Memory Setup

If your Moltbot or Clawdbot agent keeps forgetting everything between sessions, this walks you through adding persistent memory via vector search. You'll configure memorySearch in your config JSON, set up a MEMORY.md file for curated context, and organize daily logs so the agent can actually recall past conversations and decisions. Supports Voyage, OpenAI, or local embeddings. The troubleshooting section is genuinely helpful for when things don't work after restart. Honest take: this is one of those configs you set up once and forget about, but it completely changes how useful the agent feels over time. The goldfish to elephant framing is accurate.

skills.sh installs: 1.7K
GitHub stars: 674
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add sundial-org/awesome-openclaw-skills --skill memory-setup --agent claude-code

Installs into .claude/skills of the current project.

Files

Memory Setup Skill

Transform your agent from goldfish to elephant. This skill helps configure persistent memory for Moltbot/Clawdbot.

Quick Setup

1. Enable Memory Search in Config

Add to ~/.clawdbot/clawdbot.json (or moltbot.json):

{
  "memorySearch": {
    "enabled": true,
    "provider": "voyage",
    "sources": ["memory", "sessions"],
    "indexMode": "hot",
    "minScore": 0.3,
    "maxResults": 20
  }
}

2. Create Memory Structure

In your workspace, create:

workspace/
├── MEMORY.md              # Long-term curated memory
└── memory/
    ├── logs/              # Daily logs (YYYY-MM-DD.md)
    ├── projects/          # Project-specific context
    ├── groups/            # Group chat context
    └── system/            # Preferences, setup notes

3. Initialize MEMORY.md

Create MEMORY.md in workspace root:

# MEMORY.md — Long-Term Memory

## About [User Name]
- Key facts, preferences, context

## Active Projects
- Project summaries and status

## Decisions & Lessons
- Important choices made
- Lessons learned

## Preferences
- Communication style
- Tools and workflows