1. OpenClaw Deployment

=============================【NOTE】================================

This section provides the complete installation and deployment tutorial for OpenClaw, which involves many steps. If you want to quickly use OpenClaw, please

follow the tutorial in the first section of this chapter 【01.OpenClaw Quick Start】

====================================================================

This chapter will cover two parts:

• OpenClaw Installation
• Configure Models (OpenRouter / Bailian / Ollama)

1.1 OpenClaw Installation

OpenClaw Official Website: https://openclaw.ai/

Open Source Project Address: https://github.com/openclaw/openclaw

1.1.1 Install OpenClaw

1.1.2 Use QuickStart Installation

We use the installation script provided by OpenClaw official

curl -fsSL https://openclaw.ai/install.sh | bash

During this process, the installation script will automatically detect missing environments and assist us with one-click installation

During installation, use the keyboard arrow keys to select options, space bar to select/deselect, and Enter key to confirm and configure

Here we use the QuickStart option to quickly complete OpenClaw installation, we can leave specific configurations for later

If you haven't applied for any API Key, we can choose Skip here, and configure later

For models here we choose to keep the default (configure later)

Select Channel here is mainly used for communication with third-party APPs, we still skip for now

Search provider is the API provider for search services, we choose to skip

Configure "Skills" skills, we choose not to configure for now (select no)

Configure Hooks hooks, we press space bar to select "Skip for now", then press Enter key to confirm

Wait for installation to complete.

After installation is complete, we copy this address for backup (in subsequent tutorials, the token changed because we manually configured the Gateway later, so this address actually doesn't need to be recorded, it will change later)

You need to add the OpenClaw installation location to environment variables, otherwise you may not find the openclaw command in the terminal,

xxxxxxxxxx
echo 'export PATH="$(npm prefix -g)/bin:$PATH"' >> ~/.bashrc
source ~/.bashrc

1.1.3 Open OpenClaw Control UI on PC (Windows)

1. Modify OpenClaw's configuration file to allow other devices within the intranet to access OpenClaw

xxxxxxxxxx
openclaw config

Here we select according to the image below (arrow keys to select, Enter to confirm)

Except for the Token which can be different from our image, everything else should be the same. The key point is the Gateway bind mode item, we need to set it to LAN to allow other devices within our local network to access our OpenClaw

Finally we select Continue to confirm, press Enter, and the configuration is complete!

After completing the configuration, we first start OpenClaw's Gateway. We open a new terminal and enter in the terminal

xxxxxxxxxx
openclaw gateway

2. Get Access Token

The Token here is the one we just generated in the configuration. If you didn't save it, you can use

xxxxxxxxxx
openclaw dashboard

This command to display the token once, or you can find the ~/.openclaw/openclaw.json file, your token will be configured in this file

3. On a PC computer within the same local network, configure the environment to connect to Jetson

We open the Cmd terminal on the computer (taking Windows computer as an example, Win+R keys to wake up the shortcut RUN tool, type cmd, then press Enter)

Enter in the console

xxxxxxxxxx
ssh -L 18789:127.0.0.1:18789 sunrise@<sunrise-ip-address>

Note, here needs to be replaced with your RDK board's actual IP address

After pressing Enter here, you need to enter the password (default is sunrise).

4. Access in Browser

We open the browser on the PC, enter the IP+token address in the address bar (the address we just output from openclaw dashboard, https://127.0.0.1:18789/#token=xxxxxxxxxxxxx). When this interface appears, it means the deployment is successful!

1.2 Configure Models (Must Read)

1.2.1 Why Configure Models

OpenClaw is an AI Agent gateway, which itself does not have the "intelligence" capability of large models. We need to configure large models to give OpenClaw the ability to think and understand

1.2.2 How to Configure Models

Here we take three representative models as examples, which are

1. OpenRouter (OpenClaw built-in service provider, accessible both domestically and internationally)
2. Alibaba Bailian Large Model Platform (not an OpenClaw service provider, requires manual configuration)
3. Ollama (local large model)

Before starting configuration, we need to start OpenClaw's Gateway first.

If you didn't exit the Gateway terminal after completing the deployment in the previous chapter, you can skip this step

We enter in the terminal

xxxxxxxxxx
openclaw gateway

1. OpenRouter (OpenClaw Built-in Service Provider)

Here you need to have completed the application for OpenRouter's API Key according to the previous tutorial (please refer to the previous tutorial 【Online Large Models/4.OpenRouter Large Model API Aggregation Platform】)

OpenRouter's API Key format is like sk-or-v1-b3exxxxxx4xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxcddf81d9

We’ll stick with the original onboard‑guided setup for configuration.

xxxxxxxxxx
openclaw onboard

Please select according to my illustrated options

Then enter the applied API-Key, press Enter to confirm,

In this next step, we need to select models. Limited by OpenRouter's traffic control policy, we recommend you maintain a balance of $11 or more in your OpenRouter account. For insufficient balance situations, OpenRouter may limit speed (this policy may be modified later, please refer to the latest actual situation). Here we can choose free models (model names ending with free), or choose a free dedicated model from OpenRouter openrouter/free (this is a route that will randomly select free models from those available on OpenRouter. This route will intelligently filter models that support the features required by your request)

At this time, there may be an option requiring API Key entry. We paste the API Key and press Enter to proceed to the next step

Afterwards, we reach other configuration items. We skip them here and choose Skip for all

At this point, it means we have completed the configuration

We can use the TUI function to quickly test

Enter command

xxxxxxxxxx
openclaw tui

After entering, directly type a sentence to greet openclaw (the Input part in the image is what we entered, the green box is the model we selected)

2. Bailian (Third-party Service Provider API Example)

Configuring third-party APIs requires editing Openclaw's configuration file (located at ~/.openclaw/openclaw.json). Here I recommend editing in the web page (Openclaw Control UI)

We open OpenClaw's configuration page in the browser and click these three buttons in sequence

The current existing content is as follows. We need to focus on the agents part

xxxxxxxxxx
{
  "meta": {
    "lastTouchedVersion": "2026.3.8",
    "lastTouchedAt": "2026-03-10T07:56:18.292Z"
  },
  "wizard": {
    "lastRunAt": "2026-03-10T07:56:18.270Z",
    "lastRunVersion": "2026.3.8",
    "lastRunCommand": "onboard",
    "lastRunMode": "local"
  },
  "auth": {
    "profiles": {
      "openrouter:default": {
        "provider": "openrouter",
        "mode": "api_key"
      }
    }
  },
  "agents": {
    "defaults": {
      "model": {
        "primary": "openrouter/openrouter/free"
      },
      "models": {
        "openrouter/auto": {
          "alias": "OpenRouter"
        },
        "openrouter/openrouter/free": {}
      },
      "workspace": "/root/.openclaw/workspace",
      "compaction": {
        "mode": "safeguard"
      },
      "maxConcurrent": 4,
      "subagents": {
        "maxConcurrent": 8
      }
    }
  },
  "tools": {
    "profile": "coding"
  },
  "messages": {
    "ackReactionScope": "group-mentions"
  },
  "commands": {
    "native": "auto",
    "nativeSkills": "auto",
    "restart": true,
    "ownerDisplay": "raw"
  },
  "session": {
    "dmScope": "per-channel-peer"
  },
  "gateway": {
    "port": 18789,
    "mode": "local",
    "bind": "lan",
    "controlUi": {
      "allowedOrigins": [
        "http://localhost:18789",
        "http://127.0.0.1:18789"
      ]
    },
    "auth": {
      "mode": "token",
      "token": "__OPENCLAW_REDACTED__"
    },
    "tailscale": {
      "mode": "off",
      "resetOnExit": false
    },
    "nodes": {
      "denyCommands": [
        "camera.snap",
        "camera.clip",
        "screen.record",
        "contacts.add",
        "calendar.add",
        "reminders.add",
        "sms.send"
      ]
    }
  }
}

We need to add a Models content (in the first level of JSON, meaning this newly added "models" is at the same level as "agents")

Note: You need to replace DASHSCOPE_API_KEY with your actual Bailian API Key, and change baseUrl to the OpenAI Compatible Endpoint matching your account. (Refer to the earlier section for the application procedure.)

For the models here, we take qwen3.5-plus and qwen3-coder-next as examples. If you want to support other models, please refer to this model list https://help.aliyun.com/zh/model-studio/models

xxxxxxxxxx
  "models": {
    "mode": "merge",
    "providers": {
      "bailian": {
        "baseUrl": "https://dashscope.aliyuncs.com/compatible-mode/v1",
        "apiKey": "DASHSCOPE_API_KEY",
        "api": "openai-completions",
        "models": [
          {
            "id": "qwen3.5-plus",
            "name": "qwen3.5-plus",
            "reasoning": false,
            "input": ["text", "image"],
            "contextWindow": 1000000,
            "maxTokens": 65536
          },
          {
            "id": "qwen3-coder-next",
            "name": "qwen3-coder-next",
            "reasoning": false,
            "input": ["text"],
            
 OpenClaw Quick Start
OpenClaw WhatsApp Plugin Application