CodeNomad vs herdr
Desktop cockpit for OpenCode: multi-instance sessions, git worktrees, remote browser access, voice input and a command palette — a workspace for living in AI coding sessions. — versus — Agent multiplexer for your terminal: every Claude Code/Codex session in real panes — blocked/working/done at a glance, detach and reattach over SSH, plus a socket API agents drive themselves.
Both are cockpits for living in AI coding sessions: CodeNomad is a desktop app going deep on OpenCode (worktrees, voice, palette); herdr is a terminal-native multiplexer for any agent CLI, with detach/SSH as the killer habit.
| CodeNomad | herdr | |
|---|---|---|
| Stars | 2.4k | 21k |
| Forks | 164 | 1.4k |
| Language | TypeScript | Rust |
| License | MIT | Apache-2.0 |
| Last activity | 6 days ago | yesterday |
| Topics | coding | coding, orchestration |
| Curated connections | 6 | 3 |
CodeNomad — the curator's take
For developers who run OpenCode all day and have outgrown the terminal: parallel sessions across projects in one window, git-worktree awareness for agent branches, a password-protected server mode for driving sessions from any browser, and quality-of-life extras (voice input, SideCars for embedding local web tools). NOT useful if OpenCode isn't your driver — it's a cockpit for that engine specifically, not a general agent UI; and it's young (2k stars), so expect rough edges alongside the fast release cadence.
herdr — the curator's take
tmux, rebuilt for the agent era: real terminal views (not wrapped reinterpretations), sessions that survive restarts and reattach over SSH, prefix keys AND mouse both first-class. The differentiator is the socket API — agents can spawn panes, read each other's output and wait on each other, which turns the multiplexer itself into coordination infrastructure, and the plugin marketplace suggests real ecosystem ambition. NOT an orchestrator: no task queues, no verification gates, no workflow graphs — it multiplexes and observes, you still decide. If you've already shaped your life around tmux, the marginal win is the agent-state awareness; weigh the switching cost honestly.