memory-setup
Configure and validate OpenClaw memory recall for persistent context. Use when enabling memory_search/memory_get, fixing poor memory recall, or setting up MEMORY.md + memory/*.md workflows in an OpenClaw workspace.
Why use this skill?
Learn how to configure persistent memory for OpenClaw. Improve context, recall past project decisions, and manage your agent's knowledge base effectively.
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/kaw0naivyn/memory-setup-openclawWhat This Skill Does
The memory-setup skill provides a structured framework for configuring OpenClaw's long-term memory capabilities. By establishing a consistent documentation hierarchy—specifically utilizing MEMORY.md and the memory/ directory—the agent can effectively index, search, and recall historical project data, user preferences, and task statuses. This skill goes beyond simple configuration; it implements an operating protocol that ensures the agent remains grounded in past decisions and context, reducing hallucination and improving consistency across long-running development sessions. It enables advanced RAG (Retrieval-Augmented Generation) patterns within the local workspace environment.
Installation
To integrate this capability into your OpenClaw environment, execute the following command in your terminal:
clawhub install openclaw/skills/skills/kaw0naivyn/memory-setup-openclaw
Once installed, you must update your configuration file under agents.defaults.memorySearch to enable the provider and index settings. After modifying the configuration, perform a full restart of your gateway to ensure the memory indexing engine initializes correctly.
Use Cases
- Project Onboarding: Allowing a new agent instance to catch up on weeks of development progress by reading daily logs.
- Preference Persistence: Ensuring the agent remembers your preferred code style, library choices, or architectural patterns across different repository branches.
- Task Tracking: Maintaining an accurate record of pending to-dos and completed technical debt items.
- Debugging Continuity: Recalling past attempts at solving a specific bug to avoid repeating ineffective methods.
Example Prompts
- "OpenClaw, please run a memory search to summarize the architectural decisions we made regarding the database schema last Tuesday."
- "Review the current MEMORY.md file and list all pending action items that are marked as high priority."
- "Based on our previous daily notes in the memory/ directory, what was the primary reason we decided to deprecate the legacy auth module?"
Tips & Limitations
To maximize the quality of recall, maintain a strict discipline of updating daily notes. If the agent returns irrelevant content, refine your search by lowering the minScore threshold in the configuration to allow for broader matches, or increase the maxResults to retrieve more context. Be aware that the local provider may require specific hardware resources; if performance lags, consider switching to a remote provider like openai or voyage. Always verify the agent’s memory retrieval by asking it to cite the source file and line numbers of the information provided to ensure transparency and accountability.
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-kaw0naivyn-memory-setup-openclaw": {
"enabled": true,
"auto_update": true
}
}
}Tags(AI)
Flags: file-read, file-write