skills.rest
jillesca
jillescaCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

deep-agents-memory

Route Deep Agents memory operations through pluggable backend implementations.

3|1|Updated Jun 4, 2025
Search Tags:#backend#memory#persistence#filesystem#deep-agents#composite-backend
One-click install
npx skills add https://github.com/jillesca/sp_oncall --skill deep-agents-memory-jillesca
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: deep-agents-memory
Source: https://github.com/jillesca/sp_oncall/tree/main/.agents/skills/deep-agents-memory
Command: npx skills add https://github.com/jillesca/sp_oncall --skill deep-agents-memory-jillesca

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Deep Agents often require durable memory, cross-session persistence, and filesystem access to store context, results, and configurations across runs.

Core Features & Use Cases

  • StateBackend for ephemeral, per-thread memory during a session.
  • StoreBackend for persistent memory that survives restarts and across threads.
  • CompositeBackend to route specific paths to the appropriate backend, enabling hybrid memory strategies.
  • FilesystemMiddleware to perform read/write operations on local files as part of memory operations.
  • Use Case: Maintain per-agent context and long-term memories like user preferences, logs, or intermediate results across investigations.

Quick Start

Configure a Deep Agent with a composite backend that routes memory to a persistent StoreBackend for long-term storage and uses ephemeral StateBackend for fast access under /memories.

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 memory for deep agents across sessions?▼

To persist memory for deep agents across sessions, you configure a persistent StoreBackend that survives restarts and stores context like user preferences and intermediate results across different threads.

What is the best way to combine ephemeral and persistent memory for deep agents?▼

The best way to combine ephemeral and persistent memory is using a CompositeBackend to route specific paths, directing fast access to ephemeral StateBackend and long-term storage to a persistent StoreBackend.

How does filesystem access work with deep agent memory operations?▼

Filesystem access works through FilesystemMiddleware, which performs read and write operations on local files directly as part of the deep agent's memory operations.

Do I need a configured store to use persistent memory with deep agents?▼

Yes, you need a configured store to use persistent memory with deep agents, because the StoreBackend requires a configured store to successfully retain long-term memories and context across restarts.

When should I use ephemeral per-thread memory instead of persistent memory?▼

You should use ephemeral per-thread memory via StateBackend when you only need fast, temporary context during a single active session, rather than durable memory that survives across multiple agent runs.

Related Skills

Explore More Software Engineering Skills→
Diploma-pendingDiploma-pending

Deep Agents Core

Create and configure AI agents with the Deep Agents framework.

Official
Advanced
justStevejustSteve

ReasoningBank with AgentDB

Store, retrieve, and reason over experiential memories using AgentDB.

Community
Advanced
LincyawLincyaw

deep-agents-memory

Manage memory and filesystem access through pluggable storage backends.

Community
Intermediate
daniel-dihardjadaniel-dihardja

deep-agents-memory

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

Community
Advanced