yahboom
HomeLearn
Solution
Blog
Online Store
About Us
EN/中文
RDK S600 Developer Kit📖
1.RDK S600 board introduction
  • 1.1 RDK S600 board introduction
  • 1.2 System Flashing
  • 1.3 Hardware Interface Description
  • 1.4 Accessory Installation
  • 1.5 Camera Expansion Board
  • 1.6 MCU Interface Expansion Board
  • 1.7 Precautions for Using the 15.6-inch Screen
  • 1.8 System Boot Modes
2.RDK S600 basic course
  • 2.1 Network Configuration
  • 2.2 Remote Login
  • 2.3 System Update
  • 2.4 Boot Auto-Start Configuration
  • 2.5 RDK Exclusive Command Usage
  • 2.6 Linux Command Usage
  • 2.7 Examples of GPIO Read and Write Operations
  • 2.8 Using the USB Camera
  • 2.9 Solid-state mounting
  • 2.10 SSD expansionnew
3.TogetheROS.Bot Vision Applications
  • 1. About TogetheROS. Bot
  • 2. System Installation
  • 3. Object Detection(YOLO)
  • 4. Image Classification(mobilenetv2)
  • 5. Image Segmentation(mobilenet_unet)
  • 6. Perception Algorithm(BEV)
  • 7. Human Detection and Tracking (Ultralytics YOLO Pose)
4. Offline AI Large Model Development
Offline large model (Text Interaction)
  • 1. AI large model environment deployment
  • 2. Install large model dialogue platform
  • 3. Meta AI Llama 3.2 model
  • 4. Alibaba Cloud Qwen3 model
  • 5. Microsoft Phi-4 mini model
  • 6. DeepSeek - DeepSeek-R1 model
  • 7. Alibaba Cloud Qwen2.5vl Visual Multimodal Large Model
  • 8. Google Gemma3 Visual Multimodal Large Model
  • 9. Lava Visual Multimodal Large Model
  • 10. MiniCPM-V Visual Multimodal Large Model
  • 11. Multimodal visual understand application
  • 12. Multimodal text image application
  • 13. Multimodal visual localization application
  • 14. Multimodal table scanning application
  • 15. Multimodal Autonomous Agent Applications
Offline large model (Voice Interaction)
  • 0. Voice Interaction Hardware Connection (Must Read)
  • 1. Offline speech-to-text (ASR)
  • 2. Offline Text-to-Speech (TTS)
  • 3. AI large model voice interaction
  • 4. Multimodal visual understanding voice interaction
  • 5. Multimodal Text-to-Image application
  • 6. Multimodal video analytics application
  • 7. Multimodal visual localization application
  • 8. Multimodal table scanning application
  • 9. Multimodal autonomous agent application
  • 10. AI Large Model Offline Voice Assistant
5. Online AI Large Model Development
Online large model (Text Interaction)
  • 1.OpenRouter large model API aggregation platform
  • 2.Multimodal visual understand application
  • 3.Multimodal visual localization application
  • 4.Multimodal table scanning application
  • 5.Multimodal autonomous proxy application
Online large model (Voice Interaction)
  • 0.Voice interaction hardware connection (ReadMe)
  • 1.Online speech to text (ASR)
  • 2.Online text to speech (TTS)
  • 3.AI large model voice interaction
  • 4.Multimodal visual understand speech interaction
  • 5.Multimodal visual localization application
  • 6.Multimodal table scanning application
  • 7.Multimodal autonomous proxy application
  • 8.AI large model online voice assistant
6.YOLO26 tutorials
  • 01.YOLO26 environment
  • 02.CLI use
  • 03.Object detection
  • 04.Instance segmentation
  • 05.Pose estimation
  • 06.Image classification
  • 07.Oriented object detection
  • 08.Model conversion
  • 09.Dataset annotation
  • 10.Model training - conversion
  • 11.Model prediction
7.OpenClaw Advanced Development
  • 1. OpenClaw Deployment
  • 2. OpenClaw and WhatsApp Plugin Application
  • 3. OpenClaw TUI Interaction
  • 4. OpenClaw WebChat Interaction
  • 5. OpenClaw Gate Gateway Operation Manual
  • 6. OpenClaw Plugin Function Introduction
  • 7. OpenClaw Tools Introduction
  • 8. OpenClaw ClawHub Introduction (skill Installation)
  • 9.OpenClaw Application - File Management
  • 10.OpenClaw Application - Browser Control
  • 11.OpenClaw Application - Camera
  • 12.OpenClaw Application - Script Execution
  • 13.OpenClaw Application - AI Programming (Peripheral & GPIO Control)
  • 14. OpenClaw Application - Dedicated AI Assistant
  • 15. OpenClaw Configure Web Search Capability
8.ROS2 basic course
  • 1.Introduction to ROS2
  • 2.ROS2 install Jazzy
  • 3.ROS2 development environment
  • 4.ROS2 workspace
  • 5.ROS2 function package
  • 6.ROS2 node
  • 7.ROS2 topic communication
  • 8.ROS2 service communication
  • 9.ROS2 action communication
  • 10.ROS2 custom interface message
  • 11.ROS2 parameter service case
  • 12.ROS2 meta-function package
  • 13.ROS2 distributed communication
  • 14.ROS2 DDS
  • 15.ROS2 time related API
  • 16.ROS2 common command tools
  • 17.ROS2 rviz2 use
  • 18.ROS2 rqt toolbox
  • 19.ROS2 Launch startup file configuration
  • 20.ROS2 recording and playback tool
  • 21.ROS2 URDF model
  • 22.ROS2 Gazebo simulation platform
  • 23.ROS2 TF2 coordinate transformation
Download
  • System_File
  • Code
  • 3D_Model_File
  • Tools_Software
Download ZIP

Welcome to RDK S600 Developer Kit repository

5. OpenClaw Gate Gateway Operation Manual

6. OpenClaw Gateway Operation Manual

Gateway is OpenClaw's persistent process: it maintains message channel connections, hosts the control and event plane, and serves as the unified entry point for sessions, routing, and channel state. Simply put: whether you can "connect to OpenClaw", whether the console can open, and whether messages can come in often depends on whether the Gateway is running properly.

6. OpenClaw Gateway Operation Manual1. When Do You Need to Care About the Gateway2. Fastest Way to Start (Local)3. What "External Interfaces" Does the Gateway Provide4. Hot Reload and Changes That "Need Restart"5. Authentication and Remote Access (Easiest Pitfalls)5.1 Gateway Authentication (token/password)5.2 Recommended Way for Remote Access: Tunnel First, Then Access5.3 Console Won't Open via Pure HTTP (device identity required)6. Multi-Instance and "Rescue Bot" Mode7. Troubleshooting Sequence, Usually Can Locate7.1 Check Status First7.2 Gateway Won't Start: Configuration Validation Failed7.3 Common Phenomenon: Service Installed But Not Actually Running

1. When Do You Need to Care About the Gateway

Most of the time, you just need to let it run stably; you only need to specifically check/learn about the gateway in these scenarios:

  • Opening the console on the RDK browser often gives errors, planning to switch to TUI or remote access

  • Configuration changed but "feels like it didn't take effect", suspect hot reload/restart wasn't triggered

  • Want to open the console to LAN or access via SSH/Tailscale remotely

  • Want multi-instance isolation (e.g., "rescue bot"/redundancy)

  • Port conflicts, process won't start, service "looks installed but not running"

2. Fastest Way to Start (Local)

Execute on the gateway host (e.g., RDK):

xxxxxxxxxx
openclaw gateway

Common parameters:

​x
# Print more complete debug/trace info to current terminal (helpful for troubleshooting)
openclaw gateway --port 18789 --verbose

# When port is occupied, try to kill the listener occupying the port and force start
openclaw gateway --port 18789 --force

Port priority (high to low): --port > OPENCLAW_GATEWAY_PORT > gateway.port > default 18789.

3. What "External Interfaces" Does the Gateway Provide

The same port (default 18789) provides both WebSocket control plane and HTTP service (control interface, hooks, A2UI, etc.) at once. This is "single-port multiplexing".

Common points you will use:

  • Local console: http://127.0.0.1:18789/

  • OpenAI Chat Completions compatible interface: /v1/chat/completions

  • OpenResponses interface: /v1/responses

  • Tool invocation interface: /tools/invoke

Additionally, the gateway starts Canvas static file service by default (default port 18793), providing editable HTML/A2UI resources (served from ~/.openclaw/workspace/canvas by default). To disable, set canvasHost.enabled=false or OPENCLAW_SKIP_CANVAS_HOST=1.

4. Hot Reload and Changes That "Need Restart"

The gateway monitors ~/.openclaw/openclaw.json (or the path specified by OPENCLAW_CONFIG_PATH). Configuration updates are usually applied automatically. The default reload mode is gateway.reload.mode="hybrid": safe changes are hot-applied, critical changes trigger restart.

You can explicitly configure reload behavior:

xxxxxxxxxx
{
  "gateway": {
    "reload": { "mode": "hybrid", "debounceMs": 300 }
  }
}

Experience suggestions:

  • Changing models, agents, routing, and other business configurations usually don't require manual restart

  • Changing gateway.* (port, binding, authentication, TLS, HTTP, etc.) are infrastructure changes and more likely to trigger restart

5. Authentication and Remote Access (Easiest Pitfalls)

5.1 Gateway Authentication (token/password)

Gateway has authentication enabled by default: you can set gateway.auth.token (or OPENCLAW_GATEWAY_TOKEN) or gateway.auth.password. Clients need to carry connect.params.auth.token/password when connecting.

If you use the wizard flow, a token is usually generated by default (even if only bound to loopback).

5.2 Recommended Way for Remote Access: Tunnel First, Then Access

Most recommended: Tailscale/VPN. Next: SSH tunnel.

Example (map remote 18789 to local 18789):

xxxxxxxxxx
ssh -N -L 18789:127.0.0.1:18789 user@host

Then you access locally:

  • Web: http://127.0.0.1:18789/

  • WS: ws://127.0.0.1:18789

Note: Even through the tunnel, if the gateway is configured with a token, clients still need to bring the token to connect.

5.3 Console Won't Open via Pure HTTP (device identity required)

If you open the console at http://<lan-ip>:18789/ on LAN, the browser may be in a non-secure context, causing WebCrypto to be restricted, thus unable to generate device identity, resulting in device identity required / connect failed.[^gateway_troubleshooting]

Priority fix route:

  • Open locally: http://127.0.0.1:18789/

  • For remote scenarios, use Tailscale Serve to provide HTTPS

  • If HTTP must be used, enable gateway.controlUi.allowInsecureAuth: true and use the gateway token (token mode only, not device identity/pairing)[^gateway_troubleshooting]

6. Multi-Instance and "Rescue Bot" Mode

Only try this if needed.

Usually one host running one gateway is sufficient; only when redundancy or strong isolation is needed (e.g., rescue bot) should multiple gateway instances be considered.

The core principle for multi-instance is "complete isolation + no conflicts":

  • Different gateway.port

  • Different OPENCLAW_CONFIG_PATH

  • Different OPENCLAW_STATE_DIR

  • Different workspaces (agents.defaults.workspace)

In the dev config file, you can quickly start a fully isolated dev instance without affecting the main environment:

xxxxxxxxxx
openclaw --dev setup
openclaw --dev gateway --allow-unconfigured
openclaw --dev status
openclaw --dev health

7. Troubleshooting Sequence, Usually Can Locate

7.1 Check Status First

Execute in order:[^gateway_troubleshooting]

xxxxxxxxxx
openclaw status
openclaw status --all
openclaw status --deep

Common supplementary commands:

xxxxxxxxxx
openclaw gateway probe
openclaw channels status --probe
openclaw gateway status
openclaw logs --follow
openclaw doctor

7.2 Gateway Won't Start: Configuration Validation Failed

OpenClaw configuration is strict schema validation: unknown keys, type errors, or invalid values may cause the gateway to refuse to start.

When validation fails, usually only diagnostic commands are available (e.g., openclaw doctor / logs / health / status). Recommended to directly:

xxxxxxxxxx
openclaw doctor

7.3 Common Phenomenon: Service Installed But Not Actually Running

If you use systemd/launchd/schtasks to install the gateway as a service, showing "loaded/installed" doesn't equal the process running. Priority check:[^gateway_troubleshooting]

openclaw gateway status
openclaw logs --follow
OpenClaw WebChat Interaction
OpenClaw Plugin Function Introduction

COMPANY

  • About us
  • Team Style
  • Blog

LEARNING & EXPLORATION

  • Tutorials
  • Edge AI hardware
  • Educational robots
  • Embedded intelligent hardware

WHERE TO BUY

  • Yahboom Online Store
  • Amazon
  • Alibaba
  • AliExpress
  • Mercado

TECHNOLOGY SUPPORT

  • Email: support@yahboom.com

BE A DISTRIBUTOR

  • Email: sales@yahboom.com
QR Code

Copyright © 2017-2026 Yahboom. All Rights Reserved.

EN/中文