Skip to content
Agent Search Engine.

Agent Frameworks · Head-to-head

langchain vs LangGraph

langchain and LangGraph are both agent frameworks. langchain is The agent engineering platform, while LangGraph is langChain's low-level orchestration framework for stateful, controllable agents. Here's an independent, side-by-side look at how they compare — and which fits.

langchain

Framework· Open source

The agent engineering platform.

Visit langchain →
LangGraph

Framework· Open source

LangChain's low-level orchestration framework for stateful, controllable agents.

Visit LangGraph →

Bottom line

langchain and LangGraph are both open-source agent frameworks you can self-host for free. langchain has wider GitHub adoption — 147k stars vs 42k. Neither is universally better — pick by fit.

Building one yourself? How to choose an agent framework →

Side by side

SpeclangchainLangGraph
TypeFrameworkFramework
ModelOpen sourceOpen source
PricingOpen sourceOpen source
GitHub stars147,20142,413
LanguagePythonPython
LicenseMITMIT
Last activitySep 2026Sep 2026

Key differences

  • langchain has wider GitHub adoption — 147k stars vs 42k.

Choose langchain if

Builders who want composable primitives and the broadest ecosystem of integrations for LLM applications.

Choose LangGraph if

Production agents that need controllable, stateful, graph-based orchestration.

About langchain

The agent engineering platform.

Full langchain profile →

About LangGraph

LangGraph is LangChain's open-source, low-level orchestration framework for long-running, stateful agents. It provides durable execution that resumes where it left off after failures, human-in-the-loop inspection and editing of agent state, short-term and long-term memory, and deployment infrastructure, with LangSmith for tracing. Deep Agents is a higher-level package built on it, and LangGraph.js covers JavaScript and TypeScript.

Full LangGraph profile →

Frequently asked

What's the main difference between langchain and LangGraph?
langchain has wider GitHub adoption — 147k stars vs 42k.
Is langchain or LangGraph better?
Neither is universally better. langchain is the stronger fit for Builders who want composable primitives and the broadest ecosystem of integrations for LLM applications; LangGraph for Production agents that need controllable, stateful, graph-based orchestration. Use the side-by-side specs to decide by your own constraints.
Is langchain or LangGraph free?
langchain is free to run and self-host; LangGraph is free to run and self-host. Both are free to self-host — you only pay for the infrastructure and any model or API usage.
Which is more popular, langchain or LangGraph?
By GitHub stars — a proxy for open-source adoption — langchain is ahead (147k vs 42k). Stars measure attention, not necessarily the better fit for you.
For agent buildersMake your product part of the discovery.Explore advertising

More agent frameworks comparisons

All agent frameworks →