skills.rest
brivaro
brivaroCOMMUNITY
Explore all skills by this author →
GitHub

deep-agents-memory

Manage persistent and ephemeral agent memory with pluggable backends.

Updated Mar 8, 2026
Search Tags:#state management#backend#ai agent#memory#persistence#filesystem
One-click install
npx skills add https://github.com/brivaro/brivaro-ai-wizard --skill deep-agents-memory-brivaro
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: deep-agents-memory
Source: https://github.com/brivaro/brivaro-ai-wizard/tree/main/skills/deep-agents-memory
Command: npx skills add https://github.com/brivaro/brivaro-ai-wizard --skill deep-agents-memory-brivaro

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill provides AI agents with robust memory and filesystem capabilities, enabling them to store and retrieve information persistently across sessions and threads.

Core Features & Use Cases

  • Ephemeral Memory: StateBackend for temporary, thread-local storage.
  • Persistent Memory: StoreBackend for long-term storage across sessions.
  • Hybrid Storage: CompositeBackend to route different paths to different storage types.
  • Filesystem Access: FilesystemMiddleware for ls, read_file, write_file, edit_file, glob, grep.

Quick Start

Configure the agent to use a composite backend that routes files in /memories/ to persistent storage.

Frequently Asked Questions about deep-agents-memory

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

FAQPage Schema
How do I add persistent memory to an AI agent across sessions?▼

Persistent memory for AI agents is achieved using a StoreBackend, which provides long-term data storage that survives across multiple sessions and threads. A CompositeBackend can route specific paths to this persistent storage.

What is the best way to manage both temporary and long-term memory in AI agents?▼

Hybrid memory management is handled by a CompositeBackend, which routes different paths to different storage types. StateBackend provides ephemeral thread-local data, while StoreBackend manages persistent storage.

Does this AI agent memory system integrate with LangGraph for state management?▼

Yes, the AI agent memory system integrates with LangGraph for state management and custom tool development. It supports pluggable backends to handle both ephemeral state and persistent storage within LangGraph workflows.

Can an AI agent read and write files directly using its memory backend?▼

Yes, an AI agent can read and write files using FilesystemMiddleware, which supports operations like ls, read_file, write_file, edit_file, glob, and grep. This provides direct filesystem access alongside memory management.

When should I use ephemeral memory instead of persistent storage for my agent?▼

Use ephemeral memory via StateBackend for temporary thread-local storage that does not need to survive after the session ends. Use persistent storage via StoreBackend when information must be retrieved across future sessions.

Related Skills

Explore More Software Engineering Skills→
jxtngxjxtngx
2

deep-agents-memory

Route agent memory operations across ephemeral and persistent storage backends.

Community
Advanced
Rune-kitRune-kit
82

integrity-check

Scan .rune/ files and agent outputs for prompt injection and memory poisoning.

Official
Advanced
Kushal9889Kushal9889

ai-agent-development

Automate building and managing AI agents with CrewAI and LangGraph.

Community
Advanced
dotlab-hqdotlab-hq

deep-agents-memory

Routes AI agent memory and filesystem access through pluggable backends and middleware.

Official
Advanced