by alvinunreal
Desktop pets for AI coding agents. Install pets, connect Claude Code via MCP, and see live coding status on your desktop.
# Add to your Claude Code skills
git clone https://github.com/alvinunreal/openpetsOpenPets is the original cross-platform desktop pet system for AI coding agents.
Official site: https://openpets.dev
Integration guides: https://openpets.dev/integrations
https://github.com/user-attachments/assets/fbad0d58-8040-4ebb-a26b-73fa497a4ceb
Install the desktop app, then connect your coding agent.
Download the latest app from OpenPets Releases:
OpenPets-*-arm64.dmg or OpenPets-*-arm64.zipOpenPets-*-x64.dmg or OpenPets-*-x64.zipOpenPets-Setup-*-x64.exeOpenPets-*-x86_64.AppImage or OpenPets-*-amd64.debInstall or unzip it, then launch OpenPets. You should see the desktop pet and the OpenPets tray/menu-bar icon.
Current builds are unsigned. macOS or Windows may show a security warning the first time you open the app.
No comments yet. Be the first to share your thoughts!
If macOS says the app is damaged or should be moved to Trash, remove the quarantine flag and open it again:
xattr -dr com.apple.quarantine /Applications/OpenPets.app
open /Applications/OpenPets.app
See INSTALL.md for platform notes and troubleshooting.
Use the companion integration for your agent when one exists:
For Cursor, VS Code, Windsurf, Zed, or any other MCP-capable agent, configure the OpenPets MCP server directly. See MCP integration for copy-paste JSON and commands, or use the full AI assistant integration guides.
The OpenPets MCP server lets agents control the desktop pet over the Model Context Protocol.
{
"mcpServers": {
"openpets": {
"type": "stdio",
"command": "bunx",
"args": ["@open-pets/mcp"]
}
}
}
Once connected, an agent can use OpenPets tools to start the desktop app, check health, set pet states, show short speech bubbles, and release its session.
Full setup guides live in docs/ai-assistants/ and on https://openpets.dev/integrations.
Add this to ~/.cursor/mcp.json for global setup, or .cursor/mcp.json inside a project:
{
"mcpServers": {
"openpets": {
"type": "stdio",
"command": "bunx",
"args": ["@open-pets/mcp"]
}
}
}
Restart Cursor after changing MCP config.
Add this to ~/.config/zed/settings.json:
{
"context_servers": {
"openpets": {
"command": "bunx",
"args": ["@open-pets/mcp"]
}
}
}
Restart Zed after changing settings. See docs/ai-assistants/zed.md for rules and troubleshooting.
Add this to .vscode/mcp.json for a workspace setup:
{
"servers": {
"openpets": {
"type": "stdio",
"command": "bunx",
"args": ["@open-pets/mcp"]
}
}
}
Or add it to your user profile from the command line:
code --add-mcp '{"name":"openpets","command":"bunx","args":["@open-pets/mcp"]}'
VS Code uses servers as the root key, not mcpServers.
Add this to ~/.codeium/windsurf/mcp_config.json on macOS/Linux, or %USERPROFILE%\.codeium\windsurf\mcp_config.json on Windows:
{
"mcpServers": {
"openpets": {
"command": "bunx",
"args": ["@open-pets/mcp"]
}
}
}
Fully quit and reopen Windsurf after changing MCP config.
openpets_health - check whether the desktop app is reachable.openpets_start - launch OpenPets and acquire an agent session.openpets_say - show a short speech bubble and optional pet state.openpets_set_state - update the pet state without speech.openpets_release - release the agent session.Supported states include thinking, working, editing, running, testing, waiting, success, and error.
The MCP server talks to the local OpenPets desktop app through the same local IPC client used by other integrations. Speech is intentionally short and validated before it appears on screen.