xinnaider

Orbit — Development skill for Claude Code

Development community

Desktop app for running multiple Claude Code agents simultaneously.

How to install Orbit

This entry records only its repository, not the path inside it, so there is no exact command to give. Open xinnaider/orbit and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What Orbit does

Desktop app for running multiple Claude Code agents simultaneously.

Alternatives in Development

Happy Coder — by GrocerPublishAgent - Spawn and control multiple Claude Codes in parallel from your phone or desktop 15.7k ★
Screenshot — Capture desktop, app windows, or pixel regions across OS platforms 14.6k ★
Claude Desktop Debian — Unofficial Claude desktop app for Debian/Linux 2.5k ★

README

Orbit

**Desktop app for running multiple AI coding agents simultaneously.** **Supports [Claude Code](https://github.com/anthropics/claude-code), [Codex](https://github.com/openai/codex), and [OpenCode](https://github.com/opencode-ai/opencode).**

[![Build](https://img.shields.io/github/actions/workflow/status/xinnaider/orbit/build.yml?branch=master)](https://github.com/xinnaider/orbit/actions) [![License: MIT](https://img.shields.io/badge/license-MIT-yellow.svg)](LICENSE) [![Platform: Windows](https://img.shields.io/badge/platform-Windows-blue.svg)](#windows-10-1903) [![Platform: macOS](https://img.shields.io/badge/platform-macOS-lightgrey.svg)](#macos-13) [![Platform: Linux](https://img.shields.io/badge/platform-Linux-orange.svg)](#linux-ubuntu-2204--debian--kde--other-distros)

[orbit.jfernando.dev](https://orbit.jfernando.dev)

![Orbit demo](media/demo.gif)

Features

Multi-provider — run Claude Code, Codex, and OpenCode sessions side by side
Split panes — view multiple sessions simultaneously with drag-and-drop layout
SSH remote sessions — run sessions on remote servers via SSH with any provider, key-based auth
Web access — open the Orbit dashboard from a phone, tablet, or browser on your local network
Git worktree — isolate each session in its own branch, works locally and via SSH
MCP orchestrator — built-in MCP server lets any agent spawn other agents across providers
Sub-agents monitor — track spawned sub-agents and inspect their full conversations
Real-time feed — streaming output with thinking blocks, tool calls, diffs, and markdown
Persistent history — SQLite-backed sessions survive app restarts; conversations resume automatically
Cost tracking — per-session token usage, context window %, rate limit bars, and estimated cost in USD
/model & /effort — switch models and pro