CandleKeep
CandleKeep
Anthropic

The Complete OpenClaw Developer Guide

by Marudi

programming
Pages148
Formatmarkdown
ListedJune 8, 2026
UpdatedJune 14, 2026
Subscribers10

About

A comprehensive guide to building AI agents with OpenClaw — from installation and first steps to advanced multi-agent orchestration, production deployment, and real-world examples. Covers all features, configuration, tools, patterns, and best practices. Tags: ai, agents, openclaw, development, guide.

148Chapters
637Topics
148Pages

Preview

The Complete OpenClaw Developer Guide

Load this book when:

  • You are installing, configuring, or operating an OpenClaw Gateway and need the exact config keys, CLI commands, or directory layout.
  • You are authoring agents (bootstrap files, skills, MCP servers) or multi-agent workflows (OpenProse / Task Flow).
  • You are hardening or debugging a production OpenClaw deployment (cost runaways, CVEs, ClawHub skill risk, auth/cache issues).
  • You are deciding whether OpenClaw fits a use case versus Claude Code / LangChain / AutoGen / CrewAI.

Audience & governance: Public marketplace reference. Maintainer: Marudi. Attribution required; built from openclaw.ai docs, github.com/openclaw/openclaw, and cited community/security sources.

Last updated: 2026-06-14 · Scope of validity: OpenClaw v2026.6.x. Version-pinned facts (CLI flags, config keys, CVE list, model IDs) expire fastest — see Chapter 17 (Currency & Scope) before trusting any version-specific claim.

How to use this book

  1. Read this page and the Decision Matrix (Chapter 2).
  2. Jump to the chapters the matrix lists for your task. Do not read linearly.
  3. Each chapter opens with its own > Load this page when: trigger and is self-contained.
  4. Cross-references use chapter numbers within this book and CandleKeep IDs across books.

Table of Contents

  1. Introduction to OpenClaw
  2. Decision Matrix ← start here for navigation
  3. Core Concepts and Architecture
  4. Installation and Environment Setup
  5. Your First OpenClaw Agent
  6. Configuration Deep Dive
  7. Built-in Tools Reference
  8. Building Custom Tools
  9. Agent Patterns and Workflows
  10. Memory and State Management
  11. Error Handling and Debugging
  12. Multi-Agent Systems
  13. Production Deployment
  14. Advanced Patterns
  15. Real-World Use Cases and Complete Examples
  16. Reference Guide and Appendices
  17. Currency & Scope of Validity
  18. Corrections & Stale-Fact Supersedes
Add to library to read more

Table of Contents

Install on macOS or Linux
Or via npm
Run the onboarding wizard (handles daemon setup, channel config, and workspace initialization)
Verify

Chapter 2 — Decision Matrix

1. Check that the gateway process is running and listening
Expected output: something like "Gateway running on port 18789"
2. Confirm the default agent is reachable
Expected output: agent ID, model, session count
3. Open the Control UI in your browser

Stream live logs

/etc/openclaw.env (mode 600, owned by openclaw user)

Development
Staging

Authenticate with ClawHub
Validate the skill package
Publish

File: summarize-and-translate.prose

File: parallel-research.prose

File: research-and-publish.prose
Phase 1: Parallel research (fan-out)
Phase 2: Draft (sequential)
Phase 3: Verify (sequential)
Phase 4: Conditional revision

Count conversation turns in a session

Inspect the auth chain for a specific agent

WhatsApp: re-scan QR code
Telegram: verify token and webhook

Clear session state for one agent (preserves auth profiles)
Do NOT delete:

Live stream
Structured stream with local timestamps
Pipe to jq for filtering
Find all error events across session files

research-verify.prose

parallel-research.prose

1. Provision server, SSH in
2. Create a low-privilege user — never run OpenClaw as root
3. Install Node 24 (via nvm for easy version management)
4. Install OpenClaw and run onboarding

/etc/openclaw/environment (chmod 600, owned by openclaw user)
.env (in .gitignore)

Count completed turns per agent
Find error events from the last 24 hours

deploy-config.sh

Add a local vector search MCP server

Start the Gateway daemon
Stop a running Gateway
Restart (applies config changes without clearing sessions)
Check whether the Gateway is running and on which port
Launch in development mode (verbose, hot-reload)

Run the interactive onboarding wizard (recommended for first install)
Re-run setup for workspace bootstrap files only

List all configured agents
Create a new agent
Show current configuration for an agent
Dump the full runtime state of an agent (model, skills, memory)
Check whether an agent is active and responsive
Set a configuration value for an agent

List connected channels and their status
Reconnect a channel that has dropped (e.g., after WhatsApp QR expiry)

Install a skill from ClawHub
List installed skills
Enable a plugin
Disable a plugin

Follow live log output (human-readable)
Follow with structured JSON output
Show timestamps in local time

Diagnose common configuration problems
Diagnose and auto-fix common problems
Run a full pre-deployment security audit

Chapter 17 — Currency & Scope of Validity

Add to Library

Free · Live updates included

10 readers subscribed