ChatGPT costs $20 a month. Claude is $20 a month. And they both send your data to the cloud. In this live workshop you build a private AI assistant using open weight models and Docker Model Runner that runs for free on your own machine — forever.
By Packt Publishing · Refunds up to 10 days before
Most developers paying monthly AI subscriptions do not need cloud AI. They need a reliable personal assistant for their own use cases. OpenClaw and Docker Model Runner give you exactly that — at zero ongoing cost.
OpenClaw is the open-source personal AI assistant that went viral in early 2026 with 200K+ GitHub stars. It runs on your own devices and connects to WhatsApp, Telegram, Slack and more. No subscription. No data leaving your machine.
Docker Model Runner is Docker's native feature for running large language models locally on your machine. It gives you an OpenAI-compatible API that OpenClaw uses as its AI brain — complete data privacy, no cloud costs.
OpenClaw gives you the assistant interface and messaging integrations. Docker Model Runner gives you the AI brain running privately on your machine. Together they create a production grade private AI assistant you fully own.
Setting this up from scattered documentation takes days of debugging. This live workshop gives you a complete guided build in 4 hours with a live instructor answering your questions. Packt has delivered 108 workshops worldwide.
Six modules. Four hours. A working free private AI assistant by the end.
Understand the Gateway, channels, and skills architecture. Set up and configure OpenClaw locally from scratch.
Run and manage local LLMs using Docker Model Runner. Pull models, configure memory, and understand the OpenAI-compatible API.
Configure DM pairing, allowlists, sandbox mode, and proper access controls for your local AI deployment.
Deploy your AI assistant to real messaging platforms without sending data to any third party cloud service.
Design an extensible assistant architecture. Add skills, configure personality, and set up proactive automation.
Deploy your OpenClaw and Docker setup to a VPS for always-on availability running 24 hours a day.
Everything you need to never pay for a monthly AI subscription again.
A fully functional local AI assistant running on your machine
Docker Model Runner configured with your chosen LLM model
OpenClaw connected to WhatsApp or Telegram
Security and privacy configuration you can trust
A reusable architecture for future AI assistant projects
Certificate of completion from Packt Publishing
A Docker Captain who has built and deployed production AI systems without cloud dependency.
Rami is a Senior Manager of Data Science and Engineering, Docker Captain, and LinkedIn Learning Instructor with deep expertise in building and deploying production AI systems. He guides you step by step from a blank terminal to a fully deployed private AI assistant — answering your questions live throughout the 4-hour session.
Any developer tired of monthly AI bills who wants a private alternative.
Everything you need to know before you cancel your AI subscriptions.
For personal assistant tasks — answering questions, summarising content, helping with writing, coding assistance, and daily productivity — modern open weight models like Llama and Mistral running locally are excellent. They are not identical to GPT-4 but for the majority of everyday AI use cases the quality difference is minimal. This workshop helps you select the best model for your specific use cases.
After this workshop your private AI assistant runs at zero ongoing cost. You pay nothing for the open weight model, nothing for Docker Model Runner, and nothing for OpenClaw. The only cost is the hardware you already own. No subscription. No API fees. No usage limits.
ChatGPT Plus costs around $20 per month — approximately $240 per year. Claude Pro is similar. By building your own private AI assistant in this workshop you eliminate that ongoing cost entirely. The workshop fee pays for itself within a couple of months of cancelled subscriptions.
Response speed depends on your hardware. On a modern laptop with 16GB RAM running a 7B parameter model through Docker Model Runner you can expect around 10 to 30 tokens per second. This is slower than cloud APIs but perfectly usable for a personal assistant. With a GPU the speed improves significantly.
Yes. Many developers use their private OpenClaw assistant for sensitive or personal tasks and cloud AI for tasks requiring the highest capability. This workshop gives you the option — not forces you to choose one exclusively.
OpenClaw is designed to be extensible. The workshop covers the architecture so you understand how to add skills, connect to external services, and extend your assistant's capabilities over time. For the majority of everyday tasks your locally running model will perform excellently.
4 hours. Live instructor. Free private AI assistant by the end. Seats are limited.
Register Now →Sunday April 26 · 9am to 1pm EDT · Online · Packt Publishing