ClawKit Logo
ClawKitReliability Toolkit
Back to Registry
Official Verified developer tools Safety 4/5

memory-setup

Enable and configure Moltbot/Clawdbot memory search for persistent context. Use when setting up memory, fixing "goldfish brain," or helping users configure memorySearch in their config. Covers MEMORY.md, daily logs, and vector search setup.

Why use this skill?

Learn how to enable and configure persistent memory search for your OpenClaw agent. Prevent data loss, track project history, and improve recall with this comprehensive guide.

skill-install — Terminal

Install via CLI (Recommended)

clawhub install openclaw/skills/skills/gwsq/memory-setup-1-0-0
Or

What This Skill Does

The memory-setup skill provides a robust framework for enabling persistent context within OpenClaw AI agents. By configuring the memorySearch system, the agent gains the ability to retrieve long-term facts, preferences, project history, and daily logs. This transforms the agent from a stateless assistant into one that remembers prior interactions, making it far more effective for multi-day coding tasks, personal knowledge management, and complex project tracking. It effectively eliminates the 'goldfish brain' syndrome by indexing your workspace documentation and historical logs.

Installation

To install this skill, run the command: clawhub install openclaw/skills/skills/gwsq/memory-setup-1-0-0. After installation, modify your ~/.clawdbot/clawdbot.json configuration file to include the memorySearch block, ensuring you specify your preferred embedding provider (e.g., 'voyage' or 'openai'). Create a MEMORY.md file in your workspace root to serve as the foundational knowledge base, and establish the memory/ directory structure to house your project notes and daily logs.

Use Cases

This skill is ideal for developers managing long-term coding projects, users who want the AI to remember project-specific architecture decisions, or individuals tracking personal habits and recurring daily tasks. It is also excellent for teams wanting to maintain a 'shared brain' of common project knowledge across multiple sessions.

Example Prompts

  • 'I'm feeling like my agent keeps forgetting our setup. Can you help me install and configure the memory-setup skill?'
  • 'Run a memory search for all my notes on the authentication refactor project from last week.'
  • 'My memory results are too sparse; can you help me tune the minScore and index settings in my config to get more relevant context?'

Tips & Limitations

To get the best results, keep your MEMORY.md file updated and ensure your logs follow the YYYY-MM-DD.md naming convention. If you are not using an API-based provider like Voyage or OpenAI, the 'local' provider is a great, private alternative that requires no external keys. Remember that search quality is heavily dependent on the detail level of your documentation; keep notes specific and descriptive. If results are irrelevant, try lowering the minScore threshold or increasing maxResults.

Metadata

Author@gwsq
Stars2387
Views1
Updated2026-03-09
View Author Profile
AI Skill Finder

Not sure this is the right skill?

Describe what you want to build — we'll match you to the best skill from 16,000+ options.

Find the right skill
Add to Configuration

Paste this into your clawhub.json to enable this plugin.

{
  "plugins": {
    "official-gwsq-memory-setup-1-0-0": {
      "enabled": true,
      "auto_update": true
    }
  }
}

Tags(AI)

#memory#context#persistence#productivity#knowledge-base
Safety Score: 4/5

Flags: file-write, file-read, external-api