Copied to Clipboard
Launch and Prepare the Sandbox
1. Double-click your OpenClawSandbox.wsb file.
2. Open the PowerShell terminal inside the sandbox and download Node.js (OpenClaw requires version 22+).
You can download it using the command below or through the browser: https://nodejs.org/en/download
Invoke-WebRequest-Uri"https://nodejs.org/dist/v24.15.0/node-v24.15.0-x64.msi"-OutFile"node.msi"
3. Install it manually from the downloaded .msi file or by using the following command:
Start-Processmsiexec.exe-Wait-ArgumentList"/i node.msi /qn"
This command runs the Windows Installer (msiexec) to install the node.msi package silently (/qn) and waits for the process to finish.
4. Set environment path:
$env:Path=[System.Environment]::GetEnvironmentVariable("Path","Machine")+";"+[System.Environment]::GetEnvironmentVariable("Path","User")
This command refreshes the current PowerShell session’s PATH variable so newly installed programs (like Node.js) are immediately available.
PATH allows Windows to find installed programs like Node.js and npm from any terminal window.
5. Allow PowerShell to run locally created scripts for this session only (e.g., npm scripts):
Set-ExecutionPolicy-ExecutionPolicyRemoteSigned-ScopeProcess
This command lets PowerShell run scripts (like npm) just for this session, without permanently changing your system settings.
6. Install OpenClaw
Install OpenClaw globally using npm (Node.js package manager)
npminstall-gopenclaw@latest
This step may take a few minutes. If nothing seems to happen, that’s normal—Node.js installation runs silently in the background.
If successful, you should see a version number when running:
openclaw--version
7. Run OpenClaw
Run the OpenClaw onboarding command:
openclawonboard
The OpenClaw onboarding step may also take some time depending on network and system performance. You can monitor progress in Task Manager. Open Task Manager (Ctrl + Shift + Esc) inside the sandbox and look for the Node.js runtime.
After running the onboarding command, you should see a setup wizard in the terminal where you can configure your model and tools.
For the first time select Setup mode: QuickStart
Rest of the Onboarding is straightforward. If you’re unsure what to select, you can choose skip for now and configure it later.
OpenClaw operating in isolation: A look inside the Windows Sandbox environment:
OpenClaw operating in isolation: A look inside the Windows Sandbox environment.
Troubleshooting
Persistence
Everything will be deleted when you close the Sandbox window. If you want to keep your OpenClaw configuration, copy the .openclaw folder from the sandbox user directory to your host machine before closing.
Resource Usage
OpenClaw can be resource-intensive. If the sandbox feels slow, increase <MemoryInMB> in your .wsb file to 8192 (8 GB).
Cancel a running command
To cancel any running command, press Ctrl + C.
npm is not recognized
If you see an error like this:
npm:Theterm'npm'isnotrecognizedasthenameofacmdlet,function,scriptfile,oroperableprogram.Checkthespellingofthename,orifapathwasincluded,verifythatthepathiscorrectandtryagain.Atline:1char:1+npminstall-gopenclaw@latest+~~~+CategoryInfo:ObjectNotFound:(npm:String)[],CommandNotFoundException+FullyQualifiedErrorId:CommandNotFoundException
This usually means that Node.js is not available in your environment path.
Solution:
- Make sure Node.js was installed successfully
- Re-run the PATH setup step
- Restart the PowerShell session inside the sandbox if needed
PowerShell cannot run scripts
If you see an error like this:
npm:FileC:\ProgramFiles\nodejs\npm.ps1cannotbeloadedbecauserunningscriptsisdisabledonthissystem.Formoreinformation,seeabout_Execution_Policiesathttps:/go.microsoft.com/fwlink/?LinkID=135170.Atline:1char:1+npminstall-gopenclaw@latest+~~~+CategoryInfo:SecurityError:(:)[],PSSecurityException+FullyQualifiedErrorId:UnauthorizedAccess
You need to allow PowerShell to run locally created scripts for the current session:
Set-ExecutionPolicy-ExecutionPolicyRemoteSigned-ScopeProcess
Copy Paste issues in Sandbox
When copying commands from your host machine into the Sandbox, pasting may not always work reliably.
Open this article directly inside the Sandbox browser and copy commands from there instead.
Gateway CIAO issue (probing cancelled)
[openclaw] Unhandled promise rejection: CIAO PROBING CANCELLED
Gateway should run in another Command Prompt window. If you don’t see it or see the error above, open a new PowerShell window and check if the OpenClaw gateway is running:
openclaw gateway status
If you see something similar:
...Runtime:stopped(stateReady,lastrun1,lastruntime4/26/20268:55:31AM,TaskLastRunResult=1;treatingasnotrunning.)Connectivityprobe:failedProbetarget:ws://127.0.0.1:18789connectECONNREFUSED127.0.0.1:18789Capability:unknownServiceisloadedbutnotrunning(likelyexitedimmediately)....
run:
openclawdoctor--fix
If this does not help and the gateway still does not run in the opened Command Prompt window, you will need to reinstall OpenClaw to a different version (the issue occurred in version 2026年4月24日):
npminstall-gopenclaw@2026年4月25日
On Windows, if another program (like Edge or System services) is already using Port 5353, or if your network interface is virtualized (like in Windows Sandbox), the ciao library's attempt to "probe" the network is cancelled by the OS. In version 2026年4月24日, instead of ignoring the failed network probe, the whole app crashes and closes your CMD window.
Not all GitHub Copilot models work
Some GitHub Copilot models did not work reliably. Copilot endpoints rejected the requests and responded with the following message:
runerror:LLMrequestfailed:providerrejectedtherequestschemaortoolpayload.
I tested the following models with a Copilot Pro subscription and they worked properly:
"agents":{"defaults":{"workspace":"C:\\Users\\WDAGUtilityAccount\\.openclaw\\workspace","models":{"github-copilot/gemini-2.5-pro":{},"github-copilot/grok-code-fast-1":{},"github-copilot/gemini-3.1-pro-preview":{},},"model":{"primary":"github-copilot/grok-code-fast-1"}}},
This snippet is part of the openclaw.json file located at C:\Users\WDAGUtilityAccount\.openclaw\openclaw.json in the Windows Sandbox environment.
After editing the config, stop OpenClaw (press Ctrl+C twice) and run it again using openclaw chat.
Summary
The key idea is that OpenClaw’s risk depends on the permissions and tools you enable, not the model itself. Windows Sandbox helps contain system-level risk by isolating execution from your host environment, making it a practical way to safely experiment with AI agents.
From here, you can explore OpenClaw in a controlled environment, test configurations and build tools with reduced risk to your main system. Keep in mind that while the sandbox protects your host machine, it does not make the agent inherently safe — any data or external services you explicitly provide to it are still accessible within the sandbox and can be misused depending on configuration.