vector-memory

Smart memory search with automatic vector fallback. Uses semantic embeddings when available, falls back to built-in search otherwise. Zero configuration - works immediately after ClawHub install. No setup required - just install and memory_search works immediately, gets better after optional sync.

Install only if you are comfortable with a memory tool that can install npm dependencies, download/cache an embedding model, create a persistent local index of memory files, and run sync commands. Prefer manual installation from reviewed source, avoid the curl-to-bash path, and do not expose this tool to untrusted prompts or users until memory_get path validation and shell command construction are fixed.

Package: vector-memory (mcp) Version: 2.1.1 Description: Smart memory search with automatic vector fallback. Uses semantic embeddings when available, falls back to built-in search otherwise. Zero configuration - works immediately after install. The package provides a local vector-based memory search system for the OpenClaw agent framework. It utilizes the Transformers.js library to generate embeddings locally using the all-MiniLM-L6-v2 model, enabling semantic search capabilities without external API calls. The codebase includes a smart wrapper (smart_memory.js) that automatically switches between neural vector search and a keyword-based fallback search depending on the availability of the index. It manages memory files within a specific workspace directory, implements semantic chunking, and provides a CLI for indexing and searching. No malicious behavior, unauthorized data exfiltration, or suspicious network activity was detected; the installation script and file operations are consistent with the stated purpose of an agent skill extension.