Setup & Installation
Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:
What This Skill Does
A local RAG-powered knowledge base that stores text, files, and URLs in SQLite with vector embeddings for semantic search. Query anything you've saved using natural language. Works as both a CLI tool and an agent-callable context store.
Semantic search means you retrieve by meaning rather than exact keywords, so you find relevant notes even when you don't remember how you phrased them.
When to use it
- Searching past meeting notes by topic
- Saving research snippets for later retrieval
- Querying your own notes with natural language
- Building agent memory across sessions
- Storing and retrieving project context
Example Workflow
Here's how your AI assistant might use this skill in practice.
User asks: what did we decide about the pricing model last week?
- 1Run query.py with the user's question as input
- 2SQLite database is searched using vector embeddings
- 3Top semantically similar chunks are retrieved
- 4Results are ranked by relevance and returned
Relevant excerpts from saved notes about pricing decisions
Requirements
Accounts, API keys, or tools you or your AI assistant may need to set up while using this skill.