herdr

supervise multiple coding agents in one terminal.

run Claude Code, Codex, pi, opencode, droid, amp, and plain shells side by side in your existing terminal. see which agent is blocked, done, or still working without leaving the command line.

workspaces, tabs, panes, automatic agent detection, and notifications. no electron, no web dashboard, no separate gui window.

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

github docs api

for you

supervise, triage, act

one place to see all running agents across workspaces
sidebar rolls up each workspace to its most urgent state
switch contexts instantly — click or keyboard
sound alerts and toast notifications for background events
mouse-native: click panes, drag borders, select text to copy
session persistence — close and reopen, everything restores
9 built-in themes, full color token overrides

for your agents

orchestrate, spawn, wait

create workspaces and split panes programmatically
spawn other agents in sibling panes
read output from any pane in the session
send text and keys into other panes
wait for output patterns or agent state changes
subscribe to real-time events over the socket
ship an agent skill or use the socket API directly

ambient awareness

the sidebar is split into two layers. scan the workspace list for the most urgent signal, then drill into the agents causing it in the selected workspace or across all workspaces.

workspaces

each workspace shows one aggregate dot — the most urgent state across all its agents. yellow means something is working. you scan the full list in a glance.

agents

the bottom section shows which specific agents are running in the selected workspace, or across all workspaces when you switch the panel scope. pi is working, droid is idle.

blocked

done

working

idle

how it works

install and launch

one binary, no dependencies. run herdr in your terminal. onboarding takes 10 seconds.

create workspaces

press n to create a workspace. it opens as a terminal context, labels itself from git repo or folder name.

launch agents

start your agents in panes like you normally would. herdr detects them automatically — no hooks, no config.

supported agents

herdr detects agents by reading foreground process and terminal output patterns. zero config required.

agent	idle / done	working	blocked
pi	✓	✓	partial
claude code	✓	✓	✓
codex	✓	✓	✓
droid	✓	✓	✓
amp	✓	✓	partial
opencode	✓	✓	✓
gemini cli	detected, not fully tested
cursor agent	detected, not fully tested
cline	detected, not fully tested

socket api

agents can use herdr too

herdr exposes a local unix socket that agents can talk to directly. create workspaces and tabs, split panes, spawn agents, read output, and wait for state changes.

the same surface is available as CLI commands (herdr workspace, herdr tab, herdr pane, herdr wait) and as a reusable agent skill.

socket api docs → agent skill →

# create a workspace with a label
herdr workspace create --cwd ~/project --label "api server"

# split a pane and run a command
herdr pane split 1-1 --direction right
herdr pane run 1-2 "npm test"

# wait for an agent to finish
herdr wait agent-status 1-1 --status done

# read pane output
herdr pane read 1-2 --source recent-unwrapped --lines 50