deepsleep

Community

Two-phase memory persistence for AI agents.

AuthorArry8
Version1.0.0
Installs0

System Documentation

What problem does it solve?

Cross-session context is frequently lost as AI agents interact across conversations. DeepSleep delivers a two-phase memory workflow to persist and consolidate memory between sessions.

Core Features & Use Cases

  • Phase 1: Deep Sleep Pack (23:40) auto-discovers sessions, pulls conversation history, and writes a daily memory file to memory/YYYY-MM-DD.md.
  • Phase 2: Morning Dispatch (00:10) reads yesterday's summary and sends per-group briefs, including reminders and open questions.
  • Phase 3: Session Memory Restore on demand reads per-group memory (memory/groups/<chat_id>.md) to restore context for a new session.
  • Privacy & safety: ensures MEMORY.md data is not leaked into daily summaries and supports per-group isolation.

Quick Start

Configure cron to run Phase 1 at 23:40 and Phase 2 at 00:10, create memory/storage directories, and initialize memory/schedule files.

Dependency Matrix

Required Modules

None required

Components

Standard package

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: deepsleep
Download link: https://github.com/Arry8/openclaw-edge/archive/main.zip#deepsleep

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.