Connect Agent Tools

WorkBuddy

WorkBuddy is a full-scene desktop AI agent from Tencent. It integrates with QQ / WeCom ecosystems, supports local computer control and multi-model switching, and offers commercial service via Token quota plans for both individuals and teams. Through custom models (OpenAI-compatible protocol), you can seamlessly connect models served by AutoRouter. This guide uses gpt-5-nano as an example.

📦 Prerequisites

What you'll need

  • WorkBuddy installed (macOS / Windows)
  • An AutoRouter API key (generated in the console)
  • A model ID exactly matching one exposed by your AutoRouter console (e.g. gpt-5-nano, claude-sonnet-4-6)

🚀 Step 1: Download and install WorkBuddy

  1. Visit the WorkBuddy website: https://www.workbuddy.cn
  2. Download the installer for your platform
    • On Mac, download the macOS build
    • On Windows, download the Windows build
  3. Complete the installation and launch WorkBuddy

🔑 Step 2: Get an API Key

  1. Open the AutoRouter API Keys page and click Create API Key. See Quick Start for details.
  2. After creation, copy and store the API Key securely — you will need it in the next steps.

Create API Key

⚙️ Step 3: Configure a custom model in WorkBuddy

  1. Launch WorkBuddy, click your account in the bottom-left corner, then choose Settings.

Open Settings

  1. In the left navigation, select Model. Under Custom Models, click Add Model.

Add Model

  1. Fill in the following and click Save:

    1. For Provider, choose Custom:

Select custom provider

  1. Fill in these fields:

    • Endpoint URL: https://api.autorouter.top/v1/chat/completions
    • API Key: your AutoRouter API key
    • Model name: gpt-5-nano (or any model ID available in your AutoRouter console)
    • Advanced settings (optional): recommended — enable Tool calling, Image input, and Thinking mode

Fill model info

✅ Step 4: Verify

After saving, pick the newly added gpt-5-nano model in WorkBuddy’s model selector and send a test message. A normal response means the setup succeeded.

Verify connection

❓ Troubleshooting

IssueFix
Connection failed / invalid API keyConfirm the endpoint is https://api.autorouter.top/v1/chat/completions and the API key is correct
Model not foundConfirm the model name matches your AutoRouter console exactly
New model missing from the selectorConfirm the config was saved, then switch to it in the chat model dropdown
Wrong endpoint URLUse the full Chat Completions URL (including /v1/chat/completions), not just /v1
Tool calling / image input unavailableEnable the matching options under Advanced settings, and confirm the model supports those capabilities

TRAE

TRAE is an AI coding assistant with built-in models and custom model integration. It natively supports code generation, debugging, and full-stack development assistance. The official build, however, has limited model choices, queueing during peak hours, network restrictions, and higher costs — you cannot freely switch among Claude, GPT, Gemini, and other mainstream models. AutoRouter solves this by removing model lock-in, delivering near-instant responses without queues, supporting multiple models, local payment methods, and lower call costs, so TRAE can adapt to different models and development scenarios.

On this page

📦 Prerequisites🚀 Step 1: Download and install WorkBuddy🔑 Step 2: Get an API Key⚙️ Step 3: Configure a custom model in WorkBuddy✅ Step 4: Verify❓ Troubleshooting