LangGraph
Graph-structured agent runtime
- Open source
- Agent Frameworks
What it is
LangGraph models an agent as a state graph: nodes are steps, edges are transitions, and a shared state object flows between them. Because control flow is explicit rather than implicit in a prompt loop, runs can be checkpointed, resumed, branched and interrupted for human approval. It works standalone and integrates with the wider LangChain ecosystem.
Best for
Long-running or approval-gated agent workflows that need durable state and control flow you can read off a diagram.
Where it falls short
The graph abstraction is overhead for a single-step task — one model call with a tool schema is simpler and easier to debug.
Characteristics
- agent-runtime
- state-machine
- checkpointing
- human-in-the-loop
This page carries no score, star rating or review count, and nothing about its placement in the directory was paid for. The outbound links above go to the product’s own domain with no referral parameters. Read the directory methodology for what that means in practice.
More in Agent Frameworks
Other tools solving the same problem, so you can see what LangGraph is actually competing with.
AI SDK
Open sourceUnified model interface for JavaScript applications
CrewAI
Open sourceRole-based multi-agent orchestration
LlamaIndex
Open sourceData framework for retrieval over your own content