Main

A good way to structure “many agents”

• Create one workspace per repo.
• Use one tab per task (tests, build, lint, deploy).
• Detach (ctrl+b q) when you want agents to keep running in the background.

README excerpt (verbatim)

herdr

herdr.dev · install · quick start · supported agents · integrations · configuration · socket api

https://github.com/user-attachments/assets/043ec09f-4bdd-41d5-aee0-8fda6b83e267

agent multiplexer that lives in your terminal.

workspaces, tabs, panes. mouse-native: click, drag, split. every agent at a glance: blocked, working, done. detach and reattach, agents keep running. no gui app, no electron, no mac-only native wrapper. you see the agent's own terminal, not someone's interpretation of it.

install

curl -fsSL https://herdr.dev/install.sh | sh

or download the binary from releases. requires linux or macos.

update

herdr notifies you when a new version is available. run manually to update:

herdr update

how it compares

FAQ

Q: Is it a tmux replacement? A: It overlaps on persistence/panes, but it’s designed to be agent-aware (see README comparison table).

Q: Can I use it remotely? A: Yes—README shows SSH attach patterns and remote targets.

Q: Do I need integrations? A: No—zero-config works by default; integrations add richer agent state forwarding (per README).