菜单
Companion scripts for OpenClaw memory-lancedb: vector index builder with Google/Ollama embeddings, fast semantic search with FTS5 hybrid scoring, and unified multi-source search. Solves LanceDB's weak full-text search for non-English languages.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Deploy KERNEL_INTUITION_Cp on any AI architecture with calibrated thresholds. Use when user wants to "activate Cp", "setup creative intuition", "deploy kernel on [AI]", "enable intuition mode", or mentions activating computational intuition on a specific model. Also trigger for "configure Cp for [architecture]" or "calibrate creative thresholds". This skill handles the full activation workflow including architecture profiling, threshold calibration, kernel generation, and monitoring setup.
Three-Layer Thinking Chain Architecture — Personality-Driven Agent Self-Evolution Framework
CLI to manage emails via IMAP/SMTP. Use `himalaya` to list, read, write, reply, forward, search, and organize emails from the terminal. Supports multiple accounts and message composition with MML (MIME Meta Language).
OpenProse VM skill pack. Activate on any `prose` command, .prose files, or OpenProse mentions; orchestrates multi-agent workflows.
Delegate coding tasks to Codex, Claude Code, Cursor Agent, or Pi agents via background process. Use when: (1) building/creating new features or apps, (2) reviewing PRs (spawn in temp dir), (3) refactoring large codebases, (4) iterative coding that needs file exploration. NOT for: simple one-liner fixes (just edit), reading code (use read tool), thread-bound ACP harness requests in chat (for example spawn/run Codex or Claude Code in a Discord thread; use sessions_spawn with runtime:"acp"), or any work in ~/clawd workspace (never spawn agents here). Claude Code: use --print --permission-mode bypassPermissions (no PTY). Codex/Pi/OpenCode/Cursor Agent: pty:true required.
Host security hardening and risk-tolerance configuration for OpenClaw deployments. Use when a user asks for security audits, firewall/SSH/update hardening, risk posture, exposure review, OpenClaw cron scheduling for periodic checks, or version status checks on a machine running OpenClaw (laptop, workstation, Pi, VPS).
| name | memory-tools |
| description | Companion scripts for OpenClaw memory-lancedb: vector index builder with Google/Ollama embeddings, fast semantic search with FTS5 hybrid scoring, and unified multi-source search. Solves LanceDB's weak full-text search for non-English languages. |
| homepage | https://looi.ru/a/looi-clawd |
| metadata | {"author":"Arthur Arsyonov","license":"MIT"} |
OpenClaw's memory-lancedb plugin uses OpenAI embeddings only and has weak full-text search for non-English languages (no stemming, no morphology). For Russian and other inflected languages, recall is poor.
Python scripts that build a parallel vector+FTS5 index over your chat history:
gemini-embedding-2-preview (fallback: Ollama nomic-embed-text), stores in SQLitenomic-embed-text~/.openclaw/lcm.db)# Place in your OpenClaw workspace
cp -r memory-tools/ ~/.openclaw/workspace/scripts/memory/
# Install dependencies
pip3 install numpy
# Build the index (first run takes a while)
python3 build_vector_index.py
# Search
./search_history.sh "your query here" 10
lcm.db (chat history)
│
├─ build_vector_index.py ──→ chat_vectors.db (SQLite + FTS5)
│ Google embeddings (primary)
│ Ollama embeddings (fallback)
│
├─ search_history_fast.py ──→ Hybrid vector+lexical search
│ numpy memmap for fast cosine similarity
│ FTS5 for morphology-aware text matching
│ Score fusion: 0.65 * vector + 0.35 * lexical
│
└─ unified_search.py ──→ Multi-source orchestrator
vector DB + entity graph + raw LCM
Set via environment variables:
| Variable | Default | Description |
|---|---|---|
OLLAMA_HOST | http://localhost:11434 | Ollama server URL |
GOOGLE_AI_API_KEY | from openclaw.json | Google AI API key for embeddings |