Monitor and control your AI agents from anywhere

Stream terminal sessions to a live dashboard. Approve permissions, send instructions, and orchestrate Claude Code across all your machines.

Get startedView setup
Dashboard screenshot — sessions list with live agent activity

Purpose-built for AI coding agents. One CLI command wraps any process in a streamable session. Monitor progress from your phone, approve tool calls from the couch, and keep your agents productive while you do other things.

Terminal output streaming to browser in real-time
01

Stream

Wrap any command with orch and it streams to your dashboard instantly. PTY mode for shells, structured mode for AI agents with rich message rendering.

Permission approval UI with Allow / Deny buttons
02

Control

Approve permissions, deny tool calls, toggle YOLO mode, and send follow-up instructions — all from the dashboard. No SSH, no VPN.

Multi-session dashboard grouped by machine hostname
03

Orchestrate

Run agents across multiple machines. Sessions are grouped by hostname. See which agents are working, idle, or waiting for your input at a glance.

Structured Mode

Rich agent conversations, not raw terminal output

Claude Code sessions render with full markdown, tool call blocks, thinking indicators, and permission requests — just like the native CLI, but in your browser from anywhere.

1.0  Structured Mode  →
Chat view with markdown, tool blocks, and permission banners
Sessions grouped by hostname: MacBook, Workstation, Server

Multi-Machine

All your machines, one dashboard

Sessions are automatically grouped by hostname. Run agents on your desktop, a remote server, and a cloud VM — monitor them all from a single view. CLI version tracking tells you when machines need updates.

2.0  Multi-Machine  →

Permissions

Stay in control without being in the terminal

Approve or deny tool calls per-session or per-project. Toggle between normal and YOLO mode on the fly. Grant blanket permissions for trusted tools, or review each action individually.

3.0  Permissions  →
Permission prompt: Allow Bash / Deny with Normal/YOLO toggle

Get Started

Three commands. That's it.

1Install the CLI
$npm i -g orchestrating
2Authenticate
$orch login
3Start a session
$orch claude "refactor the auth module"

Then open app.orchestrat.ing — your session appears instantly.

Built for developers who run AI agents and want to stay in control without being chained to a terminal.

Kick off agents before bed

Start a long refactor from your laptop, check progress from your phone in the morning. Approve the one permission it's waiting on, and it continues.

Parallel agents, one view

Run Claude on auth, another on tests, a third on docs. See all three in one dashboard. Know instantly which one needs your attention.

Remote machine control

SSH into a server, run orch claude — now monitor and interact from your browser. No port forwarding, no tmux, no VPN.

Start orchestrating your agents

Get startedView on GitHub