langgraph

Building stateful, multi-actor applications with LLMs

langgraph Permissive license MIT Active ★ 39,627 v1.2.11 released 2026-08-11

Install

langgraph on PyPI

pip

pip install langgraph

uv

uv add langgraph

poetry

poetry add langgraph

Package facts

License	MIT (permissive)
Python support	supports the current Python release (>=3.10)
Install friction	low — pure-Python wheel
Runtime dependencies	6 — langchain-core, langgraph-checkpoint, langgraph-prebuilt, langgraph-sdk, pydantic, xxhash
Maintenance	actively maintained — 2 days since the last release
Last repo commit	2026-08-12
First released	2024-01-08
Popularity	one of the top 1,000 most-downloaded packages on PyPI (30-day window, as of 2026-08-13)
Known vulnerabilities	none known (OSV.dev, checked 2026-08-13)

Evidence: langgraph-1.2.11-py3-none-any.whl

Development Status :: 5 - Production/StableProgramming Language :: PythonProgramming Language :: Python :: 3Programming Language :: Python :: 3 :: OnlyProgramming Language :: Python :: 3.10Programming Language :: Python :: 3.11Programming Language :: Python :: 3.12Programming Language :: Python :: 3.13Programming Language :: Python :: Implementation :: CPythonProgramming Language :: Python :: Implementation :: PyPy

About langgraph

from the package's own PyPI description — quoted content, verbatim

🦜🕸️ LangGraph

PyPI - Version (image) PyPI - License (image) PyPI - Downloads (image) Open Issues (image) Twitter (image)

Looking for the JS/TS version? Check out LangGraph.js.

To help you ship LangGraph apps to production faster, check out LangSmith. LangSmith is a unified developer platform for building, testing, and monitoring LLM applications.

Quick Install

uv add langgraph

🤔 What is this?

LangGraph is a low-level orchestration framework for building, managing, and deploying long-running, stateful agents. LangGraph provides the...

Read as markdown · JSON record · Source repository · Homepage · Docs

AI interpretation — verify before relying

AI-generated interpretation of the package facts above; every digit, version, license, or vulnerability id it cites is grounded in the facts already shown on this page

LangGraph is a low-level orchestration framework for building stateful, long-running agents with durable execution, streaming, persistence, and human-in-the-loop capabilities.

Low install friction with a pure-wheel distribution and six runtime dependencies. Actively maintained with a release 2 days ago and strong community backing.

MIT license permits unrestricted commercial and private use, modification, and redistribution with minimal obligations—only attribution required.

Usage

pip install langgraph

from langgraph.graph import StateGraph
from pydantic import BaseModel

class State(BaseModel):
    value: str

graph = StateGraph(State)

Requires Python 3.10 or later; langchain-core, langgraph-checkpoint, langgraph-prebuilt, and langgraph-sdk must be installed as runtime dependencies.

Verdict: LangGraph is a production-ready, actively maintained orchestration framework for building advanced agentic applications. With no known vulnerabilities, permissive MIT licensing, low install friction, and strong adoption signals, it is a solid choice for teams needing deterministic and agentic workflow control.

Needs verification

Whether the six runtime dependencies introduce transitive vulnerabilities or significant additional install complexity.
Performance characteristics and latency overhead compared to simpler agent frameworks for basic use cases.
Specific human-in-the-loop and persistence mechanisms available out-of-the-box versus requiring langgraph-checkpoint or langgraph-prebuilt.

agent orchestration frameworkstateful workflow executionllm agent persistenceagentic application frameworklong-running agent managementgraph-based agent workflowshuman-in-the-loop agents