Architecture map
How the repo is organized
Click systems in the graph to inspect responsibilities, important files, and nearby dependencies.
Architecture map
Use this map to orient around systems, dependencies, and files worth reading first.
Click a system in the map
Explore langchain-ai/langgraph by selecting services, gateways, clients, and data stores. Each node shows the files, responsibilities, and neighboring systems an agent should keep in scope.
Pan, zoom, and use the minimap to keep large repos navigable.
Sign up to turn selected graph context into repo-aware agent sessions.
Key systems
What an agent should understand first
High-level graph builder for defining stateful workflows
Core message-passing orchestration engine managing node execution, state flow, and lifecycle
Value storage, update aggregation, and state change tracking (LastValue, DeltaChannel, Topic, etc.)
Durable state snapshots supporting memory, SQLite, PostgreSQL backends with delta compression
Individual node runners with retry policies, caching, timeout management, and error handling
Real-time streaming output with configurable modes (values, updates, debug, messages)
HTTP/WebSocket client for remote graph execution against LangGraph API server
Equivalent SDK for JavaScript/TypeScript environments with same client interface
Evidence coverage
What this context is grounded in
Coverage
- Citations
- 7
- Findings
- 5
- Files discovered
- 623
- Architecture systems
- 12
- Architecture relationships
- 14
- Agent graph
- Agent graph entities
- 2,882
- Agent graph relationships
- 5,604