Balance agent control with agency
Design agents that reliably handle complex tasks with LangGraph, an agent runtime and low-level orchestration framework.
How does LangGraph help?
Guide, moderate, and control your agent with human-in-the-loop
Prevent agents from veering off course with easy-to-add moderation and quality controls. Add human-in-the-loop checks to steer and approve agent actions.
Build expressive, customizable agent workflows
LangGraph’s low-level primitives provide the flexibility needed to create fully customizable agents. Design diverse control flows — single, multi-agent, hierarchical — all using one framework.
Persist memory for future interactions
LangGraph’s built-in memory stores conversation histories and maintains context over time, enabling rich, personalized interactions across sessions.
First-class streaming for better UX design
Bridge user expectations and agent capabilities with native token-by-token streaming, showing agent reasoning and actions in real time.
Foundation: Introduction to LangGraph
Learn the basics of LangGraph in this LangChain Academy Course. You'll learn about how to leverage state, memory, human-in-the-loop, and more for your agents.
Developers trust LangGraph to build reliable agents
Build and ship agents fast with any model provider. Use high-level abstractions or fine-grained control as needed.
“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.”
“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.”
“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.”
LangGraph FAQs
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.
LangGraph will not add any overhead to your code and is specifically designed with streaming workflows in mind.
Yes. LangGraph is an MIT-licensed open-source library and is free to use.
See what your agent is really doing
LangSmith, our agent engineering platform, helps developers debug every agent decision, eval changes, and deploy in one click.