LangChain v1 is under active development and is not recommended for production use.
  • APIs may change without notice
  • The docs are incomplete and subject to change
For the latest stable version, see the v0 LangChain docs.
LangChain is the easiest way to start building with LLMs, letting you get started on building agents with OpenAI, Anthropic, Google, and more in under 10 lines of code. LangChain agents are built on top of LangGraph in order to provide durable execution, streaming, human-in-the-loop, persistence, and more. You do not need to know LangGraph for basic LangChain agent usage.

​
Install

pip install --pre -U langchain

​
Create an agent

# pip install -qU "langchain[anthropic]" to call the model

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="anthropic:claude-3-7-sonnet-latest",
    tools=[get_weather],
    prompt="You are a helpful assistant",
)

# Run the agent
agent.invoke(
    {"messages": [{"role": "user", "content": "what is the weather in sf"}]}
)

​
Core benefits

Standard Model Interface

Different providers have unique APIs for interacting with models, including the format of responses. LangChain standardizes how you interact with models so that you can seamlessly swap providers and avoid lock-in.

Easy to use, yet highly flexible agent

LangChain’s agent abstraction is designed to be easy to get started with, letting you build a simple agent in ~10 lines of code. But it also provides enough flexibility to allow you to do all the context engineering your heart desires.

Built on top of LangGraph

LangChain’s agents are built on top of LangGraph. This allows us to take advantage of LangGraph’s durable execution, human-in-the-loop support, persistence, and more.

Debugging with LangSmith

Gain deep visibility into complex agent behavior with visualization tools that trace execution paths, capture state transitions, and provide detailed runtime metrics.