openclaw-memory

Persist critical OpenClaw session information to workspace files for durable memory.

Updated Mar 3, 2026
One-click install
npx skills add https://github.com/0xb11a/crypto-claw --skill openclaw-memory-0xb11a
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: openclaw-memory
Source: https://github.com/0xb11a/crypto-claw/tree/main/.claude/skills/openclaw-memory
Command: npx skills add https://github.com/0xb11a/crypto-claw --skill openclaw-memory-0xb11a

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

The OpenClaw memory management skill helps ensure durability of important information across sessions by guiding users to persist critical notes, rules, and session decisions to disk so they survive compaction and restarts.

Core Features & Use Cases

  • Four memory layers (bootstrap files, session transcripts, LLM context window, retrieval index) and guidance on diagnosing memory loss or context drift.
  • Memory and retrieval protocols that tell the agent when to write durable information to disk and how to retrieve it for future tasks.
  • Configuration guidance for pre-compaction flush, context pruning, memory search, and a structured workspace file architecture to support long-term memory hygiene.
  • Practical patterns for memory hygiene, daily logs, and habit formation to minimize information loss over time.

Quick Start

Write a concise durable note to MEMORY.md documenting a memory item observed during the session.

Frequently Asked Questions about openclaw-memory

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

FAQPage Schema
Why does my agent lose context and memory after a session compaction or restart?

Session memory loss occurs when critical information is not persisted to durable workspace files. Writing structured durable notes like MEMORY.md before compaction or restarts ensures information survives context pruning and new sessions.

How do I configure durable memory management to survive context pruning?

Configure durable memory management by setting up pre-compaction flush protocols and a structured workspace file architecture. This ensures critical session data is written to disk and retrieved properly before context window pruning occurs.

What is the best way to structure workspace files for long-term memory hygiene?

The best way to structure workspace files for memory hygiene is using four layers: bootstrap files, session transcripts, the LLM context window, and a retrieval index, guided by clear memory protocols and daily logs.

How do I retrieve information from disk for future tasks after a session restart?

Retrieve persisted information by integrating memory_search workflows with your workspace file architecture. This retrieval protocol tells the agent when and how to access durable notes written to disk during previous sessions.

Can I use daily logs to minimize information loss during OpenClaw workflows?

Yes, daily logs support memory hygiene by promoting habit formation for writing durable notes. Combined with bootstrap files and retrieval protocols, daily logs minimize information loss across compaction events and new sessions.

When should I flush context to disk to prevent memory loss during compaction?

You should flush context to disk during pre-compaction to prevent memory loss. Executing a pre-compaction flush writes critical session decisions and rules to durable workspace files before the context window is pruned.