langgraph
Building stateful, multi-actor applications with LLMs
Decision gist · record as of 2026-08-14
Yes, if you need to build stateful, long-running agents with fine-grained control over orchestration, durable execution, and human-in-the-loop workflows. The framework is production-stable, actively maintained, and has no known vulnerabilities. Install it when LangChain's pre-built agent abstractions are too rigid for your use case. Skip it if you want quick prototyping or simple agent patterns—use LangChain directly instead.AI-flagged interpretation of the facts on this page — verify before relying
Before you install
- Requires Python 3.10 or later; depends on langchain-core and pydantic at runtime.
- Low friction install with a pure-Python wheel.
- Active maintenance with a release 3 days old and last commit on 2026-08-13.
License · maintenance · safety
MIT (permissive) — MIT license (permissive) allows commercial and private use with minimal restrictions.
last release 2026-08-11 (3 days) · last repo commit 2026-08-13 · 39,639 stars
0 known vulnerabilities (OSV.dev, 2026-08-14) · 72,703,662 downloads/mo, #459 on PyPI
Alternatives
Verify before relying
pip install langgraph
from langgraph.graph import StateGraph
from pydantic import BaseModel
class State(BaseModel):
messages: list
graph = StateGraph(State)
# Define nodes and edges, then compile and invoke- Whether the framework's learning curve and customization requirements match your team's capacity for advanced orchestration.
- Performance characteristics and latency guarantees for your specific agent workloads and scale.
What it is and what it does
LangGraph is a framework for orchestrating complex, stateful agent applications built on LLMs. It sits below higher-level libraries like LangChain, providing low-level control over deterministic and agentic workflows, durable execution across restarts, streaming, human-in-the-loop checkpoints, and persistent state management. It is designed for teams with advanced requirements who need fine-grained control over agent behavior, latency, and customization rather than quick prototyping.
The package is actively maintained, production-stable, and trusted by companies including Klarna, Replit, and Elastic for shipping AI applications at scale. It depends on langchain-core, pydantic, and related LangChain ecosystem packages, making it a natural choice if you are already working within that ecosystem. The framework is inspired by Pregel and Apache Beam and draws its public interface from NetworkX.
Use it for
- Build multi-step agentic workflows with deterministic control flow and human approval gates between steps.
- Implement long-running agents that persist state across restarts and resume from checkpoints.
- Create streaming agent applications that yield intermediate results to clients in real time.
- Coordinate multi-actor systems where different LLM agents or tools interact in a controlled, stateful manner.
- Deploy production agent systems that require careful latency tuning and custom memory/persistence backends.
Worth the install?
AI-flagged interpretation of the facts on this page. Verify before relying on it.
Yes, if you need to build stateful, long-running agents with fine-grained control over orchestration, durable execution, and human-in-the-loop workflows.
The framework is production-stable, actively maintained, and has no known vulnerabilities. Install it when LangChain's pre-built agent abstractions are too rigid for your use case. Skip it if you want quick prototyping or simple agent patterns—use LangChain directly instead.
Install
langgraph on PyPI
Before you install
Low friction install with a pure-Python wheel. Active maintenance with a release 3 days old and last commit on 2026-08-13. Depends on six runtime packages including langchain-core and pydantic, all within the LangChain ecosystem.
Requires Python 3.10 or later; depends on langchain-core and pydantic at runtime.
License in practice
MIT license (permissive) allows commercial and private use with minimal restrictions.
Quickstart
pip install langgraph
from langgraph.graph import StateGraph
from pydantic import BaseModel
class State(BaseModel):
messages: list
graph = StateGraph(State)
# Define nodes and edges, then compile and invokeVerify before relying
- Whether the framework's learning curve and customization requirements match your team's capacity for advanced orchestration.
- Performance characteristics and latency guarantees for your specific agent workloads and scale.
Package facts
| License | MIT permissive |
| Python support | Supports the current Python release >=3.10 |
| Install friction | Low. Pure-Python wheel |
| Runtime dependencies | 6 packageslangchain-corelanggraph-checkpointlanggraph-prebuiltlanggraph-sdkpydanticxxhash |
| Maintenance | Actively maintained 3 days since the last release |
| Last repo commit | |
| First released | |
| Downloads | 72,703,662 / month, #459 on PyPI 30-day window, as of 2026-08-14 |
| Known vulnerabilities | None known OSV.dev, checked 2026-08-14 |
| Classifiers | 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 |
Evidence: langgraph-1.2.11-py3-none-any.whl
Tags
Let your AI agent find packages like this
Example. Real query, live index.
You found this page by searching. An agent finds it by wishing: SkillFed indexes 14,416 PyPI packages by what they can do, searchable in plain language.
wish › “stateful agent framework”
- langgraphLangGraph is a low-level orchestration framework for building…
- mistralai-vibe-sdkPython SDK for building and running Vibe agents with stateful…
- agent-framework-azurefunctionsHosts Microsoft Agent Framework agents on Azure Durable Functions,…
Give your agent the search over MCP, or paste the wish link into any chat.
More Application Frameworks packages
FastAPI is a Python web framework for building REST APIs using type hints, with automatic request validation, serialization, and interactive API documentation.
Provides a way to document function parameters, class attributes, return types, and variables inline using Python's `Annotated` type hint syntax instead of traditional docstrings.
Textual is a Python framework for building cross-platform user interfaces that run in the terminal or web browser using a modern, component-based API.
Install it if you're developing CLI tools, dashboards, or interactive terminal applications.
Typer builds command-line applications from Python functions using type hints, automatically generating help text, argument parsing, and shell completion.
Install it if you are building CLIs in Python.
Build and connect to Model Context Protocol servers that expose tools, resources, and prompts to LLM applications over stdio, HTTP, or SSE transports.
Install it if you need to build or connect to servers.
Werkzeug is a WSGI utility library providing request/response objects, URL routing, an interactive debugger, HTTP utilities, and a development server for building web applications.
See also bernstein · conductor-python · langchain · langgraph-sdk · langgraph-runtime-inmem · langchain-protocol · langgraph-cli · langgraph-supervisor · copilotkit · langgraph-prebuilt