RizRiyz/luvus

Mission control for your AI agents

What it solves

Luvus acts as a "mission control" for AI coding agents, providing a unified terminal-based interface to manage multiple agents, persistent workspaces, and development tools. It eliminates the need to juggle multiple terminal windows and manually track the state of various AI agents while coding.

How it works

Luvus uses a background server to maintain persistent sessions, layouts, and terminal states. It provides a TUI (Terminal User Interface) that can detect supported AI agents automatically and track their status (working, idle, blocked). It implements a Universal Harness Protocol (UHP 1.0) to allow developers to build orchestrators and harnesses with versioned method registries and event streams.

Who it’s for

Developers who use multiple AI coding agents (such as Claude Code, GitHub Copilot CLI, or Devin) and need a centralized environment to orchestrate their workflows, manage Git repositories, and maintain persistent remote or local sessions.

Highlights

  • Agent Awareness: Automatically detects agents and tracks tokens, cost, context use, and live status.
  • Persistent Workspaces: Keeps tabs, panes, and terminal states alive in the background.
  • Orchestration Tools: Supports creating worktrees, scheduling recurring work, and running quality gates.
  • Git Integration: Built-in dashboard for viewing branches, commits, pull requests, and repository activity.
  • Remote Access: Ability to attach via SSH and switch between remote machine profiles.
  • Extensible Interface: Supports custom modules, widgets, and community themes.

Related

  • Project
  • Project
  • Project
  • Project
  • Project