Balance agent control with agency

Gain control with LangGraph to design agents that reliably handle complex tasks. Build and scale agentic applications with LangGraph Platform.

Introduction to LangGraph

Learn the basics of LangGraph in this LangChain Academy Course. You'll learn how to build agents that automate real-world tasks with LangGraph orchestration.

Enroll for freeBook enterprise training

Controllable cognitive architecture for any task

LangGraph's flexible framework supports diverse control flows – single agent, multi-agent, hierarchical, sequential – and robustly handles realistic, complex scenarios.

Ensure reliability with easy-to-add moderation and quality loops that prevent agents from veering off course.

Use LangGraph Platform to templatize your cognitive architecture so that tools, prompts, and models are easily configurable with LangGraph Platform Assistants.

See the docs

Designed for human-agent collaboration

With built-in statefulness, LangGraph agents seamlessly collaborate with humans by writing drafts for review and awaiting approval before acting. Easily inspect the agent’s actions and "time-travel" to roll back and take a different action to correct course.

Read a conceptual guide

First class streaming support for better UX design

Bridge user expectations and agent capabilities with native token-by-token streaming and streaming of intermediate steps, helpful for showing agent reasoning and actions back to the user as they happen. Use LangGraph Platform's API to deliver dynamic and interactive user experiences.

Learn more

Deploy agents at scale, monitor carefully, iterate boldly

Design agent-driven user experiences with LangGraph Platform's APIs. Quickly deploy and scale your application with infrastructure built for agents. Choose from multiple deployment options.

Fault-tolerant scalability

Handle large workloads gracefully with horizontally-scaling servers, task queues, and built-in persistence. Enhance resilience with intelligent caching and automated retries.

Dynamic APIs for designing agent experience

Craft personalized user experiences with APIs featuring long-term memory to recall information across conversation sessions. Track, update, and rewind your app's state for easy human steering and interaction. Kick off long-running background jobs for research-style or multi-step work.

Integrated developer experience

Simplify prototyping, debugging, and sharing of agents in our visual LangGraph Studio. Deploy your application with 1-click deploy with our SaaS offering or within your own VPC. Then, monitor app performance with LangSmith.

Trusted by companies taking agency in AI innovation:

LangGraph helps teams of all sizes, across all industries, from ambitious
startups to established enterprises.

“LangChain is streets ahead with what they've put forward with LangGraph. LangGraph sets the foundation for how we can build and scale AI workloads — from conversational agents, complex task automation, to custom LLM-backed experiences that 'just work'. The next chapter in building complex production-ready features with LLMs is agentic, and with LangGraph and LangSmith, LangChain delivers an out-of-the-box solution to iterate quickly, debug immediately, and scale effortlessly.”

Garrett Spong
Principal SWE

“LangGraph has been instrumental for our AI development. Its robust framework for building stateful, multi-actor applications with LLMs has transformed how we evaluate and optimize the performance of our AI guest-facing solutions. LangGraph enables granular control over the agent's thought process, which has empowered us to make data-driven and deliberate decisions to meet the diverse needs of our guests.”

Andres Torres
Sr. Solutions Architect

“It's easy to build the prototype of a coding agent, but deceptively hard to improve its reliability. Replit wants to give a coding agent to millions of users — reliability is our top priority, and will remain so for a long time. LangGraph is giving us the control and ergonomics we need to build and ship powerful coding agents.”

“As Ally advances its exploration of Generative AI,

Michele Catasta
President

“As Ally advances its exploration of Generative AI, our tech labs is excited by LangGraph, the new library from LangChain, which is central to our experiments with multi-actor agentic workflows. We are committed to deepening our partnership with LangChain.”

“As Ally advances its exploration of Generative AI,

Sathish Muthukrishnan
Chief Information, Data and Digital Officer

“LangChain is streets ahead with what they've put forward with LangGraph. LangGraph sets the foundation for how we can build and scale AI workloads — from conversational agents, complex task automation, to custom LLM-backed experiences that 'just work'. The next chapter in building complex production-ready features with LLMs is agentic, and with LangGraph and LangSmith, LangChain delivers an out-of-the-box solution to iterate quickly, debug immediately, and scale effortlessly.”

Garrett Spong
Principal SWE

“LangGraph has been instrumental for our AI development. Its robust framework for building stateful, multi-actor applications with LLMs has transformed how we evaluate and optimize the performance of our AI guest-facing solutions. LangGraph enables granular control over the agent's thought process, which has empowered us to make data-driven and deliberate decisions to meet the diverse needs of our guests.”

Andres Torres
Sr. Solutions Architect

“It's easy to build the prototype of a coding agent, but deceptively hard to improve its reliability. Replit wants to give a coding agent to millions of users — reliability is our top priority, and will remain so for a long time. LangGraph is giving us the control and ergonomics we need to build and ship powerful coding agents.”

“As Ally advances its exploration of Generative AI,

Michele Catasta
President

“As Ally advances its exploration of Generative AI, our tech labs is excited by LangGraph, the new library from LangChain, which is central to our experiments with multi-actor agentic workflows. We are committed to deepening our partnership with LangChain.”

“As Ally advances its exploration of Generative AI,

Sathish Muthukrishnan
Chief Information, Data and Digital Officer

LangGraph FAQs

Do I need to use LangChain to use LangGraph? What’s the difference?

No. LangGraph is an orchestration framework for complex agentic systems and is more low-level and controllable than LangChain agents. LangChain provides a standard interface to interact with models and other components, useful for straight-forward chains and retrieval flows.

How is LangGraph different from other agent frameworks?

Other agentic frameworks can work for simple, generic tasks but fall short for complex tasks bespoke to a company’s needs. LangGraph provides a more expressive framework to handle companies’ unique tasks without restricting users to a single black-box cognitive architecture.

Does LangGraph impact the performance of my app?

LangGraph will not add any overhead to your code and is specifically designed with streaming workflows in mind.

Is LangGraph open source? Is it free?

Yes. LangGraph is an MIT-licensed open-source library and is free to use.

How are LangGraph and LangGraph Platform different?

LangGraph is a stateful, orchestration framework that brings added control to agent workflows. LangGraph Platform is a service for deploying and scaling LangGraph applications, with an opinionated API for building agent UXs, plus an integrated developer studio.

LangGraph (open source)
LangGraph Platform
Features
Stateful orchestration framework for agentic applications
Scalable infrastructure for deploying LangGraph applications
Python and JavaScript
Python and JavaScript
None
Yes - useful for retrieving & updating state or long-term memory, or creating a configurable assistant
Basic
Dedicated mode for token-by-token messages
Community contributed
Supported out-of-the-box
Self-managed
Managed Postgres with efficient storage
Self-managed
- Cloud SaaS
- Free self-hosted
-  Enterprise
(BYOC or paid self-hosted)
Self-managed
Auto-scaling of task queues and servers
Self-managed
Automated retries
Simple threading
Supports double-texting
None
Cron scheduling
None
Integrated with LangSmith for observability
LangGraph Studio for Desktop
LangGraph Studio for Desktop & Cloud
What are my deployment options for LangGraph Platform?

We currently have the following deployment options for LangGraph applications:

Self-Hosted Lite: A free (up to 1M nodes executed), limited version of LangGraph Platform that you can run locally or in a self-hosted manner. This version requires a LangSmith API key and logs all usage to LangSmith. Fewer features are available than in paid plans.
Cloud SaaS: Fully managed and hosted as part of LangSmith, with automatic updates and zero maintenance.
Bring Your Own Cloud (BYOC): Deploy LangGraph Platform within your VPC, provisioned and run as a service. Keep data in your environment while outsourcing the management of the service.
Self-Hosted Enterprise: Deploy LangGraph entirely on your own infrastructure.

Is LangGraph Platform open source?

No. LangGraph Platform is proprietary software.

There is a free, self-hosted version of LangGraph Platform with access to basic features. The Cloud SaaS deployment option is free while in beta, but will eventually be a paid service. We will always give ample notice before charging for a service and reward our early adopters with preferential pricing. The Bring Your Own Cloud (BYOC) and Self-Hosted Enterprise options are also paid services. Contact our sales team to learn more.

For more information, see our LangGraph Platform pricing page.

Ready to start shipping 
reliable GenAI apps faster?

Get started with LangChain, LangSmith, and LangGraph to enhance your LLM app development, from prototype to production.