no longer cites the stale fact. Without that drill, LTM becomes a write-only junk drawer.