Your AI agent can remember past conversations and save its progress. This skill teaches you how to give your agent a memory using checkpointing. It works by saving the agent's state at every step. You can use different storage backends like PostgreSQL for production or simple in-memory for testing. The skill also covers thread IDs to keep separate conversations apart. And it explains the Store for long-term memory across many chats. This makes your agent smarter and more reliable over time.
Global
mkdir -p ~/.claude/skills/langgraph-persistenceProject
mkdir -p .claude/skills/langgraph-persistenceSource Repository
Find Skillsvercel-labs/skills
Find and install the perfect skill to extend your AI agent
Microsoft Foundrymicrosoft/azure-skills
Build, deploy, and improve AI agents on Microsoft Foundry from start to finish
Azure Aimicrosoft/azure-skills
Search, transcribe, and analyze with Azure AI tools for smarter apps
Azure Hosted Copilot Sdkmicrosoft/azure-skills
Build, deploy, and manage your Copilot SDK apps on Azure with ease
Triagemattpocock/skills
Triage issues with a state machine driven by clear roles and agent briefs
Handoffmattpocock/skills
Hand off your work to another AI agent with a clear summary
Image Editagentspace-so/runcomfy-agent-skills
Smart router picks the best AI model for your image editing needs
Agentspaceagentspace-so/skills
See your AI agent's live folder from any browser instantly