LangGraph
LangChain's library for building agents and workflows as graphs of steps with saved state.
In more detail
A checkpointer saves state after each step, so a graph can pause with an interrupt for human input and resume later; a recursion limit bounds the number of steps. Because each step is explicit, it suits workflows that mix fixed paths with agent decisions.
Related terms
- agent SDK — A library that packages the agent loop with tools, budgets, saved state, tracing and hooks for human approval.
- agent checkpoint — The saved state of a paused agent run, from which it can resume later, for example after a person approves a tool call.
Taught in
- Agent SDKs And Human Approval — AI Engineering: LLM Apps, RAG & Agents