A personal productivity AI assistant running locally costs nothing per conversation, keeps your work conversations private, and connects to WhatsApp or Telegram for instant access. This live workshop shows you how to build one using OpenClaw and Docker Model Runner in 4 hours.
By Packt Publishing · Refunds up to 10 days before
Cloud productivity AI assistants charge per use and process your work conversations on external servers. A locally running productivity AI assistant costs nothing per conversation and keeps your productivity data — including sensitive work content — completely private on your own machine.
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. One working private AI assistant by the time you finish.
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.
Concrete working deliverables — not just theory.
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
Rami Krispin builds and uses locally running productivity AI tools in his own daily work.
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.
You do not need to be an expert. You do need the basics.
Common questions about the workshop, what to expect, and how to prepare.
For most everyday productivity tasks — drafting, summarising, explaining, brainstorming — a locally running open weight model performs at a level comparable to cloud AI. The key advantages of local are: zero cost per query, complete privacy for sensitive work content, and no dependency on external services.
Yes. This is one of the primary reasons to build a locally running productivity AI assistant. A locally running AI processes everything on your own machine — your confidential work conversations never leave your device.
Response time varies by hardware and model. On a laptop with 16GB RAM using Mistral 7B, typical productivity queries receive responses in 5 to 15 seconds. For faster responses, Phi-3 Mini delivers results in 3 to 8 seconds at slightly reduced quality.
With VPS deployment your productivity AI assistant is accessible from any device through WhatsApp or Telegram. For laptop-only deployment the assistant is accessible when your laptop is running. The workshop covers both scenarios.
Open weight models have training data cutoffs. For productivity tasks requiring current information, the instructor covers how to configure OpenClaw skills that can fetch specific real-time information when needed, extending your local AI's utility beyond its training cutoff.
Yes. OpenClaw's system prompt configuration lets you customise your productivity AI assistant's communication style, area of focus, and behaviour. You can instruct it to be concise, technical, formal, or casual. The instructor covers personalisation configuration during the workshop.
4 hours. Live instructor. Local productivity AI assistant working by the end. Seats are limited.
Register Now →Sunday April 26 · 9am to 1pm EDT · Online · Packt Publishing