Compare PK-Herdr

The agent multiplexer that lives in your terminal.

PK-Herdr gives coding agents the thing tmux gave terminal users: persistent real panes, detach and reattach, remote access, and a control surface. Then it adds agent state and an API the agents can use.

PK-Herdr combines

tmux persistence, agent awareness, no terminal replacement.

  • Runs inside your existing terminal
  • Owns persistent PTY sessions
  • Attaches locally, over SSH, or directly to one agent
  • Tracks blocked, working, done, and idle state
  • Exposes CLI and socket APIs agents can drive

The stack

Pick the center of gravity.

The question is not whether a tool can run a terminal. Most can. The question is whether it combines terminal-native persistence with agent state and agent-controlled automation.

CapabilityPK-Herdrtmux / Zellijcmux / WarpSoloConductor / Emdash / Superset
Runs inside your existing terminalyesyesno, terminal appno, desktop appno, app workspace
Persistent PTY session runtimeyesyessession/app restoremanaged processesembedded terminals
Detach, reattach, and SSH inyesyespartialnoremote projects
Direct attach to one agent terminalyesnononono
Semantic agent stateblocked / working / done / idlenoattention or native-agent statusprocess statusworkspace status
Agent-shaped APIread, send, wait, split, attachterminal scriptingapp APIsMCP for processesworkflow APIs
Git worktree and diff review flowpairs with itnopartialnoyes

How PK-Herdr differs

The intersection other tools miss.

PK-Herdr

Persistent terminal runtime, built for agents.

PK-Herdr keeps real terminal panes alive like a multiplexer, but treats agents as first-class runtime objects. You can scan state, jump to blocked work, attach directly to one agent, and let agents read, send, split, and wait through the CLI/socket API.

existing terminalpersistent PTYsSSH attachdirect agent attachagent stateagent API
tmux / Zellij

Classic multiplexers stop at terminals.

They own panes and persistence. They do not know which pane is blocked, working, done, or ready for an agent wait.

cmux / Warp

Terminal apps replace the terminal.

They can add polished desktop UX, but the workflow moves into their app. PK-Herdr stays inside the terminal you already use.

Solo

Dashboards supervise processes.

Process health and auto-restart are useful, but PK-Herdr is about persistent interactive agent panes, not dev-stack supervision.

Conductor / Emdash / Superset

Worktree tools own review flow.

They are for branch isolation, diffs, and PRs. PK-Herdr is the live terminal layer those agents can run inside or alongside.

One-line comparisons

Use this when deciding.

PK-Herdr vs tmuxtmux persists terminals; PK-Herdr persists agent workspaces and understands agent state.
PK-Herdr vs ZellijZellij is a modern terminal workspace; PK-Herdr is an agent multiplexer with state, waits, and orchestration.
PK-Herdr vs cmuxcmux is a Mac terminal app for agents; PK-Herdr is a terminal-native multiplexer that runs anywhere your terminal and SSH do.
PK-Herdr vs WarpWarp is an agentic development platform; PK-Herdr is the local terminal control layer for your existing agents.
PK-Herdr vs OpenCode webOpenCode's web mode serves one agent over HTTP; PK-Herdr is a terminal-native multiplexer for many agents and harnesses, reachable over plain SSH.
PK-Herdr vs SoloSolo manages your dev stack; PK-Herdr manages persistent interactive agent panes.
PK-Herdr vs Conductor, Emdash, SupersetThey orchestrate isolated worktrees and review diffs; PK-Herdr orchestrates live terminals and agent state.

Start with the multiplexer

If your agents live in terminals, put the terminals in PK-Herdr.

Install PK-Herdr, run two agents, split a pane, then detach once. The difference is obvious when the agents keep running.

light[/]