olafgeibig/memory-lancedb-pro-use
skills/memory-lancedb-pro-use/SKILL.md
Use this skill when installing, configuring, operating, or troubleshooting the memory-lancedb-pro plugin for OpenClaw. It covers hybrid retrieval (vector + BM25), cross-encoder reranking, smart extraction, multi-scope isolation, lifecycle controls, and the memory-pro CLI workflow. Triggers: memory-lancedb-pro, OpenClaw memory plugin, memory-pro CLI, hybrid retrieval, BM25, reranker, session memory.
tools
Updated May 5, 2026
$ install --global
skillsauthnpx skillsauth add olafgeibig/skills memory-lancedb-pro-useInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: May 5, 2026, 7:28 AM111.1s10 files scanned
SKILL.md
- name:
- memory-lancedb-pro-use
- description:
- Use this skill when installing, configuring, operating, or troubleshooting the memory-lancedb-pro plugin for OpenClaw. It covers hybrid retrieval (vector + BM25), cross-encoder reranking, smart extraction, multi-scope isolation, lifecycle controls, and the memory-pro CLI workflow. Triggers: memory-lancedb-pro, OpenClaw memory plugin, memory-pro CLI, hybrid retrieval, BM25, reranker, session memory.
- license:
- MIT
- compatibility:
- Requires OpenClaw with plugin slots support, Node.js 22+, and an embedding provider API key
- source:
- https://github.com/CortexReach/memory-lancedb-pro
- version:
- 1.1.0-beta.8
Memory LanceDB Pro Helper
memory-lancedb-pro is a production-focused long-term memory plugin for OpenClaw. It adds persistent memory with hybrid retrieval (vector + BM25), optional cross-encoder rerank, smart LLM extraction, lifecycle decay and tiering, multi-scope isolation, and an operations CLI.
What It Does
- Stores memories in LanceDB with vector + FTS support.
- Retrieves with hybrid scoring, reranking, and filtering.
- Auto-captures memories from conversation turns.
- Auto-recalls relevant memory before agent responses.
- Isolates memory by scope (
global,agent:*,project:*,user:*,custom:*). - Provides
openclaw memory-procommands for operations and migration.
Quick Start
Install plugin
npm i memory-lancedb-pro@beta
Bind memory slot in openclaw.json
{
"plugins": {
"slots": {
"memory": "memory-lancedb-pro"
}
}
}
Validate and restart
openclaw config validate
openclaw gateway restart
openclaw logs --follow --plain | rg "memory-lancedb-pro"
Usage Overview
- Use auto-capture + smart extraction for low-friction memory building.
- Use auto-recall for memory injection before replies.
- Use scopes to prevent cross-agent/user memory leakage.
- Use CLI for audit and maintenance (
list,search,stats,export,import,upgrade,migrate).
Detailed References
- Installation guide (README Installation section):
./reference/installation.md - Configuration guide (README Configuration section):
./reference/configuration.md - Advanced topics (README Advanced Topics section):
./reference/advanced.md - Comparison and project structure from README:
./reference/comparison-and-project-structure.md
README documentation links are mirrored locally here:
- OpenClaw integration playbook:
./reference/openclaw-integration-playbook.md - OpenClaw integration playbook (zh-CN):
./reference/openclaw-integration-playbook.zh-CN.md - Memory architecture analysis:
./reference/memory_architecture_analysis.md - Long-context chunking:
./reference/long-context-chunking.md - Changelog v1.1.0:
./reference/CHANGELOG-v1.1.0.md
Core CLI Commands
openclaw memory-pro list --scope global --limit 20
openclaw memory-pro search "query" --scope global --limit 10
openclaw memory-pro stats --scope global
openclaw memory-pro export --scope global --output memories.json
openclaw memory-pro import memories.json --scope global --dry-run
openclaw memory-pro upgrade --dry-run
openclaw memory-pro migrate check --source /path/to/memory-lancedb
Operational Guardrails
- Run
openclaw config validatebefore restart. - Keep API keys in environment variables, not in tracked files.
- Use
upgradeonly for legacymemory-lancedb-prodata. - Use
migrateonly when moving from built-inmemory-lancedb.
Related Skills
olafgeibig/vault-wiki
development
VerifiedTrustedCommunity
Multi-domain LLM Wiki in vault — build and maintain a federation of interlinked markdown wiki knowledge bases inside your Obsidian vault. Each domain wiki has its own schema, index, and log, linked across boundaries via path-based wikilinks. Use when user wants to use a wiki (create, ingest into, query, lint).
SKILL.mdUpdated May 30, 2026
olafgeibig/turbovault-use
tools
VerifiedTrustedCommunity
Safe and effective use of TurboVault MCP tools — vault selection, active vault management, read/write/edit_note patterns, SEARCH/REPLACE syntax, search tools, graph tools, batch operations, verification, and troubleshooting. Load this skill whenever a task uses mcp_turbovault_* tools.
SKILL.mdUpdated May 30, 2026
olafgeibig/skills/skill-templates/skill-improvements
testing
VerifiedTrustedCommunity
--- name: {{BUNDLE_NAME}}-improvements description: "Container for agent-discovered optimizations to the {{BUNDLE_NAME}} bundle — {{SKILL_NAMES}}" metadata: version: "0.3.0" source: https://github.com/olafgeibig/skills hermes: tags: [template, improvement, bundle, profile] related_skills: [{{SKILL_NAMES}}] --- # {{BUNDLE_NAME}} Improvements This skill collects all improvements discovered while working with {{SKILL_LIST}}. Core skills remain untouched. **Profile-specific:** This
SKILL.mdUpdated May 30, 2026
olafgeibig/skill-templates/skill-improvements
testing
VerifiedTrustedCommunity
--- name: {{BUNDLE_NAME}}-improvements description: "Container for agent-discovered optimizations to the {{BUNDLE_NAME}} bundle — {{SKILL_NAMES}}" metadata: version: "0.3.0" source: https://github.com/olafgeibig/skills hermes: tags: [template, improvement, bundle, profile] related_skills: [{{SKILL_NAMES}}] --- # {{BUNDLE_NAME}} Improvements This skill collects all improvements discovered while working with {{SKILL_LIST}}. Core skills remain untouched. **Profile-specific:** This
SKILL.mdUpdated May 30, 2026