Run and orchestrate AI agents your way

Run agents directly from the browser or stream local sessions to a live dashboard. Two modes, one platform — no compromises.

Try Server Mode — no installSet up CLI Mode
Dashboard — server-side and CLI sessions running side by side

Two ways to run agents. Pick the mode that fits your workflow — or use both.

New

Server Mode

Run agents directly from the dashboard. No install needed — open your browser, start a session, and go. Sandboxed environment for safe experimentation with multi-turn conversations.

  • +No install needed — runs in the browser
  • +Server-side Claude SDK integration
  • +Multi-turn conversations without respawning
  • +Sandboxed environment for safe testing
CLI

CLI Mode

Run agents locally with full file access. One command wraps any process in a streamable session — monitor from your phone, approve tool calls from the couch, keep agents productive while you do other things.

  • +Full local file system access
  • +Stream any terminal session to the dashboard
  • +Multi-machine support — all in one view
  • +PTY mode for shells, structured mode for AI agents
Agent session started from dashboard — no install needed
01

Run

Start agents from the dashboard with Server Mode, or stream local sessions with the CLI. Either way, your agents show up in one unified view 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. Multi-turn conversations keep context across messages.

Multi-session dashboard with server and CLI sessions
03

Orchestrate

Run agents across multiple machines and from the browser simultaneously. See which agents are working, idle, or waiting for your input at a glance.

Server-Side SDK

Rich agent conversations, right from the browser

Server Mode runs Claude through a server-side SDK integration with full markdown, tool call blocks, and multi-turn conversations — no respawning between messages. CLI sessions render the same way, streamed from your local machine.

1.0  Server-Side SDK  →
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

Coming Soon

Multi-provider support

Server Mode will expand beyond Claude to support Gemini, Codex, and more. Run different providers side by side and pick the best tool for each task — all from the same dashboard.

Get Started

Choose your mode. Start in seconds.

Server Mode — no install needed

1Open the dashboard
app.orchestrat.ing
2Start a new session
Click "New Session" → choose a prompt

Agents run in a sandboxed server environment. Great for testing and experimentation.

CLI Mode — full local access

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

Agents run locally with full file access. Sessions stream to the dashboard automatically.

Built for developers who run AI agents — whether from the browser or the command line — and want to stay in control.

Quick experiments from the browser

Open the dashboard, start a Server Mode session, and test ideas in a sandboxed environment. No setup, no install — just start prompting.

Kick off agents before bed

Start a long refactor with CLI Mode 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 server-side and local agents simultaneously. See all sessions in one dashboard. Know instantly which one needs your attention.

Start orchestrating your agents

Try Server Mode from the dashboard — no install needed. Or set up the CLI for full local access.

Open DashboardView on GitHub