LangGraph

LangGraph is an open-source orchestration framework and runtime, developed by the LangChain team, for building stateful and long-running AI agents. It models an application as a graph: each node is a unit of work (often an LLM call or tool invocation), and edges describe how control and state flow between them. Unlike pipelines restricted to a directed acyclic graph, LangGraph supports cycles, so an agent can loop, retry, and reflect until a condition is met.

State and durability

Every node receives the current shared state, returns a partial update, and the framework merges that update according to developer-defined reducers. With a checkpointer attached (for example Postgres or SQLite), this state becomes durable, meaning an agent run can crash, resume, or be rewound to an earlier step. This makes LangGraph a common choice for builders who want explicit, inspectable control over how an agent reasons rather than a fully opaque autonomous loop.

Where it fits

LangGraph can be used standalone or alongside other LangChain libraries, and it does not require LangChain to operate. For those running their own infrastructure, the ability to persist agent state to a self-hosted database is often attractive, since it keeps the reasoning record under the operator's control. It is one of several frameworks a sovereign AI builder might evaluate; the right tool depends on the workload and the surrounding stack.

For neighbouring concepts, D-Central maintains entries on the underlying ReAct reasoning-and-acting pattern and on CrewAI, another open-source multi-agent framework. We describe these tools neutrally so readers can choose what best fits their own self-hosted setup.