Hormozi Mentor Agent
Answers queries based on Alex Hormozi's YouTube content using local RAG with SQLite and vector embeddings.
README
Hormozi Mentor Agent
Alex Hormozi RAG mentor agent. Katie calls hormozi_query() and gets answers grounded in Hormozi's actual YouTube content.
Stack
- SQLite + sqlite-vec (local, always-on, no cloud DB needed)
- Voyage AI
voyage-3-liteembeddings (1024 dimensions) - YouTube Data API v3 +
youtube-transcriptnpm - Claude
claude-sonnet-4-6for synthesis - MCP server registered with mcporter
Prerequisites
-
sqlite-vec — install on Mac mini:
brew install sqlite-vec -
Environment variables — copy
.env.exampleto.envand fill in:YOUTUBE_API_KEY— Google Cloud Console → APIs → YouTube Data API v3 → Create KeyVOYAGE_API_KEY— sign up at voyageai.com (free tier, 5 minutes)ANTHROPIC_API_KEY— already in Mark's environment
Setup
npm install
npm run db:init
Ingestion
# Full channel load (run once — ~30-60 min for 600+ videos)
npm run ingest
# Subsequent manual refresh (only fetches new videos)
npm run cron
Query (CLI test)
npm run query "what would you do about cold calling pricing objections?"
Run the MCP Server
# stdio mode (for mcporter)
node dist/index.js --stdio
# HTTP mode (with health endpoint + built-in weekly cron)
node dist/index.js
# http://localhost:3456/health
mcporter Registration
After building (npm run build), register with mcporter on the Mac mini:
mcporter add hormozi-mentor --command "node /path/to/hormozi-mentor/dist/index.js --stdio"
Or if running as HTTP server:
mcporter add hormozi-mentor --url http://localhost:3456/mcp
Mac mini launchd Cron (Weekly Refresh)
Create /Library/LaunchDaemons/com.marksapp.hormozi-mentor-cron.plist:
<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE plist PUBLIC "-//Apple//DTD PLIST 1.0//EN" "http://www.apple.com/DTDs/PropertyList-1.0.dtd">
<plist version="1.0">
<dict>
<key>Label</key>
<string>com.marksapp.hormozi-mentor-cron</string>
<key>ProgramArguments</key>
<array>
<string>/usr/local/bin/node</string>
<string>/Users/mandyassistant/Desktop/MarkProjects/hormozi-mentor/dist/cron-ingest.js</string>
</array>
<key>StartCalendarInterval</key>
<dict>
<key>Weekday</key>
<integer>0</integer>
<key>Hour</key>
<integer>2</integer>
<key>Minute</key>
<integer>0</integer>
</dict>
<key>EnvironmentVariables</key>
<dict>
<key>YOUTUBE_API_KEY</key>
<string>YOUR_KEY_HERE</string>
<key>VOYAGE_API_KEY</key>
<string>YOUR_KEY_HERE</string>
<key>ANTHROPIC_API_KEY</key>
<string>YOUR_KEY_HERE</string>
<key>DB_PATH</key>
<string>/Users/mandyassistant/Desktop/MarkProjects/hormozi-mentor/hormozi.db</string>
</dict>
<key>StandardOutPath</key>
<string>/tmp/hormozi-mentor-cron.log</string>
<key>StandardErrorPath</key>
<string>/tmp/hormozi-mentor-cron.err</string>
</dict>
</plist>
Load it:
sudo launchctl load /Library/LaunchDaemons/com.marksapp.hormozi-mentor-cron.plist
Notes
- The
books/directory is gitignored. Drop Hormozi PDFs there for book ingestion (Phase 2). - The
hormozi.dbfile is gitignored. It lives on the Mac mini only. - Weekly cron also runs automatically when the HTTP server is up (built into
src/index.tsvia node-cron).
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.