OpenClaw

The AI that actually does things

OpenClaw brings your AI agents directly into your daily conversations on WhatsApp, Telegram, or Matrix. OpenClaw is a self-hosted solution that lets you interact with your personal assistants from anywhere, keeping infrastructure under your control.

This guide will walk you through the setup process and show you how to combine OpenClaw with Cortecs.

Before you begin: Make sure you have generated your Cortecs API key. If not, check out our QuickStart guide.

1. Install OpenClaw

Run the following command in your terminal to install OpenClaw

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

For additional installation options, refer to the OpenClaw documentation.

2. Complete Onboarding

After the installation completes, the onboarding process starts automatically. If this is not the case, run the following command

openclaw onboard --install-daemon

During onboarding configure the system to your liking. Answer the following options when prompted:

1. Model/auth provider: Custom Provider

2. API Base URL: https://api.cortecs.ai/v1

3. How do you want to provide this API key: Paste API key now

4. API Key: Paste your generated Cortecs API key

5. Endpoint compatibility: OpenAI Responses-compatible

6. Model ID: Copy the exact ID of your preferred model from the model catalog.

7. Endpoint ID: cortecs

8. ... Proceed with the remainder of the configuration to your liking

The Cortecs Responses API is recommended for OpenClaw agent workflows. Choose OpenAI-compatible only if a model or workflow requires Chat Completions.

Your default model is now set up, and you are able to chat with your model using the dashboard provided by OpenClaw.

Set up your connected communication gateway by running the following command in your terminal:

openclaw tui

3. Adding Multiple Models (Optional)

You can configure multiple models using a single API key. The various models are listed in our catalog.

Adding new models to OpenClaw is very straightforward. The simplest approach is to prompt your default model to add new ones. By pasting the following prompt into the chat, OpenClaw is automatically able to add your model. Adapt the prompt to use a model of your liking, or add multiple if desired.

Add the model <MODEL_ID> from provider cortecs to my config.
Add it to the models and the agents sections in the config.
Then restart the gateway.

Now you are able to switch to the new model/s using the command

/model <MODEL_ID>

For faster switching, you can prompt OpenClaw to assign aliases to the models. Then you can switch using your defined alias with the following commands, for example:

/model oss
/model opus
/model mini