LangGraph

Package

Open-source framework for building stateful, long-running agents as graphs

Price: Free, open source
Access: None, runs locally

About

LangGraph is LangChain's MIT-licensed, low-level orchestration runtime for agents and workflows in Python and JavaScript. It gives durable execution, streaming and human-in-the-loop, but you design the graph yourself. Hosted deployment is a separate LangSmith product.

What you can do with it

Build a multi-step agent that mixes LLM calls with fixed code steps
Pause a workflow for human approval and resume it later
Persist agent state with checkpointers so runs survive failures

Get started

Install the library with pip install -U langgraph
Add your LLM calls and tools as graph nodes

Example

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!"}]})

Details

Hosting: Runs locally
Available in: Worldwide
Official SDKs: Python, JavaScript/TypeScript
MCP server: None