Getting Started

LangChain Tools

Five structured memory tools that let a LangChain agent store, search, list, update and delete memories — with scoping, idempotent writes, and failures that never abort an agent run.

The tool set

Tool	What it does
`add_memory`	Save one durable fact or preference. Repeats are recognised, not duplicated.
`search_memory`	Semantic search over the user’s memories, with relevance scores.
`list_memories`	Newest-first listing, for "what do you remember about me?".
`update_memory`	Change tags or importance by id. Memory text is immutable.
`delete_memory`	Permanently delete one memory by id.

Create the tools

from langchain.agents import create_agent
from langchain_memorysync import create_memorysync_tools

tools = create_memorysync_tools(end_user_id="user-123")
agent = create_agent(model, tools=tools)

agent.invoke({"messages": [{"role": "user", "content": "Remember that I'm allergic to peanuts."}]})

The factory also works with LangGraph’s create_react_agent and the legacy AgentExecutor on 0.3.x — the tools are plain structured tools, nothing framework-version specific.

Scope to the right user

Pass end_user_id whenever the key belongs to an organisation. It is what keeps one customer’s memories out of another’s session: every tool call is isolated to that user, and a delete cannot reach another user’s memory even by id.

tools = create_memorysync_tools(
    end_user_id="user-123",
    read_only=True,  # only search_memory and list_memories
)

Write behaviour worth knowing

add_memory derives an idempotency key from the content, so an agent that repeats "remember X" gets "already stored" instead of a duplicate.
Extraction judges what is durable: transient chit-chat comes back as "nothing stored" with guidance to rephrase, not as a memory.
Memory text is immutable by design — the update tool changes tags and importance, and replacing a fact is delete plus add, which keeps history auditable.
Over-quota writes degrade silently server-side; the agent sees a normal response rather than a billing error to narrate to the end user.

Where to go next

LangChain Memory

Persist chat history and build recall context.

Agent Memory

The policy for what agents should store.

MCP Memory Tools

The same capabilities over the Model Context Protocol.

Was this page helpful?

← Previous

Memory & Chat History

Advanced Overview