memory-lancedb-hybridLanceDB long-term memory plugin with BM25 + vector hybrid search (RRF or linear reranking).
Install via ClawdBot CLI:
clawdbot install joeykrug/memory-lancedb-hybridThis skill packages a drop-in OpenClaw memory plugin that adds hybrid search to LanceDB memory:
rrf (Reciprocal Rank Fusion, recommended)linear (weighted combination)It is based on (and credits) OpenClaw PR openclaw/openclaw#7636.
A local plugin (extension) located at:
plugin/ โ overrides the built-in plugin id memory-lancedb (adds hybrid search)Once enabled, it provides the same tools as the bundled LanceDB memory plugin:
memory_storememory_recallmemory_forgetโฆbut memory_recall/auto-recall/forget now use hybrid search when enabled.
1) Ensure the skill folder exists (ClawHub install puts it under your workspace):
~/.openclaw/workspace/skills/memory-lancedb-hybrid/plugin2) Install the plugin dependencies (once):
cd ~/.openclaw/workspace/skills/memory-lancedb-hybrid/plugin
npm install --omit=dev
3) Add the plugin to OpenClawโs plugin load paths.
This plugin keeps the id memory-lancedb, so it will override the bundled memory-lancedb extension when discovered via plugins.load.paths (higher precedence than bundled).
Edit ~/.openclaw/openclaw.json:
{
plugins: {
load: {
// Point at the plugin directory inside this skill
paths: ["~/.openclaw/workspace/skills/memory-lancedb-hybrid/plugin"]
},
// Ensure the memory slot points at LanceDB memory
slots: {
memory: "memory-lancedb"
},
// Configure LanceDB memory (this override adds the `hybrid` config block)
entries: {
"memory-lancedb": {
enabled: true,
config: {
embedding: {
apiKey: "${OPENAI_API_KEY}",
model: "text-embedding-3-small"
},
// Optional
dbPath: "~/.openclaw/memory/lancedb",
// Optional
autoCapture: true,
autoRecall: true,
// Hybrid search options
hybrid: {
enabled: true,
reranker: "rrf"
// If using reranker: "linear", you can also set:
// vectorWeight: 0.7,
// textWeight: 0.3,
}
}
}
}
}
}
4) Restart the Gateway.
Hybrid search needs an FTS index on the text column; the plugin will attempt to create it automatically. If FTS setup fails for any reason, the plugin logs a debug message and falls back to vector-only search.
All config lives under plugins.entries.memory-lancedb.config.
hybrid.enabled (boolean, default true)hybrid.reranker (rrf | linear, default rrf)hybrid.vectorWeight (number 0โ1, default 0.7, only used for linear)hybrid.textWeight (number 0โ1, default 0.3, only used for linear)memory-lancedb at runtime (remove plugins.load.paths to revert).dbPath.hybrid.enabled is true and that the FTS index was created (check Gateway logs).plugin/index.ts โ plugin implementation (hybrid search)plugin/config.ts โ config parsing + UI hintsplugin/openclaw.plugin.json โ manifest + JSON Schema (used for strict config validation)Generated Feb 24, 2026
Law firms can use hybrid search to quickly find relevant case law and contracts by combining semantic understanding of legal concepts with exact keyword matching for specific clauses or citations. This improves accuracy in legal research and reduces time spent on manual document review.
Support teams can enhance chatbots by enabling hybrid search to retrieve past ticket resolutions, blending semantic context of user issues with precise term matching for error codes or product names. This leads to faster, more accurate responses and improved customer satisfaction.
Researchers and students can leverage hybrid search to sift through academic papers, combining vector-based semantic similarity for topics with BM25 for exact author names or publication dates. This streamlines literature reviews and supports comprehensive data collection.
Medical institutions can implement hybrid search to access patient records, using semantic search for symptom descriptions and exact term matching for diagnostic codes or medication names. This aids in clinical decision-making and ensures precise data retrieval.
Online retailers can integrate hybrid search into their platforms to help customers find products by blending semantic understanding of user intent with keyword matching for brand names or specifications. This enhances search relevance and boosts conversion rates.
Offer the hybrid search plugin as a premium add-on for OpenClaw users, charging a monthly fee for enhanced memory capabilities. This model targets businesses needing advanced AI memory features, generating recurring revenue through tiered pricing based on usage or data volume.
Provide professional services to help organizations customize and deploy the hybrid search plugin within their OpenClaw setups. This includes configuration, training, and ongoing support, with revenue coming from project-based fees or retainer agreements.
Distribute the basic plugin for free to attract users, then monetize through paid upgrades for advanced features like custom reranking algorithms, priority support, or enterprise-scale data handling. This model encourages adoption while driving revenue from power users.
๐ฌ Integration Tip
Ensure the FTS index is properly created by checking Gateway logs after enabling hybrid search to avoid fallback to vector-only mode.
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Clau...
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.
Search and analyze your own session logs (older/parent conversations) using jq.
Typed knowledge graph for structured agent memory and composable skills. Use when creating/querying entities (Person, Project, Task, Event, Document), linking related objects, enforcing constraints, planning multi-step actions as graph transformations, or when skills need to share state. Trigger on "remember", "what do I know about", "link X to Y", "show dependencies", entity CRUD, or cross-skill data access.
Ultimate AI agent memory system for Cursor, Claude, ChatGPT & Copilot. WAL protocol + vector search + git-notes + cloud backup. Never lose context again. Vibe-coding ready.
Headless browser automation CLI optimized for AI agents with accessibility tree snapshots and ref-based element selection