Build Daily

Tinley Park · October 21, 2026
Mischa van den BurgOct 20, 2026

I Ditched My Custom tmux Setup for Herdr (Here’s Why)

What it covers

The creator explains why they replaced their custom tmux setup with Herdr, a terminal multiplexer purpose-built for running multiple AI coding agents like Claude Code, and demonstrates how they run each agent inside a dev container over SSH for safety. The video also closes with a question to consider before adopting a multi-agent tool into your workflow.

The outline

Every point the video makes, in the order it makes them.

  1. 01

    What Herdr Is

    Herdr is a terminal multiplexer built for AI agents that shows the status of every agent in a single sidebar and plays a sound when one finishes.

  2. 02

    Why the Switch Happened

    The creator was already tracking agents in tmux but an update broke the setup, and they needed something that worked reliably over SSH.

  3. 03

    Herdr's Workflow Features

    Herdr runs in its own terminal window alongside a second tmux window, keeps tmux keybindings, connects to multiple machines, and lets the user run 3–4 long agent tasks while doing other work.

  4. 04

    Dev Containers Over SSH

    Each agent is run inside a dev container over SSH so that Claude Code can skip permission prompts without touching the creator's real file system.

  5. 05

    Open Source & Active Development

    Herdr is an open-source project that is in very active development, which the creator highlights as a reason to consider it.

  6. 06

    The Pre-Adoption Question

    The video ends with a question the creator recommends asking yourself before adding a multi-agent tool to your workflow.

The tool follows the workload

The moment a general-purpose terminal setup stops serving the new workload, a purpose-built one earns its place. Forty thousand stars and fresh funding suggest multi-agent orchestration is moving from experiment to infrastructure, and the dev-container-over-SSH pattern is the safety guardrail a solo shipper needs when agents run unattended. The question the video closes on—what to weigh before adopting multi-agent tooling—is the one a solo builder can't skip past.