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?
Enable persistent long-term memory for your AI agent. Learn how to configure vector search, structure your MEMORY.md, and retain context across sessions.
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/jrbobbyhansen-pixel/memory-setupWhat This Skill Does
The memory-setup skill provides a structured framework for enabling persistent long-term memory for Moltbot and Clawdbot agents. By implementing vector search capabilities, this skill allows your agent to recall past conversations, user preferences, project details, and critical decision logs, effectively transforming the agent from a stateless 'goldfish' into a context-aware assistant. It automates the configuration of embedding providers, indexing modes, and file-based knowledge management, ensuring your agent maintains a deep understanding of your specific workspace history.
Installation
To install this skill, use the Clawhub CLI within your development environment: clawhub install openclaw/skills/skills/jrbobbyhansen-pixel/memory-setup. Once installed, you must initialize the configuration by adding the memorySearch block to your ~/.clawdbot/clawdbot.json or moltbot.json file. Finally, create the required /memory directory in your workspace root and initialize your MEMORY.md file to begin the indexing process. You may need to restart your gateway via clawdbot gateway restart to apply changes.
Use Cases
- Fixing Context Loss: Use this when your agent repeatedly forgets project goals or user preferences across sessions.
- Project Management: Track ongoing development by logging daily progress in
/memory/logs/, allowing the agent to summarize project status at any time. - Developer Onboarding: Point the agent at your technical documentation and system notes stored within the memory structure to act as an expert technical lead.
- Decision Tracking: Archive important architectural or design decisions to ensure future technical discussions are grounded in past rationale.
Example Prompts
- "I'm having trouble with context, can you help me set up memory search so I don't have to explain my project requirements every time we start?"
- "Please check the memory logs for the last three days and provide a summary of all the bugs we addressed regarding the authentication module."
- "Help me configure my memory search settings to use the Voyage provider and increase the result limit to 30 for better coverage of my old sessions."
Tips & Limitations
To maximize effectiveness, maintain clean markdown files within your /memory directory. If the agent returns irrelevant information, try lowering the minScore to 0.2 to broaden the search scope, or increasing maxResults. Note that this skill requires read access to your local files and potentially API keys for providers like Voyage or OpenAI. If you are working in a privacy-sensitive environment, utilize the local provider option to keep all vector embeddings within your local machine without requiring external cloud connectivity.
Metadata
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 skillPaste this into your clawhub.json to enable this plugin.
{
"plugins": {
"official-jrbobbyhansen-pixel-memory-setup": {
"enabled": true,
"auto_update": true
}
}
}Tags(AI)
Flags: file-read, file-write, external-api