---
title: "LangGraph: features, version and quickstart · DotsAgent"
description: "LangGraph by LangChain Inc.: licence, latest version, MCP support, durable runs, human approval, tracing and evals, plus a quickstart to copy."
url: https://dotsagent.io/frameworks/langgraph
---

Framework · LangChain Inc.

# 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](https://github.com/langchain-ai/langgraph) · 42,550 stars
- **Hosted option**: [LangSmith Deployment (formerly LangGraph Platform)](https://docs.langchain.com/oss/python/langgraph/overview)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)

`Install`

```
pip install -U langchain
```

Needs Provider API key, e.g. OPENAI_API_KEY

`Python (LangChain create_agent)`

```
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](https://docs.langchain.com/oss/python/langchain/quickstart)

### Python (raw LangGraph)

`Install`

```
pip install -U langgraph
```

`Python (raw 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](https://docs.langchain.com/oss/python/langgraph/overview)

## Features

| Any model | — | — |
| --- | --- | --- |
| MCP client | — | Via langchain-mcp-adapters |
| MCP server | — | — |
| Multi-agent | — | Subgraphs; the Deep Agents harness adds subagents |
| Durable runs | — | Checkpointers for Postgres or SQLite; resume after failures |
| Human approval | — | Interrupts let you inspect and edit state mid-run |
| Tracing | — | Via LangSmith, with LANGSMITH_TRACING=true |
| Evals | — | Evaluation lives in LangSmith, not the open-source library |

## 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

- [OpenAI Agents SDK](https://dotsagent.io/frameworks/openai-agents-python)

- [OpenAI Agents SDK (JS)](https://dotsagent.io/frameworks/openai-agents-js)

- [Claude Agent SDK](https://dotsagent.io/frameworks/claude-agent-sdk)

- [Google ADK](https://dotsagent.io/frameworks/google-adk)

- [Microsoft Agent Framework](https://dotsagent.io/frameworks/microsoft-agent-framework)

- [CrewAI](https://dotsagent.io/frameworks/crewai)

## Sources

1. [docs.langchain.com](https://docs.langchain.com/oss/python/langgraph/overview)/oss/python/langgraph/overview
2. [docs.langchain.com](https://docs.langchain.com/oss/python/langchain/quickstart)/oss/python/langchain/quickstart
3. [pypi.org](https://pypi.org/pypi/langgraph/json)/pypi/langgraph/json
4. [pypi.org](https://pypi.org/pypi/langchain/json)/pypi/langchain/json
5. [registry.npmjs.org](https://registry.npmjs.org/@langchain%2flanggraph)/@langchain%2flanggraph
6. [api.github.com](https://api.github.com/repos/langchain-ai/langgraph)/repos/langchain-ai/langgraph

Independent reference for people who build AI agents. Not affiliated with any vendor named here.

© 2026 DotsAgent · Facts checked October 1, 2026