langgraph-persistence

Configure durable state persistence for LangGraph graphs with checkpointers.

Updated Apr 12, 2026
One-click install
npx skills add https://github.com/dotlab-hq/torque --skill langgraph-persistence-dotlab-hq
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: langgraph-persistence
Source: https://github.com/dotlab-hq/torque/tree/main/.agents/skills/langgraph-persistence
Command: npx skills add https://github.com/dotlab-hq/torque --skill langgraph-persistence-dotlab-hq

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Provides a robust persistence layer for LangGraph to reliably save and restore graph execution state so conversations, long-running flows, and multi-turn agents can resume across invocations and process restarts.

Core Features & Use Cases

  • Checkpointer selection: guidance and examples for InMemorySaver, SqliteSaver, and PostgresSaver with production recommendations.
  • Thread-scoped short-term memory: use thread_id to isolate conversation histories and enable multi-turn interactions.
  • Long-term Store: cross-thread key-value store for persistent user preferences and facts accessible from runtime.
  • State history & time travel: inspect, replay, fork, and update past checkpoints to resume or branch execution.
  • Subgraph scoping: rules for compile-time checkpointer modes (False, None, True) and namespace isolation for parallel subgraphs.
  • Operational fixes and best practices: always supply thread_id, prefer PostgresSaver for production, use Overwrite to bypass reducers, and access store via runtime.

Quick Start

Invoke the graph with a persistent checkpointer and include a configurable.thread_id to enable durable conversation history.

Frequently Asked Questions about langgraph-persistence

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I persist LangGraph conversation state across process restarts?▼

LangGraph persistence uses checkpointers like PostgresSaver or SqliteSaver to save graph execution state, allowing multi-turn agents and long-running flows to resume across invocations and process restarts by supplying a configurable thread_id.

What is the best way to manage multi-turn conversation history in LangGraph?▼

Thread-scoped short-term memory in LangGraph isolates conversation histories using a thread_id, ensuring multi-turn interactions maintain individual state. For long-term data, use a cross-thread Store for persistent user preferences and facts accessible at runtime.

Does LangGraph support time-travel replay and state history inspection?▼

LangGraph persistence supports state history inspection, enabling you to replay, fork, and update past checkpoints. This time-travel capability lets you resume or branch graph execution from previous states using configurable checkpointers.

When should I use InMemorySaver versus PostgresSaver for LangGraph checkpointing?▼

InMemorySaver suits development scenarios, while PostgresSaver is recommended for production deployments. PostgresSaver provides durable checkpointing and operational setup capabilities required for robust LangGraph state persistence.

How do I isolate checkpointer state for parallel LangGraph subgraphs?▼

LangGraph subgraph scoping uses compile-time checkpointer modes (False, None, True) and namespace isolation to manage state persistence for parallel subgraphs, ensuring isolated checkpointing behavior across complex graph structures.