memory lancedb pro OpenClaw Plugin Skill by [ara.so](https://ara.so) — Daily 2026 Skills collection. memory lancedb pro is a production grade long term memory plugin for [OpenClaw](https://github.com/openclaw/openclaw) agents. It stores preferences, decisions, and project context in a local [LanceDB](https://lancedb.com) vector database and automatically recalls relevant memories before each agent reply. Key features: hybrid retrieval (vector + BM25 full text), cross encoder reranking, LLM powered smart extraction (6 categories), Weibull decay based forgetting, multi scope isolation (agent/user/project), and a full management CLI. Installation Option A: One Click Setup Script (Recommended) Flags: The script handles fresh installs, upgrades from git cloned versions, invalid config fields, broken CLI fallback, and provider presets (Jina, DashScope, SiliconFlow, OpenAI, Ollama). Option B: OpenClaw CLI Option C: npm Critical: When installing via npm, you must add the plugin's absolute install path to plugins.load.paths in openclaw.json . This is the most common setup issue. Minimal Configuration ( openclaw.json ) Why these defaults: autoCapture + smartExtraction → agent learns from conversations automatically, no manual calls needed autoRecall → memories injected before each reply extractMinMessages: 2 → triggers in normal two turn chats sessionMemory.enabled: false → avoids polluting retrieval with session summaries early on Full Production Configuration Provider Options for Embedding Provider provider value Notes OpenAI / compatible "openai compatible" Requires apiKey , optional baseURL Jina "jina" Requires apiKey Gemini "gemini" Requires apiKey Ollama "ollama" Local, zero API cost, set baseURL DashScope "dashscope" Requires apiKey SiliconFlow "siliconflow" Requires apiKey , free reranker tier Deployment Plans Full Power (Jina + OpenAI): Budget (SiliconFlow free reranker): Fully Local (Ollama, zero API cost): CLI Reference Validate config and restart after any changes: Expected startup log output: Memory Management CLI MCP Tool API The plugin exposes MCP tools to the agent. Core tools are always available; management tools require enableManagementTools: true in config. Core Tools (always available) memory recall Retrieve relevant memories for a query. memory store Manually store a memory. memory forget Delete a specific memory by ID. memory update Update an existing memory. Management Tools (requires enableManagementTools: true ) memory stats memory list self improvement log Log an agent learning event for meta improvement tracking. self improvement extract skill Extract a reusable pattern from a conversation. self improvement review Review and consolidate recent self improvement logs. Smart Extraction: 6 Memory Categories When smartExtraction: true , the LLM automatically classifies memories into: Category What gets stored Example profile User identity, background "User is a senior TypeScript developer" preference Style, tool, workflow choices "Prefers functional programming patterns" entity Projects, people, systems "Project 'Falcon' uses PostgreSQL + Redis" event Decisions made, things that happened "Chose Vite over webpack on 2026 02 15" case Solutions to specific problems "Fixed CORS by adding proxy in vite.config.ts" pattern Recurring behaviors, habits "Always asks for tests before implementation" Hybrid Retrieval Internals With retrieval.mode: "hybrid" , every recall runs: 1. Vector search — semantic similarity via embeddings (weight: vectorWeight , default 0.7) 2. BM25 full text search — keyword matching (weight: bm25Weight , default 0.3) 3. Score fusion — results merged with weighted RRF (Reciprocal Rank Fusion) 4. Cross encoder rerank — top candidatePoolSize candidates reranked by a cross encoder model 5. Score filtering — results below hardMinScore are dropped Retrieval mode options: "vector" — pure semantic search only "bm25" — pure keyword search only "hybrid" — both fused (recommended) Multi Scope Isolation Scopes let you isolate memories by context. Enabling all three gives maximum flexibility: When recalling, specify scope to narrow results: Weibull Decay Model Memories naturally fade over time. The decay model prevents stale memories from polluting retrieval. Memories accessed frequently get their decay clock reset Important, repeatedly recalled memories effectively become permanent Noise and one off mentions fade naturally after ~30 days Upgrading From pre v1.1.0 See CHANGELOG v1.1.0.md in the repo for behavior changes and upgrade rationale. Troubleshooting Plugin not loading Common causes: Missing or relative plugins.load.paths (must be absolute when using npm install) plugins.slots.memory not set to "memory lancedb pro" Plugin not listed under plugins.entries autoRecall not injecting memories By default autoRecall is false in some versions — explicitly set it to true : Also confirm the plugin is bound to the memory slot, not just loaded. Jiti cache issues after upgrade Memories not being extracted from conversations Check extractMinMessages — must be ≥ number of turns in the conversation (set to 2 for normal chats) Check extractMaxChars — very long contexts may be truncated; increase to 12000 if needed Verify extraction LLM config has a valid apiKey and reachable endpoint Check logs: openclaw logs follow plain grep "extraction" Retrieval returns nothing or poor results 1. Confirm retrieval.mode is "hybrid" not "bm25" alone (BM25 requires indexed content) 2. Lower rerank.hardMinScore temporarily (try 0.4 ) to see if results exist but are being filtered 3. Check embedding model is consistent between store and recall operations — changing models requires re embedding Environment variable not resolving Ensure env vars are exported in the shell that runs OpenClaw, or use a .env file loaded by your process manager. The ${VAR} syntax in openclaw.json is resolved at startup. Telegram Bot Quick Config Import If using OpenClaw's Telegram integration, send this to the bot to auto configure: Resources GitHub: https://github.com/CortexReach/memory lancedb pro npm: https://www.npmjs.com/package/memory lancedb pro Setup script: https://github.com/CortexReach/toolbox/tree/main/memory lancedb pro setup Agent skill: https://github.com/CortexReach/memory lancedb pro skill Video walkthrough (YouTube): https://youtu.be/MtukF1C8epQ Video walkthrough (Bilibili): https://www.bilibili.com/video/BV1zUf2BGEgn/

memory-lancedb-pro-openclaw