This is a submission for the OpenClaw Writing Challenge
Intro
In this article, I want to guide you on how to make OpenClaw "just work" on Windows. I used Windows as my OS, but I think this guide can be easily followed on Linux as well.
Chances are, I don't have to explain the title. If you (like me) are trying to participate in the OpenClaw challenge or just trying OpenClaw for the first time, you certainly found that making OpenClaw "just work" on your machine is not an easy task.
I think there is room to improve in this area for the OpenClaw team, or maybe that's the point of this challenge after all? hehe You tell me.
After that fresh introduction, I will try to be direct and simple in this guide. I think I need to save you some time since you probably already wasted some, trying to set up OpenClaw...
Table Of Contents
- Versions
- Installation
- Initial Setup
- First chat with the Agent
- Congrats, You made it work
- Extra: Things to consider
Versions
For reference and reproducibility:
- Operating System ->
Windows 11 - Node Version ->
Node.js v24.11.0 - Openclaw version ->
openclaw 2026.4.22
Installation
- Install Node if you haven't installed it.
- Install OpenClaw with:
>> npm install -g openclaw@2026.4.22
added 498 packages in 51s
- Check it is installed with:
>> openclaw -v
OpenClaw 2026.4.22 (00bd2cf)
Note: I use a specific version for reproducibility. The team is making releases every day and something might get broken if you try a different version after the publication date of this post. I did experience issues with version 2026.4.21, so if you are skilled enough, feel free to play with the latest version; but if you are in the mode of "let's make this thing just work," stick to the guide.
Initial Setup
To set up OpenClaw, we need to set a model and model provider; this is necessary for the agent to work. As the provider, we will use Google AI Studio. Let's go to Google AI Studio and look for the section to generate an API KEY. It is relatively easy to do.
Once we have it, we save it in a secure place. It's all we need beforehand; we can proceed with OpenClaw. Let's start with the command:
openclaw onboard
Now, on my computer, I had to wait about 4 minutes for the command to show the CLI of OpenClaw. Haha, this is just a warning in case you run the command and see it hangs. Just trust the process and wait for it. It seems it needs to install something else before actually starting. After some minutes you should see something like:
So, you are about to set up. Here are the default answers to use to finish the setup quickly:
| Question | Option to choose |
|---|---|
| I understand this is personal-by-default and shared/multi-user use requires lock-down. Continue? | yes |
| Setup Mode | QuickStart |
| Model/auth provider | |
| Enter Gemini API key | Enter the API KEY you got from Google AI Studio |
| Model | google/gemini-2.5-flash |
| Select channel (QuickStart) | Skip for Now |
| Search provider | Skip for Now |
| Configure skills now? (recommended) | No |
| Enable hooks? | Skip for now |
| How do you want to hatch your bot? | Do this later |
Ok, the setup is ready. Let's confirm by looking at the default model, run:
openclaw models
You should see something like:
It is important that the default model is the one we set during onboard.
If everything is as expected, we can proceed to play with the agent.
First chat with the Agent
In one terminal run :
openclaw gateway
This is like "run the server" to start playing with an agent.
In another terminal run:
openclaw tui
This is like "open a client" to chat with the agent.
Once is ready type something, like "Hello". If you are lucky enough, you should receive a response:
And there you go. You can start playing and interacting with OpenClaw.
Congrats, You made it work !
So now you can chat with the agent. The agent will guide you on how to define the behavior, the personality, and the tasks to do. You can continue exploring on your own from this point.
Hopefully, this tutorial was useful and saved you some time :)
Extra : Things to consider
- You created an API KEY in Google AI Studio, make sure you set a budget, (let's say of 1 dollar for example), so you dont have surprises after some time using the agent. Although it is said free tier of this API KEY from google is good, it's better to be safe on that.
- If you need to keep working with OpenClaw on windows, or OpenClaw in general I would advice to be patient, it's likely you'll find things don't work in the way it should. I came up with this guide with a mix of trial-and-error, Geminis' help and testing with help from OpenClaw CLI.
- I tried to make this guide easy and practical, I consider I am not doing anything risky in the proposed setup, but feel free to comment if I am missing something or something else should be considered for starters.
- For some reason I couldn't finish the "npm openclaw" processes with
CTRL+Cas usual. I had to use the following command in PowerShell to kill the processes when neededtaskkill /F /IM node.exe /TIt is not best, but it is what it works by now.
This article was originally published by DEV Community and written by Angeluz-07.
Read original article on DEV Community

