What problem does it solve?
This Skill addresses the challenge of managing state, conversation history, and durable execution within LangGraph applications, ensuring that your agents can remember past interactions and maintain context across sessions.
Core Features & Use Cases
- State Persistence: Enables saving and loading of graph states using various checkpointers (in-memory, SQLite, PostgreSQL).
- Conversation History: Manages thread-specific conversation logs for multi-turn interactions.
- Time Travel: Allows browsing, replaying, and forking from past states in the execution history.
- Long-Term Memory: Integrates a
Store for cross-thread memory, storing user preferences or facts.
- Subgraph Scoping: Provides control over persistence behavior for subgraphs, crucial for managing interrupts and parallel execution.
- Use Case: Building a customer support chatbot that needs to remember previous interactions within a single conversation thread, and also retain user preferences across different conversations.
Quick Start
Use the langgraph-persistence skill to set up a graph with in-memory checkpointing and thread-based state persistence.