INVOKE THIS SKILL when your Deep Agent needs memory, persistence, or filesystem access. Covers StateBackend (ephemeral), StoreBackend (persistent), FilesystemMiddleware, and CompositeBackend for routing.
The deep-agents-memory skill is designed to enhance the capabilities of Deep Agents by providing them with memory, persistence, and filesystem access. This skill addresses the need for agents to manage data effectively across different sessions and threads, allowing for a more robust interaction model. By utilizing various backends, it enables agents to store and retrieve information seamlessly, ensuring that critical data is not lost when a thread ends or when switching contexts.
You can invoke the skill by creating a Deep Agent instance and using the appropriate backend configuration for your use case.
The skill offers StateBackend for ephemeral storage, StoreBackend for persistent storage, and CompositeBackend for routing between different storage types.
Yes, you can use StoreBackend to persist files across different threads and sessions.
Yes, the deep-agents-memory skill provides examples and support for both Python and TypeScript.
StateBackend only stores data within a single thread and loses that data when the thread ends.
Quick Setup:
.claude/skills/Repository
langchain-ai/langchain-skills