Skip to content

AIO LLM + MCP + web server container collection for Meticulous Espresso

Notifications You must be signed in to change notification settings

hessius/MeticAI

Folders and files

NameName
Last commit message
Last commit date

Latest commit

Β 

History

280 Commits
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 

Repository files navigation

MeticAI Logo

MeticAI

Your AI Barista Coach for the Meticulous Espresso Machine

Create, profile and understand your espresso. 1. Take a photo or describe your coffee. Get a perfect espresso profile. Automatically. 2. Understand your profiles, shot graphs by enabling shot comparison, analysis and AI-coaching

Get Started β€’ Features β€’ Web Interface β€’ Updates


🎯 What is MeticAI?

When I got my Meticulous, after a loooong wait, I was overwhelmed with the options β€” dialing in was no longer just adjusting grind size, the potential was (and is) basically limitless β€” my knowledge and time not so.

MeticAI is a growing set of AI tools to help you get the most out of your Meticulous Espresso machine. Among other things it lets you:

  • 🧠 Automatically create espresso profiles tailored to your preferences and coffee at hand
  • πŸ“Š Understand your espresso profiles and shot data like never before
  • πŸ”¬ Get AI coaching to improve your technique
  • β˜•οΈ Unleash your Meticulous β€” no more guesswork, just great espresso

✨ What It Does

For Everyone

  • 🌐 Beautiful Web Interface - Upload photos or describe preferences from any device
  • πŸ“± Mobile Friendly - Works perfectly on your phone's browser
  • 🎨 Creative Recipe Names - Like "Slow-Mo Blossom" and "Choco-Lot Going On"
  • πŸ’¬ Natural Language - Just describe what you want in plain English
  • πŸ€– Fully Automatic - From input to machine, no steps in between

For Coffee Enthusiasts

  • 🎯 Advanced Profiling - Multi-stage extraction, blooming, pressure ramping
  • πŸ“Š Detailed Guidance - Dose, grind, temperature recommendations
  • πŸ”¬ Science-Based - Explanations of why each profile works
  • ⚑️ Modern Techniques - Turbo shots, flow profiling, and more

For Power Users

  • πŸ”Œ REST API - Integrate with any automation system
  • 🐳 Self-Hosted - Runs on Raspberry Pi or any Unix server
  • πŸ”“ Open Source - Customize and extend as you like
  • πŸ“‘ Update System - One-command updates for all components

Additional Features

  • 🍎 macOS Dock Integration - Optional dock shortcut for quick access
  • πŸ“± QR Code Setup - Easy mobile access during installation
  • πŸ”„ Automatic Updates - Built-in update system with web UI support
  • 🌍 URL Integration - Control via curl from any HTTP-capable device
  • πŸ” Secure - Self-hosted means your data stays private
  • 🎨 Modern UI - Built with React and shadcn/ui for a polished experience

πŸš€ Quick Start

What You Need

  • β˜‘οΈ A Meticulous Espresso Machine (connected to your network)
  • β˜‘οΈ A server to run MeticAI (Raspberry Pi, Mac, or Linux computer)
  • β˜‘οΈ A free Google Gemini API key β†’ Get yours here (takes 30 seconds)

Installation (5 minutes)

Option 1: macOS Installer App (Easiest for Mac users)

Download and run the standalone installer app - completely GUI-based, no terminal at all!

  1. Download the installer: MeticAI-Installer.dmg (coming soon)
  2. Open the DMG and drag "MeticAI Installer" to Applications
  3. Launch the app and follow the graphical prompts

The app will guide you through everything via dialogs:

  • βœ… Checking prerequisites (with helpful install links)
  • βœ… Choosing installation location
  • βœ… Entering API key and IP addresses
  • βœ… Background installation with progress feedback
  • βœ… Auto-opens web interface when complete

No Terminal window - 100% graphical!

β†’ Learn more about the macOS installer

Option 2: One-Line Install (Recommended for terminal users)

curl -fsSL https://raw.githubusercontent.com/hessius/MeticAI/main/web_install.sh | bash

That's it! The installer will:

  • βœ… Check for and install prerequisites (git, docker, docker-compose)
  • βœ… Detect and handle any existing MeticAI installations
  • βœ… Stop and remove running MeticAI containers if found
  • βœ… Guide you through setup (just paste your API key and machine IP)
  • βœ… Download and start all services
  • βœ… Show a QR code to access the web interface from your phone
  • βœ… [macOS only] Optionally create a Dock icon for quick access

Option 3: Manual Install

git clone https://github.com/hessius/MeticAI.git
cd MeticAI
./local-install.sh

After installation completes, scan the QR code with your phone or visit http://YOUR_SERVER_IP:3550 in a browser!

Reinstalling or Upgrading?

If you already have MeticAI installed, the installer will:

  • Detect existing containers and installation artifacts
  • Offer to run the uninstall script first for a clean installation
  • Allow you to continue anyway if you prefer to reuse existing configuration

For a clean reinstall, it's recommended to run ./uninstall.sh first.

Need Help?

πŸ“± Using MeticAI

Web Interface (Recommended)

The web interface is the easiest and most powerful way to use MeticAI. Simply open http://YOUR_SERVER_IP:3550 in any browser.

Create a profile in 3 steps:

  1. Upload a photo of your coffee bag, or describe what you want - like "bold and chocolatey" or "light and fruity"
  2. Click Create Profile
  3. ✨ Done! The recipe is now on your machine

The web interface shows real-time status, analysis results, and generated profiles with full details. It works perfectly on mobile browsers too!

API Examples

For automation and integration:

With a photo:

curl -X POST http://YOUR_IP:8000/analyze_and_profile \
  -F "file=@coffee_bag.jpg"

With text preferences:

curl -X POST http://YOUR_IP:8000/analyze_and_profile \
  -F "user_prefs=Bold and chocolatey"

With both:

curl -X POST http://YOUR_IP:8000/analyze_and_profile \
  -F "file=@coffee_bag.jpg" \
  -F "user_prefs=Traditional extraction"

β†’ Full API documentation

Advanced: iOS Shortcuts

For power users who want one-tap brewing from their iPhone, you can create custom shortcuts.

β†’ iOS Shortcuts setup guide

πŸ”„ Keeping MeticAI Updated

MeticAI has automatic updates built in!

Quick update:

./update.sh

Check without updating:

./update.sh --check-only

The system automatically:

  • βœ… Checks all components for updates
  • βœ… Shows what's new
  • βœ… Updates and rebuilds containers
  • βœ… Can even update from the web interface!

β†’ Full update system documentation

πŸ—‘οΈ Uninstalling MeticAI

Need to remove MeticAI? We've got you covered with a clean uninstallation process.

Run the uninstaller:

./uninstall.sh

The uninstaller will:

  • βœ… Stop and remove all Docker containers
  • βœ… Remove Docker images built by MeticAI
  • βœ… Remove cloned repositories (meticulous-source, meticai-web)
  • βœ… Remove configuration files (.env, settings)
  • βœ… Remove macOS integrations (Dock shortcut, rebuild watcher)
  • βœ… Ask about external dependencies (Docker, git, qrencode)

Safe by default:

  • External dependencies are NOT automatically removed
  • You'll be asked to confirm before removing anything
  • Summary shows what was removed and what was kept

Note: The uninstaller doesn't remove Docker, git, or other tools unless you explicitly choose to do so. This is safe if you use these tools for other projects.


🎨 What Makes MeticAI Special

The AI Barista Persona

MeticAI doesn't just create recipesβ€”it creates experiences with:

🎯 Witty Profile Names

  • "Slow-Mo Blossom" for gentle light roasts
  • "Choco-Lot Going On" for bold chocolatey extractions
  • "Warp Speed Espresso" for turbo shots

πŸ“Š Complete Guidance Every profile includes:

  • β˜•οΈ Recommended dose and grind settings
  • 🌑️ Temperature recommendations
  • πŸ”¬ Scientific explanation of why it works
  • βš™οΈ Any special equipment notes

πŸš€ Modern Techniques Supports advanced espresso methods:

  • Multi-stage extractions
  • Pre-infusion and blooming
  • Pressure profiling and flow control
  • Turbo shots and more

β†’ See example profiles and dialogues


πŸ“š Additional Resources

For Users

For Developers


πŸ†˜ Troubleshooting

Installation Issues

Prerequisites not installing:

  • The script auto-detects your OS and installs what's needed
  • On unsupported systems, manually install: git, docker, docker-compose
  • See TECHNICAL.md for manual setup

Can't connect to machine:

  • Verify your Meticulous machine is on the network
  • Check the IP address is correct in your .env file
  • Ensure both devices are on the same network

Usage Issues

"Connection Failed" errors:

  • Make sure MeticAI is running: docker ps
  • Check you're on the same network as the server
  • Verify the IP address in your requests

Profiles not appearing on machine:

  • Check the MCP server logs: docker logs meticulous-mcp -f
  • Verify METICULOUS_IP in .env is correct
  • Ensure the machine's API is accessible

Poor coffee analysis:

  • Take photos in good lighting
  • Ensure the label is clear and in focus
  • Try adding text preferences to guide the AI

Getting Help

Check detailed logs:

# View structured error logs
tail -f logs/coffee-relay-errors.log | jq .

# View all logs
tail -f logs/coffee-relay.log | jq .

# Or via API
curl "http://localhost:8000/api/logs?level=ERROR&lines=100"

# See LOGGING.md for more details

Check container logs:

# All services
docker compose logs -f

# Specific service
docker logs coffee-relay -f
docker logs gemini-client -f
docker logs meticulous-mcp -f

Restart services:

docker compose restart

Full reset (recommended - uses wrapper script for correct permissions):

./docker-up.sh

Full reset (manual - may require permission fix on Linux):

docker compose down
docker compose up -d --build
# If you used sudo, fix permissions:
sudo chown -R $(id -u):$(id -g) data logs meticulous-source meticai-web

For comprehensive troubleshooting and log analysis, see LOGGING.md.


πŸ™ Credits & Attribution

MeticAI is built on the excellent Meticulous MCP project by twchad and its containerized fork by @manonstreet, which provides the essential interface for controlling the Meticulous Espresso Machine.

Technology Stack

  • Google Gemini 2.0 Flash - Vision AI and reasoning
  • FastAPI - Backend API framework
  • Docker - Containerization and deployment
  • React - Web interface
  • Python - Core application logic

Open Source

MeticAI is open source and welcomes contributions!


Made with β˜•οΈ, ❀️, and πŸ€–

Get Started β€’ Features β€’ Documentation

About

AIO LLM + MCP + web server container collection for Meticulous Espresso

Resources

Stars

Watchers

Forks

Packages

No packages published

Contributors 4

  •  
  •  
  •  
  •  

Languages