langgraph-persistence

langgraph persistence

langchain-ai 952 ↓ 12k updated 26d ago
Claude Code
View source ↗

What it does

  • Checkpointer: Saves/loads graph state at every super-step
  • Thread ID: Identifies separate checkpoint sequences (conversations)
  • Store: Cross-thread memory for user preferences, facts
  • Short-term (checkpointer): Thread-scoped conversation history
  • Long-term (store): Cross-thread user preferences, facts
  • checkpointer=False — Subgraph doesn't need interrupts or persistence. Simplest option, no checkpoint overhead.
  • checkpointer=True — Subgraph needs to remember state across invocations (multi-turn conversations). Each call picks up where the last left off.

Requirements & configuration

  • When compiling a subgraph, the checkpointer parameter controls persistence behavior. This is critical for subgraphs that use interrupts, need multi-turn memory, or run in parallel.
  • checkpointer=False — Subgraph doesn't need interrupts or persistence. Simplest option, no checkpoint overhead.
  • checkpointer=True — Subgraph needs to remember state across invocations (multi-turn conversations). Each call picks up where the last left off.
  • Need interrupts but not cross-invocation persistence (default)
  • Need cross-invocation persistence (stateful)

Derived from the skill's own SKILL.md documentation · extracted 2026-07-23

langgraph persistence

Source

Repository: https://github.com/langchain-ai/langchain-skills

langgraph-persistence FAQ

What does the langgraph-persistence skill do?

INVOKE THIS SKILL when your LangGraph needs to persist state, remember conversations, travel through history, or configure subgraph checkpointer scoping. Covers checkpointers, thread_id, time travel, Store, and subgraph persistence modes. Checkpointer: Saves/loads graph state at every super-step Thread ID: Identifies separate checkpoint sequences (conversations)

What does langgraph-persistence require?

When compiling a subgraph, the checkpointer parameter controls persistence behavior. This is critical for subgraphs that use interrupts, need multi-turn memory, or run in parallel. checkpointer=False — Subgraph doesn't need interrupts or persistence. Simplest option, no checkpoint overhead. checkpointer=True — Subgraph needs to remember state across invocations (multi-turn conversations). Each call picks up where the last left off. Need interrupts but not cross-invocation persistence (default) Need cross-invocation persistence (stateful)

How do I install langgraph-persistence?

Run: npx -y skills add https://github.com/langchain-ai/langchain-skills --skill langgraph-persistence --agent claude-code — the source lives at github.com/langchain-ai/langchain-skills.

Maintain langgraph-persistence?

Let people know it's listed here — add the badge (live metrics, light/dark aware) or a plain link to your README or docs.

langgraph-persistence on getagentictools
[![langgraph-persistence on getagentictools](https://getagentictools.com/badge/skills/langchain-ai-langchain-skills-langgraph-persistence.svg)](https://getagentictools.com/skills/langchain-ai-langchain-skills-langgraph-persistence?ref=badge)
npx agentictools info skills/langchain-ai-langchain-skills-langgraph-persistence

The second line is the CLI lookup for this page — handy in READMEs and docs.