# WorkBuddy: install, configure and troubleshoot LYRouter access Source: https://platform.lyrouter.com/ai_gateway/docs/workbuddy/en Last updated: 2026-10-14 WorkBuddy can connect to LYRouter as a custom model service. This page starts with the installation prerequisites, then shows how to configure the tool and make your first call. Already installed? Go straight to [Configure LYRouter](#configure-lyrouter). ## Prerequisites This page covers the WorkBuddy desktop app. Prepare an account for the app, network access and permission to install software locally, then follow the instructions for your operating system. **Choose your operating system** Windows: #### 1. Check the system and architecture WorkBuddy officially requires Windows 10 1809+ / Windows 11, a 64-bit system (x64 / ARM64), at least 4 GB of RAM and 500 MB of free disk space. Check your system in PowerShell: ```powershell Get-CimInstance Win32_OperatingSystem | Select-Object Caption, Version, OSArchitecture ``` #### 2. Prepare installation and sign-in Choose the Windows installer from the [official download](https://www.workbuddy.ai/), and prepare write permission to the installation directory and an account to sign in with. For detailed requirements, see the [Windows installation guide](https://www.workbuddy.ai/docs/workbuddy/From-Beginner-to-Expert-Guide/Installation-Win-Guide). Linux: #### 1. Check desktop app support The [official desktop download page](https://www.workbuddy.ai/) currently lists installers for Windows and macOS. This page does not provide installation steps for a Linux desktop version. #### 2. Choose an environment you can use Continue this guide on Windows or macOS. To connect to LYRouter locally on Linux, see [Claude Code](https://platform.lyrouter.com/ai_gateway/docs/claude-code/en), [Codex CLI](https://platform.lyrouter.com/ai_gateway/docs/codex/en) or [OpenCode](https://platform.lyrouter.com/ai_gateway/docs/opencode/en); their Linux prerequisites are in the Linux tab of each page. macOS: #### 1. Check the system and processor Check your macOS version and processor in Terminal, and confirm the system version requirement in the [official installation instructions](https://www.workbuddy.ai/docs/workbuddy/From-Beginner-to-Expert-Guide/Installation-Mac-Guide): ```bash sw_vers -productVersion uname -m ``` #### 2. Prepare installation and sign-in From the [official website](https://www.workbuddy.ai/), choose the Mac ARM64 (Apple Silicon) or Mac x64 (Intel) installer, make sure the Applications folder is writable, and prepare an account for the app and network access. To connect to LYRouter you also need an enabled API key and a model available in the current workspace. Replace `MODEL_ID` in the examples with an actual system model identifier. Your tool account and your LYRouter account are two separate identities. ## Install the app 1. Open the [WorkBuddy website](https://www.workbuddy.ai/) and choose the macOS or Windows installer. 2. On macOS, open the DMG and drag the app into Applications; on Windows, run the installer and complete the wizard. 3. Start the app, sign in, and note the version shown in the app information. 4. Grant access to local files and other system permissions only as your tasks actually require. ## Configure LYRouter In Settings → Model, add a Custom model: set URL to `https://api.lyrouter.com/v1`, API Key to your LYRouter API key, and the model name to a system model identifier. The default standard protocol mode completes the Chat Completions path for you. If you explicitly turn on Custom Protocol, the app requests the URL you entered as is. In that case, use the full `https://api.lyrouter.com/v1/chat/completions`, and do not treat the Base URL as the full endpoint. After saving, select the custom model in the conversation. ## Verify your first call Start the app, explicitly select the model you just configured, and send a minimal task such as "Reply OK". Then check the generation endpoint, status and actual model in LYRouter's [request logs](https://platform.lyrouter.com/ai_gateway/docs/logs/en). A successful connection test does not mean that full generation or tool calling works. ## Everyday use and troubleshooting ### The app does not start after installation. How do I check? **Answer:** Check the operating system, processor architecture and installation permission against "Prerequisites" on this page, then check the installation against the installation guide for your system. Use the official installer; the official resources linked on this page define the specific system requirements. ### What is the difference between the Base URL and the Custom Protocol URL? **Answer:** The default standard protocol mode uses `https://api.lyrouter.com/v1`, and the app completes the Chat Completions path. With Custom Protocol on, enter the full endpoint `https://api.lyrouter.com/v1/chat/completions`. Do not use the root address or the Base URL as the full request endpoint. ### What should I check before switching models? **Answer:** Make sure the new model is enabled in the current workspace, has at least one valid service source, and supports the protocol and tool capabilities the app needs. Use the system model identifier, not the display name. ### Why does my configuration stop working after an app update? **Answer:** First check the current app version and which configuration location it actually reads, then check the provider, address, key and model against "Configure LYRouter" on this page. The official resources linked on this page define the configuration requirements of each version. ### A request returns 401 / 403. What should I check first? **Answer:** Make sure you entered an enabled LYRouter API key, and check the model sources and access policies of the workspace the key belongs to. Use the specific error and the logs to find what rejected the request; see [401 / 403: authentication and access](https://platform.lyrouter.com/ai_gateway/docs/auth-errors/en). ### A request returns 429. Does retrying repeatedly help? **Answer:** First find out whether a platform limit or an exhausted upstream quota caused it, then adjust concurrency, call frequency or resource configuration. Retry with bounded backoff instead of retrying immediately and repeatedly; see [429: rate limits and quotas](https://platform.lyrouter.com/ai_gateway/docs/rate-errors/en). ### The app replies, but I cannot find the request in the LYRouter logs. What should I do? **Answer:** Make sure the conversation uses the custom model you just configured, not a built-in model or Auto mode, then send a minimal generation request. Search the [request logs](https://platform.lyrouter.com/ai_gateway/docs/logs/en) in the correct workspace by time and key; a request that just finished may need a refresh a little later. ## Official resources The requirements and installation methods below come from the tool's official documentation. For later versions, the official instructions take precedence. - [Windows installation guide](https://www.workbuddy.ai/docs/workbuddy/From-Beginner-to-Expert-Guide/Installation-Win-Guide) - [macOS installation guide](https://www.workbuddy.ai/docs/workbuddy/From-Beginner-to-Expert-Guide/Installation-Mac-Guide) - [Custom models and protocols](https://www.workbuddy.ai/docs/workbuddy/From-Beginner-to-Expert-Guide/Function-Description/Model)