Use Case
RAGLite is a powerful AI agent skill that extends your assistant with new capabilities. Local-first RAG cache: distill docs into structured Markdown, then index/query with Chroma + hybrid search (vector + keyword). This guide walks you through installing RAGLite, configuring it for your setup, and running your first commands β so you can start getting value in minutes.
Install RAGLite: npx clawhub@latest --dir ~/.claude/skills install raglite-local-rag-cache
Restart your AI client (Claude Code, Cursor, Gemini CLI, or OpenClaw)
Type a natural language request related to data & analytics to trigger RAGLite
Review the output and refine your prompt for better results
Combine RAGLite with other skills to build multi-step workflows
Copy these prompts and use them with your AI agent after installing RAGLite
Help me get started with RAGLite
What can RAGLite do for my data & analytics workflow?
Show me an example of using RAGLite
Select your agent
Option 1: Install via CLI (recommended)
Recommended (no pre-install needed)
npx clawhub@latest --dir ~/.claude/skills install raglite-local-rag-cacheOr via clawhub CLI (if already installed)
clawhub --dir ~/.claude/skills install raglite-local-rag-cacheβ οΈ Requires Node.js 18+. No Node? Use Option 2 below to download the ZIP instead. Install Node.js β
Option 2: Manual install (no Node required)
Download the ZIP, extract it, and place the folder at the path below. Restart your agent to activate.
Install path
~/.claude/skills/raglite-local-rag-cache/π‘Extract and place the folder at the path above, then restart your agent.