memory-lancedb-pro-openclaw — Claude Code skill: install
Guides setup of OpenClaw’s LanceDB memory plugin. Useful when an agent needs to retain project context between sessions or retrieve stored details.
npx skills add reason-machines/trending-skills --skill memory-lancedb-pro-openclaw -a claude-codeWhat memory-lancedb-pro-openclaw does
This skill covers configuring OpenClaw’s long-term memory plugin, which stores preferences and project context in LanceDB and can bring relevant entries back before an agent responds. The setup guide discusses hybrid vector and BM25 retrieval, cross-encoder reranking, and separate memory scopes for agents, users, and projects.
It includes openclaw.json examples, embedding provider choices, and commands to validate the configuration and restart the gateway. The OpenAI-compatible setup uses an API key; Ollama is shown as a local option. One setup detail matters: npm installs require the plugin’s absolute path in plugins.load.paths.
What it helps with
- configure persistent memory for an OpenClaw agent
- enable vector and BM25 hybrid retrieval
- isolate memory by agent, user, or project
- validate OpenClaw settings and restart the gateway
Example prompts for the agent
- Show me how to enable hybrid search and reranking in
memory-lancedb-pro. - Check my
openclaw.jsonmemory setup and explain how to restart the OpenClaw gateway.
How to install memory-lancedb-pro-openclaw
1Skills CLI (Vercel)
npx skills add reason-machines/trending-skills --skill memory-lancedb-pro-openclaw -a claude-code2Manually: put the files in place
~/.claude/skills/memory-lancedb-pro-openclaw/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/memory-lancedb-pro-openclaw/
1Skills CLI (Vercel)
npx skills add reason-machines/trending-skills --skill memory-lancedb-pro-openclaw -a codex2Manually: put the files in place
.agents/skills/memory-lancedb-pro-openclaw/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add reason-machines/trending-skills --skill memory-lancedb-pro-openclaw -a cursor2Manually: put the files in place
.cursor/skills/memory-lancedb-pro-openclaw/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install reason-machines/trending-skills memory-lancedb-pro-openclaw2Manually: put the files in place
.github/skills/memory-lancedb-pro-openclaw/SKILL.md1Skills CLI (Vercel)
npx skills add reason-machines/trending-skills --skill memory-lancedb-pro-openclaw -a gemini-cli2Platform CLI
gemini skills install https://github.com/reason-machines/trending-skills --path skills/memory-lancedb-pro-openclawManually: put the files in place
.devin/skills/memory-lancedb-pro-openclaw/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add reason-machines/trending-skills --skill memory-lancedb-pro-openclaw -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about memory-lancedb-pro-openclaw
How do I install memory-lancedb-pro-openclaw in Claude Code?
Run npx skills add reason-machines/trending-skills --skill memory-lancedb-pro-openclaw -a claude-code. The skill file is at ~/.claude/skills/memory-lancedb-pro-openclaw/SKILL.md.
What does memory-lancedb-pro-openclaw do?
It guides you through setting up OpenClaw’s long-term memory plugin. The plugin stores context in LanceDB and retrieves relevant entries for agent replies.
Does the OpenClaw memory setup need an API key?
The OpenAI-compatible configuration uses an API key. The guide also shows Ollama for local embeddings and extraction.