skills.rest
langchain-ai
langchain-aiOFFICIAL
Explore all skills by this author →
Website𝕏@LangChainGitHub

deep-agents-memory

Configure pluggable memory backends for ephemeral and persistent storage in Deep Agents.

113|9|Updated Jan 24, 2026
Search Tags:#backend#memory#persistence#state-backend#deep-agents#composite-backend#store-backend
One-click install
npx skills add https://github.com/langchain-ai/skills-benchmarks --skill deep-agents-memory
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: deep-agents-memory
Source: https://github.com/langchain-ai/skills-benchmarks/tree/main/skills/main/deep-agents-memory
Command: npx skills add https://github.com/langchain-ai/skills-benchmarks --skill deep-agents-memory

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Deep Agents need flexible memory where data can be ephemeral to a single task or persistent across sessions. This skill provides pluggable backends (StateBackend, StoreBackend) and routing via CompositeBackend to manage where and how memory is stored, enabling clean separation of ephemeral and long-term data.

Core Features & Use Cases

  • Ephemeral memory with StateBackend for fast, in-thread storage that disappears with the thread.
  • Persistent memory with StoreBackend for cross-session memory that survives restarts.
  • Hybrid routing with CompositeBackend to direct specific paths to different backends and combine memory strategies.
  • Local development and sandboxing using FilesystemBackend for real disk access with safety controls.

Quick Start

Instantiate a deep agent with a chosen memory backend and perform a read/write operation to verify persistence.

Frequently Asked Questions about deep-agents-memory

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

FAQPage Schema
How do I manage ephemeral and persistent memory for deep agents?▼

You can manage deep agents memory by selecting pluggable backends like StateBackend for ephemeral in-thread storage and StoreBackend for persistent cross-session memory that survives restarts.

What is the best way to combine ephemeral and long-term memory in a backend?▼

Hybrid routing with CompositeBackend combines ephemeral and long-term memory by directing specific paths to different backends, enabling a clean separation of state and persistent data strategies.

How do I set up local disk persistence for agent memory safely?▼

Use FilesystemBackend to enable real disk access for local development and sandboxing, optionally configuring human-in-the-loop or root restrictions to ensure safe memory persistence operations.

When should I use StateBackend versus StoreBackend for agent state?▼

Use StateBackend for fast, ephemeral memory that disappears with the thread, and use StoreBackend when your agents require cross-session memory and long-term data persistence across restarts.

Does configuring deep agents memory require external dependencies?▼

Configuring deep agents memory requires no external dependencies, you simply select a backend type, configure routes, and optionally enable human-in-the-loop or root restrictions for local development.

Related Skills

Explore More Software Engineering Skills→
JhonHanderJhonHander

deep-agents-memory

Manage ephemeral and persistent memory with file system middleware and composite backend routing.

Community
Advanced
daniel-dihardjadaniel-dihardja

deep-agents-memory

Persist memory and filesystem access for Deep Agents via CompositeBackend routing.

Community
Advanced
patornpatorn

deep-agents-memory

Configure Deep Agents with pluggable memory backends and filesystem middleware.

Community
Advanced
LLM-Dev-OpsLLM-Dev-Ops
1

AgentDB Memory Patterns

Manage persistent AI agent memory with AgentDB and ReasoningBank integration.

Official
Advanced