skills.rest
tivon-x
tivon-xCOMMUNITY
Explore all skills by this author →
GitHub

deep-agents-memory

Configure pluggable memory backends for persistent and ephemeral agent storage.

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

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill provides agents with the ability to store and retrieve information persistently or ephemerally, enabling state management and long-term memory.

Core Features & Use Cases

  • Ephemeral Storage: StateBackend for temporary data within a single thread.
  • Persistent Storage: StoreBackend for data that survives across threads and sessions.
  • Flexible Routing: CompositeBackend to manage different storage strategies for different paths.
  • Filesystem Operations: Tools like ls, read_file, write_file for interacting with storage.
  • Use Case: An agent needs to remember user preferences across multiple interactions. It can save these preferences to a persistent store using StoreBackend and retrieve them later.

Quick Start

Use the deep-agents-memory skill to save a note to the file /persistent-notes.txt.

Frequently Asked Questions about deep-agents-memory

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

FAQPage Schema
How do I persist agent state across multiple sessions?▼

To persist agent state across sessions, use a persistent storage backend like StoreBackend. This ensures data survives beyond a single thread, allowing agents to retrieve information later.

What's the best way to manage temporary agent memory within a single thread?▼

For temporary agent memory within a single thread, use an ephemeral storage solution like StateBackend. This handles temporary data that does not need to persist across different sessions.

Can I use different storage strategies for different file paths?▼

Yes, you can use CompositeBackend for flexible routing to manage different storage strategies. It allows you to assign different backend behaviors to different paths within your agent's filesystem.

How do agents interact with the filesystem for memory storage?▼

Agents interact with the filesystem using operations like listing, reading, writing, and editing files. These tools enable agents to save and retrieve notes or preferences directly to storage.

Does this memory management integrate with LangChain for state management?▼

Yes, this memory management integrates with LangChain for advanced state management and custom tool development. This allows for flexible configuration of persistence mechanisms.

When should I use a hybrid storage solution for agent memory?▼

Use a hybrid storage solution when you need both ephemeral and persistent data within the same agent. This approach combines temporary state management with long-term data survival across threads.

Related Skills

Explore More Software Engineering Skills→
1molchuan1molchuan
1

oh-my-ccg-init

Verify MCP, Codex, and Gemini endpoints and initialize RPI state.

Community
Intermediate
ArvincreatorArvincreator
637

session_search

Searches stored logs by keyword, semantic, and date for historical conversations.

Community
Intermediate
brivarobrivaro

deep-agents-memory

Manage persistent and ephemeral agent memory with pluggable backends.

Community
Advanced
LincyawLincyaw

deep-agents-memory

Manage memory and filesystem access through pluggable storage backends.

Community
Intermediate