openclaw-mem

Name: openclaw-mem
Availability: InStock
Author: wewetv1987-cell

Preserve knowledge across OpenClaw session compaction with MEMORY.md and daily logs.

Updated Feb 16, 2026

Search Tags:#retrieval #memory #privacy #knowledge-management #openclaw #session-compaction

Ready to run

npx skills add https://github.com/wewetv1987-cell/openclaw-backup --skill openclaw-mem-wewetv1987-cell

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: openclaw-mem
Source: https://github.com/wewetv1987-cell/openclaw-backup/tree/main/skills/openclaw-mem
Command: npx skills add https://github.com/wewetv1987-cell/openclaw-backup --skill openclaw-mem-wewetv1987-cell

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill preserves important knowledge across session compaction so OpenClaw agents do not lose decisions, preferences, or work history when the context window gets trimmed.

Core Features & Use Cases

Separates short-term session memory from durable disk memory so transient chat stays lightweight.
Guides agents to write lasting facts into MEMORY.md and day-specific work notes into memory/YYYY-MM-DD.md.
Supports retrieval-first recall, pre-compaction flushing, and privacy-safe handling of sensitive information.
Use it to remember stable preferences, capture durable decisions, and keep today's edits or blockers organized.

Quick Start

Tell the agent to store the important decision in durable memory and add today's work notes to the daily log.

Frequently Asked Questions about openclaw-mem

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

FAQPage Schema

How do I preserve agent memory across session compaction?▼

To preserve memory across session compaction, important knowledge is separated into durable disk files like MEMORY.md and daily logs, while pre-compaction flushing ensures transient context is saved before the window is trimmed.

What is the best way to separate short-term context from durable long-term memory?▼

The best way to separate memory is to keep short-term session context lightweight for transient chat, while writing lasting facts into curated MEMORY.md entries and day-specific work notes into daily log files.

How do I retrieve specific decisions or preferences from durable agent memory?▼

Retrieving decisions requires retrieval-first recall using memory_search and memory_get functions to query indexed durable memory, ensuring reliable recall of past preferences and work history.

Does this memory management approach handle privacy-safe information?▼

Yes, the memory management approach includes privacy-safe handling of sensitive information, ensuring that durable knowledge and daily work notes are stored cleanly and securely across compaction events.

When do I need to flush session memory to disk?▼

You need to flush session memory to disk during pre-compaction flushing, which must occur right before the context window gets trimmed to prevent losing active decisions and temporary work notes.

Why does my agent forget preferences after the context window is trimmed?▼

Agents forget preferences after context trimming if durable memory is not properly indexed and flushed, making retrieval-first recall and curated MEMORY.md entries essential for reliable recall.