LangGraph
In plain wordsA free software library for building AI agents as flowcharts of steps that share a memory, so developers control exactly how an agent moves between steps, pauses and resumes.
An open-source library, in Python and JavaScript, from the company behind LangChainLangChain, prop. n.: A popular free software toolkit, and the company behind it, for building applications that connect AI language models to documents, databases, tools and multi-step workflows., in which an agentAI agent, n.: An AI system that does not just answer but acts: given a goal, it decides on steps, uses tools such as a browser or code editor, checks the results and keeps going until the job is done. or a team of agents is written as a graph whose steps share a persistent state, suited to long-running work. Developers define a shared state schema, nodes (functions or model calls that read and update the state) and edges, including conditional edges chosen at run time; unlike linear chains, graphs may contain cycles, which express agent loops, retries and self-correction. A checkpointer saves state after every step, enabling durable execution that resumes after failures, memory across sessions, rewinding to earlier states for debugging, and human-in-the-loophuman-in-the-loop, adj.: Describes AI systems in which a person checks, corrects or approves the machine's work at key points, rather than letting it act entirely on its own. interrupts in which execution pauses for a person to approve or edit before continuing. Its execution model draws on Google's Pregel system for large-scale graph processing. LangGraph is the runtime beneath LangChain 1.0's agents and can also be used alone; the company sells a platform for deploying and monitoring LangGraph applications.
We built the refund agent in LangGraph so it pauses for a manager's approval before issuing anything over $500.
Origin
Announced by LangChain on 17 January 2024, after developers found linear chains too rigid for agents with loops and branches. Version 1.0 shipped alongside LangChain 1.0 on 22 October 2025, with a commitment to avoid breaking changes until version 2.0.
Usage note
An example of a graph-based agent frameworkagent framework, n.: A software library that gives developers ready-made parts for building AI agents — model connections, tool handling, memory, multi-agent coordination and logging — so they need not write everything from scratch.; compare CrewAICrewAI, prop. n.: A free software framework for setting up teams of AI agents, each given a job title, goal and backstory, that divide up tasks and work through them together like a small staff.'s role-based crews and AutoGenAutoGen, prop. n.: A free Microsoft software framework for building teams of AI agents that solve problems by messaging one another, writing and running code, and asking people for help when needed.'s conversing agents.
Related
- LangChainLangChain, prop. n.: A popular free software toolkit, and the company behind it, for building applications that connect AI language models to documents, databases, tools and multi-step workflows.
- agent frameworkagent framework, n.: A software library that gives developers ready-made parts for building AI agents — model connections, tool handling, memory, multi-agent coordination and logging — so they need not write everything from scratch.
- orchestrationorchestration, n.: Coordinating several AI calls, tools or agents so each does its part in the right order and their results are combined into one finished piece of work, as a conductor directs an orchestra.
- human-in-the-loophuman-in-the-loop, adj.: Describes AI systems in which a person checks, corrects or approves the machine's work at key points, rather than letting it act entirely on its own.
- multi-agent systemmulti-agent system, n.: A setup in which several AI agents, each with its own role or point of view, work together — or compete — on a problem, passing messages and results among themselves.
- agentic workflowagentic workflow, n.: A multi-step process in which AI models draft, check, use tools and revise their work over several rounds, instead of answering in one shot; often the steps are laid out by developers in advance.
Sources
- LangChain (2025). LangChain and LangGraph Agent Frameworks Reach v1.0 Milestones. LangChain blog, 22 October 2025. langchain.com/blog/langchain-langgraph-1dot0
Mentioned in
LangChainLangChain, prop. n.: A popular free software toolkit, and the company behind it, for building applications that connect AI language models to documents, databases, tools and multi-step workflows., AutoGenAutoGen, prop. n.: A free Microsoft software framework for building teams of AI agents that solve problems by messaging one another, writing and running code, and asking people for help when needed., CrewAICrewAI, prop. n.: A free software framework for setting up teams of AI agents, each given a job title, goal and backstory, that divide up tasks and work through them together like a small staff.