本课程教你如何在Windows或macOS上用Docker部署本地OpenClaw AI智能体，连接Google Gemini 2.5 Flash，在沙箱中安全自动化读取、分析文件并生成摘要报告，实现安全第一的本地文件处理闭环。
原始标题：OpenClaw Part 1: Build a Local AI Agent with Docker & Gemini
本课程详细教授如何在 Windows 或 macOS 电脑上，利用 Docker 沙箱安全地在本地部署自托管的 OpenClaw AI 智能体。你将配置清晰的 config 与 workspace 目录结构，并连接 Google Gemini 2.5 Flash 接入强大的 AI 大脑，使智能体能够在绝对安全的隔离环境中自动探索本地文件夹、读取并分析文件。课程不仅涵盖端到端的实操搭建，还融入了安全第一的防误配置思维，最终让智能体为你自动生成可读性极高的本地 .txt 摘要报告，帮你打破传统云端对话限制，实现本地文件处理自动化的闭环。
Published 7/2026
Created by Kevin Hwang
MP4 | Video: h264, 1920×1080 | Audio: AAC, 44.1 KHz, 2 Ch
Level: Beginner | Genre: eLearning | Language: English | Duration: 16 Lectures ( 2h 13m ) | Size: 1.3 GB
Run a security-first local AI agent on your PC with Docker & Gemini. Explore folders, summarize files, and automate repo
What you’ll learn
⚡ Build and run a local OpenClaw AI agent on your own PC using Docker
⚡ Connect Google Gemini 2.5 Flash as the “brain” of your OpenClaw agent
⚡ Set up a clean `config` and `workspace` folder structure for your agent’s files
⚡ Let your agent explore a folder and automatically generate human-readable summary reports
⚡ Apply a security-first mindset to OpenClaw by using Docker sandboxing and avoiding common misconfigurations
⚡ Understand when to use a local PC, an old laptop, or a VPS to host your AI agent
Requirements
❗ Basic computer skills and ability to install software on your machine
❗ Comfortable reading and typing simple commands in a terminal or command prompt
❗ A Windows or macOS computer that can run Docker Desktop
❗ A Google account to access Google AI Studio
❗ Interest in security and self-hosted tools is a plus, but not required
Description
You’ve tried chatbots. Now it’s time to build a reallocal AI agent that can explore your folders, understand your files, and write reports for you — all inside a secure Docker sandbox on your own PC.
1. Problem & promise
Most AI tools live in the cloud and only answer questions one message at a time. They can’t safely reach into your own files, remember your folders, or run repeatable workflows on your machine. In this course, you’ll build a self-hosted AI agent with OpenClaw that actually does things for you: scanning folders, summarizing documents, and generating clear reports locally.
2. What you’ll build
Step by step, we’ll set up OpenClaw on your computer using Docker, connect Google Gemini 2.5 Flash as the “brain”, and create a dedicated `workspace` where your agent can safely read and write files. By the end of Part 1, your agent will be able to explore a folder on your PC and automatically generate a human-readable `.txt` summary report of what it finds. You’ll see the entire workflow end to end, from first install to your first real automation.
3. How we’ll get there
We start with the basics: what agentic AI is, how OpenClaw is different from a simple chatbot, and which machine (PC, old laptop, or VPS) is best for you. Then we install Docker, create the `config` and `workspace` folders, and wire everything together with `docker-compose.yml` and a simple `.env` file. Next, we create a Gemini 2.5 Flash API key, connect it to OpenClaw, boot the agent for the first time, and run a complete “folder exploration + summary report” demo that you can customize.
4. Who this is for
This course is designed for beginner–junior developers, tech-curious professionals, and indie makers who want to go beyond copy‑pasting prompts into a web UI. If you’re comfortable installing apps and typing simple commands into a terminal or command prompt, you’ll be able to follow along. You do not need to be a DevOps expert or an AI researcher — we focus on practical steps and explain each decision along the way.
5.Security-first angle
OpenClaw is powerful because it can touch real files, but that also means security matters. Throughout the course, we use Docker as a sandbox so your agent runs in an isolated environment on your machine, not directly on your host system. In a dedicated security lesson, we review what your current setup does well, where it can still break, and simple habits you can use to keep your self-hosted AI agent as safe as possible. This way, you don’t just build “another cool demo” — you build a local AI agent with security in mind from day one.
Who this course is for
⭐ Beginner–Junior developers who want to build their first real AI agent
⭐ Tech-curious professionals who are comfortable with basic tools and want to automate real work
⭐ Indie makers and solo founders who prefer self-hosted, privacy-friendly AI over pure cloud SaaS
⭐ Anyone who wants a security-first introduction to running OpenClaw with Docker and Gemini
百度网盘下载：
