LangGraph at a glance

LangChain's low-level library for agents built as explicit graphs, with checkpointed state and interrupts at its core. LangChain v1's create_agent runs on top of it for when a prebuilt loop is enough.

Best for: Long-running, stateful agents where you want to control every step and resume after failures.

Key facts

Maintainer

LangChain Inc.

Languages

Python, TypeScript, JavaScript

Licence

MIT

Latest version

langgraph 1.2.12 / langchain 1.4.3 · September 28, 2026

Repository

langchain-ai/langgraph · 42,550 stars

Hosted option

LangSmith Deployment (formerly LangGraph Platform)

Formerly LangGraph Platform; Studio covers visual prototyping.

Quickstart

Install the package, set the credentials, then run the smallest agent from the official docs. Model IDs are the ones the docs use and may not be enabled on your account.

Python (LangChain create_agent)

pip install -U langchain

Needs Provider API key, e.g. OPENAI_API_KEY

from langchain.agents import create_agent

def get_weather(city: str) -> str:
    """Get weather for a given city."""
    return f"It's always sunny in {city}!"

agent = create_agent(
    model="openai:gpt-5.5",
    tools=[get_weather],
    system_prompt="You are a helpful assistant",
)

result = agent.invoke(
    {"messages": [{"role": "user", "content": "What's the weather in San Francisco?"}]}
)
print(result["messages"][-1].content_blocks)

Quickstart source

Python (raw LangGraph)

pip install -U langgraph

from langgraph.graph import StateGraph, MessagesState, START, END

def mock_llm(state: MessagesState):
    return {"messages": [{"role": "ai", "content": "hello world"}]}

graph = StateGraph(MessagesState)
graph.add_node(mock_llm)
graph.add_edge(START, "mock_llm")
graph.add_edge("mock_llm", END)
graph = graph.compile()

graph.invoke({"messages": [{"role": "user", "content": "hi!"}]})

Quickstart source

Features

Recent changes

• LangChain v1 agents (create_agent) are now built on LangGraph.
• LangGraph Platform was renamed LangSmith Deployment.
• Deep Agents, a harness on top of LangGraph, adds subagents.

Alternatives in the same language