Agent framework - verified
LangGraph: features, install and latest version
LangGraph is an AI agent framework maintained by LangChain Inc. As its docs describe it: LangGraph is a low-level orchestration framework and runtime from LangChain Inc for building, managing, and deploying long-running, stateful agents, and it can be used with or without LangChain. It supports Python and TypeScript. License: MIT. Latest releases: Python package langgraph 1.2.16 (October 16, 2026) and TypeScript package @langchain/langgraph 1.5.1 (October 16, 2026).
Homepage - Source on GitHub - License - In our tools directory
- Languages
- 2
- Latest Python
- 1.2.16
- Released
- 2026-10-16
- Features documented
- 6 of 10
Install
Copied verbatim from the page linked under each command.
Python
pip install -U langgraphuv add langgraphTypeScript
npm install @langchain/langgraph @langchain/coreQuickstart
The first example from the official docs, unchanged. It may need an API key for the model provider it calls.
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!"}]})Features
What the LangGraph docs say it supports. Not stated means the docs do not say either way.
| Feature | Value | Source |
|---|---|---|
| MCP | Not stated | Docs do not say |
| Multi-agent | Yes | docs.langchain.com/oss/python/langgraph/use-subgraphs |
| Durable execution | Yes | docs.langchain.com/oss/python/langgraph/persistence |
| Human in the loop | Yes | docs.langchain.com/oss/python/langgraph/interrupts |
| Streaming | Yes | docs.langchain.com/oss/python/langgraph/streaming |
| Structured output | Not stated | Docs do not say |
| Tracing | Yes | docs.langchain.com/oss/python/langgraph/overview |
| Memory | Yes | docs.langchain.com/oss/python/langgraph/overview |
| Evals | Not stated | Docs do not say |
| Model-agnostic | Not stated | Docs do not say |
| Languages | Python, TypeScript | See sources below |
| License | MIT | github.com/langchain-ai/langgraph/blob/main/LICENSE |
| Latest Python release | langgraph 1.2.16October 16, 2026 | pypi.org/project/langgraph/1.2.16 |
| Latest TypeScript release | @langchain/langgraph 1.5.1October 16, 2026 | npmjs.com/package/@langchain/langgraph/v/1.5.1 |
LangGraph on Developers Digest
Compare LangGraph
- LangGraph vs Google Agent Development Kit (ADK)
- Pydantic AI vs LangGraph
- Microsoft Agent Framework vs LangGraph
- LlamaIndex (agent workflows) vs LangGraph
- LangGraph vs CrewAITool comparison
- Claude Agent SDK vs LangGraphArticle
- Mastra vs LangGraph.jsArticle
- Vercel AI SDK vs LangGraphArticle
- LangGraph in our tools directoryTool page
- All agent frameworks in one tableFeature matrix
FAQ
Does LangGraph support MCP?
Its official docs, read on October 18, 2026, do not say.
Which languages does LangGraph support?
Python and TypeScript. Published packages: langgraph (Python) and @langchain/langgraph (TypeScript).
How do I install LangGraph?
For Python: "pip install -U langgraph", as shown at https://docs.langchain.com/oss/python/langgraph/overview. This page lists 3 install commands, each copied from the linked source.
What is the latest version of LangGraph?
As of October 18, 2026: Python package langgraph 1.2.16 (October 16, 2026), https://pypi.org/project/langgraph/1.2.16/ and TypeScript package @langchain/langgraph 1.5.1 (October 16, 2026), https://www.npmjs.com/package/@langchain/langgraph/v/1.5.1.
What license is LangGraph released under?
MIT. The license is at https://github.com/langchain-ai/langgraph/blob/main/LICENSE.
Does LangGraph support durable execution?
Yes, per https://docs.langchain.com/oss/python/langgraph/persistence
Does LangGraph support human-in-the-loop?
Yes, per https://docs.langchain.com/oss/python/langgraph/interrupts
Is LangGraph model-agnostic?
Its official docs, read on October 18, 2026, do not say.
Which features does LangGraph document?
6 of the 10 tracked here: Multi-agent, Durable execution, Human in the loop, Streaming, Tracing and Memory. Not stated in its docs: MCP, Structured output, Evals and Model-agnostic.
Sources
Last verified from the pages below.
- LangGraph overview (docs) - docs.langchain.com
- GitHub README - github.com
- LICENSE - github.com
- PyPI langgraph - pypi.org
- npm @langchain/langgraph - npmjs.com
- LangGraph.js install - docs.langchain.com
- Persistence - docs.langchain.com
- Interrupts - docs.langchain.com
- Streaming - docs.langchain.com
- Subgraphs - docs.langchain.com
Newsletter
Agent frameworks, every week
One email per week. Framework releases, new agent tooling and what they mean for what you build.