> For the complete documentation index, see [llms.txt](https://yeasy.gitbook.io/openclaw_guide/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://yeasy.gitbook.io/openclaw_guide/readme_en.md). # OpenClaw: Beginner to Expert [中文文档](/openclaw_guide/readme.md) ## OpenClaw: Beginner to Expert [![License: CC BY 4.0](https://img.shields.io/badge/License-CC%20BY%204.0-lightgrey.svg)](https://creativecommons.org/licenses/by/4.0/) [![GitHub stars](https://img.shields.io/github/stars/yeasy/openclaw_guide?style=social)](https://github.com/yeasy/openclaw_guide) [![Release](https://img.shields.io/github/release/yeasy/openclaw_guide.svg)](https://github.com/yeasy/openclaw_guide/releases) [![Online Reading](https://img.shields.io/badge/Read_Online-GitBook-brightgreen)](https://yeasy.gitbook.io/openclaw_guide) [![PDF](https://img.shields.io/badge/PDF-Download-orange)](https://github.com/yeasy/openclaw_guide/releases/latest) > [**OpenClaw**](https://github.com/openclaw/openclaw) **is an open-source, local-first personal AI assistant**, created by Peter Steinberger. This book provides a comprehensive guide from getting started to production deployment, with deep dives into the underlying mechanisms and implementation principles. OpenClaw Guide Cover ### Highlights > Note: this English page is currently an overview. The full chapter-by-chapter content is maintained in Chinese; for complete reading, use the Chinese README and table of contents. * **Hands-on**: Build a minimal working loop from scratch, with ready-to-use configuration templates * **Deep Dives**: Detailed analysis of Gateway, Agent Loop, tool system, sessions and memory * **Production-Ready**: Focus on reliability, security hardening, monitoring and troubleshooting ### Target Audience & Prerequisites * **Target Audience**: Individual users interested in AI agents, AI application developers, LLM engineers, system architects, etc. * **Prerequisites**: Basic backend development familiarity is expected, such as Node.js or Python fundamentals. If you are new to LLMs and AI agents, see [AI Beginner Guide](https://github.com/yeasy/ai_beginner_guide) and [Agentic AI Guide](https://github.com/yeasy/agentic_ai_guide). ### Book Structure | Part | Chapters | Overview | | ------------------------------- | -------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | Part 1: Getting Started | Ch 1–4 | Overview, setup, first conversation, configuration & model access | | Part 2: Advanced Usage | Ch 5–8 | Tools & skills, context memory, multi-agent collaboration, automation & ops | | Part 3: Internals & Engineering | Ch 9–12 | Gateway protocol, Agent Loop internals, reliability, plugin extensions | | Part 4: Practice & Optimization | Ch 13–16 | Case studies, performance & cost optimization, troubleshooting, AI ecosystem integration | | Appendix | — | Glossary, config templates, troubleshooting checklist, API reference, command cheatsheet, version mapping, further reading, environment self-check tool, naming history, volatile facts table | ### How to Read #### Online * [GitBook Online](https://yeasy.gitbook.io/openclaw_guide/) * [Chinese Full Edition](/openclaw_guide/readme.md) #### Local Preview This repository uses mdPress for building. For local preview: ```bash brew tap yeasy/tap && brew install mdpress mdpress serve ``` Other Markdown previewers can be used as auxiliary tools, but they are not the standard build chain for this repository. ### 5-Minute Quick Start New to OpenClaw? Just three steps: 1. **Install** (1 min): `curl -fsSL https://openclaw.ai/install.sh | bash -s -- --no-onboard` (locked-down environments should download and inspect the script first, or use the official manual/npm path) 2. **Initialize** (2 min): `openclaw onboard --install-daemon` → follow the wizard to configure your model API key and install the background service 3. **Chat** (2 min): Run `openclaw dashboard`, type "hello" in the Control UI chat, receive an AI response — you're done! 🎉 See [Chapter 2: Setup](/openclaw_guide/di-yi-bu-fen-ji-chu-ru-men/02_setup.md) and [Chapter 3: First Conversation](/openclaw_guide/di-yi-bu-fen-ji-chu-ru-men/03_minimal_loop.md). ### Learning Paths Different readers can choose their path: | Role | Core Chapters | Est. Time | What You'll Achieve | | --------------- | -------------- | ---------- | ---------------------------------------------------------------- | | Individual User | 1→2→3→5→7 | 3-4 hours | Build a personal WhatsApp/Telegram AI assistant | | App Developer | 1-7→12 | 8-10 hours | Develop custom tools, skills and multi-agent systems | | Ops Engineer | 2→3→8→11→14→15 | 6-8 hours | Production deployment, security hardening & troubleshooting | | Architect | 1→9→10→12→16 | 6-8 hours | Understand internals, design enterprise-grade agent architecture | ### Related Books This book is part of an AI technology series: | Book | Relationship | | ------------------------------------------------------------------------------- | ------------------------------------------------- | | [AI Beginner Guide](https://github.com/yeasy/ai_beginner_guide) | Zero-to-one AI introduction | | [Prompt Engineering Guide](https://github.com/yeasy/prompt_engineering_guide) | Agent prompt design fundamentals | | [Context Engineering Guide](https://github.com/yeasy/context_engineering_guide) | Context management & memory architecture | | [Claude Guide](https://github.com/yeasy/claude_guide) | Claude MCP protocol, tools & Agentic Coding | | [Agentic AI Guide](https://github.com/yeasy/agentic_ai_guide) | General agent architecture & multi-agent patterns | | [AI Security Guide](https://github.com/yeasy/ai_security_guide) | Agent security design & attack/defense practices | | [LLM Internals](https://github.com/yeasy/llm_internals) | Deep dive into LLM architecture | ### Contributing Welcome to submit [Issues](https://github.com/yeasy/openclaw_guide/issues) or [PRs](https://github.com/yeasy/openclaw_guide/pulls). Especially welcome: typo fixes, broken link repairs, case study additions, and reusable templates. ### License This book is licensed under [CC BY 4.0](https://creativecommons.org/licenses/by/4.0/).