Made for your agents.
Remade by them.

Herdr is a native app for Claude Code, Codex and any other coding agent. Your agent can change any part of it. Close it, they keep working.

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

Paste it in a terminal.

All downloads and what happens next →

Ask your agent to change Herdr. Try one:
❯

Customizing usually means picking colors. In Herdr it means everything. Want your Linear issues next to your agents? A meter for how much of your plan is left? A git graph of the repo you're in? Tell your agent. It's your Herdr.

Your agents run agents.
And hear back.

Your agent can hand a review or a test run to another agent and keep working. When the helper finishes, its report shows up in your agent's input, so you never copy anything between windows.

It starts helpershc run --bg codex "review my diff. Done: hc send t1"Any agent can start another, like Claude, Codex or a test script, and tell it where to report.
It steers themhc send t3 "take another look"While a helper works, your agent can change its task or answer its questions.
They report back<hc from="t3 reviewer">Reports, exits and requests for help go to your agent. You only see the result.

##See who needs you

Each agent tells Herdr whether it's working, done or waiting on you. The sidebar and the tab show which one needs you, so you can stop checking the rest.

Use a space for each repo and a tab for each task.

##Close it, they keep working

Your agents run in herdr-core, a small server on your machine, not in the window. Quit the app, update it or let it crash, and every terminal is still where you left it.

 

More about herdr-core →

##Every machine in one sidebar

Add any machine you can reach over SSH, like a server, a VM or a cloud sandbox. Its spaces and agents show up in the same sidebar under its name, and you start agents there the same way.

# or ask your agent: "add my server vps"
hc machine add vps

Its agents keep running there while your laptop sleeps or the app is closed.

##Change anything

Herdr keeps its layout, sidebar, tabs, keys and themes as plain files in ~/.config/herdr-app. An AGENTS.md in there explains them to your agent. You say what you want and your agent writes it.

~/.config/herdr-app/
├── AGENTS.md        what your agent can change
├── settings.json    fonts, theme, sounds
├── keys.json
├── layouts/
│   ├── main.json
│   └── board.json
├── mods/
│   ├── agents/main.js
│   └── tabs/main.js
└── themes/
❯ put a timer on each tab: how long its agent has been working

⏺ Update(mods/tabs/main.js)
  ⎿  Updated mods/tabs/main.js with 6 additions and 1 removal

⏺ Done. Each tab shows how long its agent has been at it.

##Any agent

Herdr runs real terminals, so your agents work the way they do now. Agents that support OSC 7501, an open status protocol, also show whether they're working, done or need you. Your own script can do it with one line.

# one line, and your own script is an agent too
printf '\e]7501;state=blocked:app=my-agent\e\\'

##Open source

The app, herdr-core and Herdr TUI are open source under Apache 2.0. You can read the code, change it, or build your own app on top of herdr-core.

herdrdev/herdr-app →   herdrdev/herdr-core →   herdrdev/herdr →

##Questions

What is Herdr?

A native app for running coding agents. They run in herdr-core, so they keep going when you close the window, and your agent can change any part of the app.

How is it different from Herdr TUI?

Herdr TUI is the original Herdr: a terminal app with its own server. This is a new, separate program built on herdr-core. They don't share agents, so what runs in one doesn't show up in the other. Herdr TUI keeps working, and everything for it is at herdr.dev/tui.

Which agents does it work with?

Anything that runs in a terminal. Agents that speak OSC 7501, an open protocol for reporting status, also show whether they're working, done or need you. An agent that doesn't speak it still runs, just without a status.

My agent doesn't show up in the agents list

The list shows agents that report their status through OSC 7501, so check these:

  • Older versions of an agent may not report it yet. Update the agent.
  • An agent running inside tmux within Herdr can't report through tmux. Run it in a Herdr pane directly.
  • Agents started in Herdr TUI live in its own server, so they don't show up in the app.
What happens when I quit, update or reboot?

Quitting or updating the app changes nothing: every agent keeps running in herdr-core. If the machine reboots or herdr-core stops, the programs stop too. Their panes come back with a shell in the same folder, but Herdr doesn't restart an agent or resume its work in progress. Start it again and carry on.

Which systems does it run on?

macOS (Apple silicon), Linux (x86_64 and arm64) and Windows (x86_64). Other machines join over SSH, whatever they run.

Is it free?

Yes. The app, herdr-core and Herdr TUI are all open source.

Made for your agents.
Remade by them.

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

Paste it in a terminal.

All downloads and what happens next →