Memory Lancedb Pro Openclaw
Give OpenClaw agents durable LanceDB memory with hybrid recall, reranking, and scoped storage so sessions stop forgetting decisions.
Overview
memory-lancedb-pro-openclaw is an agent skill most often used in Build (also Operate, Ship) that configures LanceDB long-term memory for OpenClaw with hybrid retrieval, reranking, scoped isolation, and recall/store tools
Install
npx skills add https://github.com/aradotso/trending-skills --skill memory-lancedb-pro-openclawWhat is this skill?
- LanceDB-backed long-term memory with automatic recall before each agent reply
- Hybrid retrieval: vector search plus BM25 full-text with cross-encoder reranking
- LLM smart extraction across 6 memory categories with Weibull decay-based forgetting
- Multi-scope isolation for agent, user, and project boundaries
- memory_recall and memory_store tools plus full management CLI and upgrade/migrate paths
- Hybrid retrieval combines vector search with BM25 full-text plus cross-encoder reranking
- LLM-powered smart extraction organized into 6 memory categories
- Weibull decay-based forgetting for aged memories
Adoption & trust: 1.2k installs on skills.sh; 31 GitHub stars; 1/3 security scanners passed (skills.sh audits).
What problem does it solve?
Your OpenClaw agent forgets preferences and decisions between sessions because nothing persists and retrieves context automatically before replies.
Who is it for?
Solo builders running OpenClaw locally who need production-style memory isolation, hybrid search, and CLI-managed LanceDB persistence.
Skip if: Builders on agents without OpenClaw plugin support, teams that forbid local vector stores, or simple one-shot chats with no cross-session continuity requirements.
When should I use this skill?
Setting up OpenClaw long-term memory; configuring memory-lancedb-pro; agent forgetting between sessions; enabling hybrid retrieval, reranking, or multi-scope isolation; using memory_recall and memory_store; migrating or
What do I get? / Deliverables
memory-lancedb-pro stores and recalls scoped memories via LanceDB with hybrid search and reranking, so the agent auto-injects relevant context using memory_recall and memory_store.
- Configured memory-lancedb-pro plugin with scoped LanceDB store
- Working memory_recall and memory_store tool behavior
- CLI-managed memory maintenance workflow
Recommended Skills
Journey fit
Spans multiple journey phases - primary shelf plus alternate fits below.
First journey stop is Build when you install and configure agent memory plugins before shipping autonomous workflows. Long-term memory, recall/store tools, and CLI management are core agent-tooling infrastructure.
Where it fits
Install memory-lancedb-pro and enable smart extraction before coding multi-day features with the same OpenClaw agent.
Tune Weibull decay and per-project scopes so production agents do not recall stale sprint decisions.
Validate recall quality and isolation rules before handing an agent to early users with persistent preferences.
How it compares
OpenClaw LanceDB memory plugin setup—not ephemeral chat history or a generic note-taking skill.
Common Questions / FAQ
Who is memory-lancedb-pro-openclaw for?
OpenClaw users and indie agent builders who need hybrid vector-plus-keyword memory, reranking, and per-agent or per-user scope isolation.
When should I use memory-lancedb-pro-openclaw?
Use it when setting up long-term memory, configuring hybrid retrieval and reranking, fixing forgotten context between sessions, migrating the plugin, or tuning multi-scope isolation—at Build agent-tooling setup and Operate infra tuning.
Is memory-lancedb-pro-openclaw safe to install?
It manages local databases and may capture conversation-derived memories; review the Security Audits panel on this Prism page, scope what gets stored, and restrict filesystem access on shared machines.
SKILL.md
READMESKILL.md - Memory Lancedb Pro Openclaw
# 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) ```bash curl -fsSL https://raw.githubusercontent.com/CortexReach/toolbox/main/memory-lancedb-pro-setup/setup-memory.sh -o setup-memory.sh bash setup-memory.sh ``` Flags: ```bash bash setup-memory.sh --dry-run # Preview changes only bash setup-memory.sh --beta # Include pre-release versions bash setup-memory.sh --uninstall # Revert config and remove plugin bash setup-memory.sh --selfcheck-only # Health checks, no changes ``` 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 ```bash openclaw plugins install memory-lancedb-pro@beta ``` ### Option C: npm ```bash npm i memory-lancedb-pro@beta ``` > **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`) ```json { "plugins": { "load": { "paths": ["/absolute/path/to/node_modules/memory-lancedb-pro"] }, "slots": { "memory": "memory-lancedb-pro" }, "entries": { "memory-lancedb-pro": { "enabled": true, "config": { "embedding": { "provider": "openai-compatible", "apiKey": "${OPENAI_API_KEY}", "model": "text-embedding-3-small" }, "autoCapture": true, "autoRecall": true, "smartExtraction": true, "extractMinMessages": 2, "extractMaxChars": 8000, "sessionMemory": { "enabled": false } } } } } } ``` **Why these defaults:** - `autoCapture` + `smartExtraction` → agent learns from conversations automatically, no manual calls needed - `autoRecall` → memories injected before each reply - `extractMinMessages: 2` → triggers in normal two-turn chats - `sessionMemory.enabled: false` → avoids polluting retrieval with session summaries early on --- ## Full Production Configuration ```json { "plugins": { "slots": { "memory": "memory-lancedb-pro" }, "entries": { "memory-lancedb-pro": { "enabled": true, "config": { "embedding": { "provider": "openai-compatible", "apiKey": "${OPENAI_API_KEY}", "model": "text-embedding-3-small", "baseURL": "https://api.openai.com/v1" }, "reranker": { "provider": "jina", "apiKey": "${JINA_API_KEY}", "model": "jina-reranker