QClaw is a localized AI Agent assistant built by Tencent PC Manager based on the OpenClaw open-source ecosystem, and is affectionately known as "Crayfish AI". It requires no complex configuration, is ready to use in three steps, and comes with built-in security protection. It supports direct WeChat binding. No matter where you are, you can send commands via WeChat to have your computer automatically complete tasks such as report processing, file transfer, and document editing. All data remains securely on the local device, making it suitable for use in various scenarios including office work, content creation, and development.
This document describes how to configure and use the Tencent Cloud Large Language Model Token Plan Enterprise Edition in QClaw.
Prerequisites
Before you start the configuration, ensure that you have completed the following preparations:
Steps
Step 1: Starting QClaw and Configuring a Custom Model
1. Start QClaw.
2. Select the model configuration at the bottom of the dialog box, and click "Custom Model".
3. On the Model API tab, click Custom Configuration.
Step 2: Configuring the API Address, API Protocol Type, API Key, and Model
After configuring the following items, click confirm and wait for the configuration to take effect.
|
Endpoint | Singapore: https://tokenhub-intl.tencentcloudmaas.com/plan/v3 Guangzhou: https://tokenhub.tencentcloudmaas.com/plan/v3 |
API Protocol Type | Select "OpenAI-compatible protocol". |
API Key | Enter the API Key you obtained from the Tencent Cloud console. For details, see Obtain the API Key. |
Model Name | |
Note:
When configuring the model name, ensure that you enter the Model ID value from your plan.
Each model requires you to individually configure its interface address, API Key, and model name, and then save the configuration.
Step 3: Switching to a Custom Model Conversation
Return to the chat page, switch to the custom model configured in the previous steps, and you can start a conversation.