skills.rest
Lincyaw
LincyawCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

deep-agents-memory

Manage memory and filesystem access through pluggable storage backends.

2|Updated Mar 7, 2026
Search Tags:#state management#backend#memory#persistence#filesystem#deep agents
One-click install
npx skills add https://github.com/Lincyaw/AgentM --skill deep-agents-memory-lincyaw
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: deep-agents-memory
Source: https://github.com/Lincyaw/AgentM/tree/main/.claude/skills/deep-agents-memory
Command: npx skills add https://github.com/Lincyaw/AgentM --skill deep-agents-memory-lincyaw

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill provides Deep Agents with memory and filesystem access, enabling persistence and state management across different operational contexts.

Core Features & Use Cases

  • Ephemeral Storage (StateBackend): For temporary data within a single thread.
  • Persistent Storage (StoreBackend): For data that needs to survive across threads and sessions.
  • Hybrid Storage (CompositeBackend): Allows routing different file paths to different storage backends.
  • Filesystem Operations: Provides tools like ls, read_file, write_file, edit_file, glob, and grep.
  • Use Case: Store user preferences persistently in /memories/user-prefs.txt while using ephemeral storage for temporary working files in /draft.txt.

Quick Start

Use the deep-agents-memory skill to save notes to /draft.txt within thread-1.

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 persistent memory for deep agents across different sessions?▼

Persistent memory for deep agents across sessions is managed through a StoreBackend, which ensures data survives beyond a single thread. This allows agentic workflows to maintain long-term state and data persistence.

What is the best way to route file operations to different storage backends in an agentic workflow?▼

Routing file operations to different storage backends is achieved using hybrid storage via a CompositeBackend. This mechanism allows you to direct specific file paths to either ephemeral or persistent storage within agentic workflows.

Can I use ephemeral state for temporary working files in deep agents?▼

Yes, ephemeral state for temporary working files in deep agents is supported via a StateBackend. This provides temporary data storage within a single thread for dynamic state management during active processing.

What filesystem operations are supported for state management and data persistence?▼

Filesystem operations supported for state management and data persistence include ls, read_file, write_file, edit_file, glob, and grep. These tools facilitate direct file manipulation within configured storage backends.

How do I store user preferences persistently while keeping temporary working files in memory?▼

Storing user preferences persistently while keeping temporary files in memory is done using hybrid storage. Route preferences to a persistent path like /memories/user-prefs.txt and temporary files to an ephemeral path like /draft.txt.

Related Skills

Explore More Software Engineering Skills→
lacetolaceto
1

deep-agents-memory

Routes memory and filesystem operations through pluggable StateBackend, StoreBackend, and CompositeBackend backends for Deep Agents.

Community
Advanced
jxtngxjxtngx
2

langgraph-fundamentals

Design state schemas and conditional routing for LangGraph agentic workflows.

Community
Advanced
brivarobrivaro

deep-agents-memory

Manage persistent and ephemeral agent memory with pluggable backends.

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

AgentDB Memory Patterns

Manage persistent AI agent memory with AgentDB and ReasoningBank integration.

Official
Advanced