Mission control for coding agents
One universe for your agents, on every machine you own.
Agentorrery orchestrates the coding CLIs already on your machines: Claude Code, Codex and OpenCode. A root agent delegates the work, a live 3D space shows which agent needs you, and any conversation can be handed to a terminal when you want to go deep.
- Your CLIs, your accounts. orrery has no model of its own. It runs the claude, codex and opencode already installed on the machine, with the accounts they are signed in to.
- On your machines. Each machine keeps its own SQLite database, and the console listens on 127.0.0.1 until you open it to your network.
- You set what agents may do. A new agent approves its own tool calls, as it would in its CLI; set it to ask first instead. Changing a file outside its project always waits for you.
- What it takes. Linux x64 or macOS on Apple silicon, Node.js 22 or newer, and one agent CLI.
01What is different
An orchestrator made of the tools you already run.
It runs the CLIs you already have
An agent in orrery is Claude Code, Codex or OpenCode as installed and signed in on that machine, not another agent loop written to replace them. You choose the runner and the model agent by agent, and can change either.
A picture that manages your interruptions
The space shows every project and agent at once, and only what needs you raises a beam: a permission, a question, a result to review, a failure. You answer that and move on, instead of sinking into one agent's problem while the others wait.
A terminal when you want to go deep
Join a running Claude Code or Codex session from a terminal and work in it alongside the console, or hand the whole conversation to the CLI itself. Message the agent in orrery again and it takes the conversation back, with what happened in the terminal.
Delegation and orchestration are built in
A root agent per machine and a lead per project start agents, break work into tasks and hand them on, with tools every session gets whichever CLI runs it. Handing work over is something agents do, not something you do for them.
02The problem
Orchestrators assume one computer. Your work does not fit on one.
Running several coding agents today mostly means more terminals on the same machine. That goes wrong in five ways.
One machine is assumed
Agents get started side by side on a single computer, or in identical containers. But an iOS build needs a Mac with Xcode, an Android build needs the SDK and a training run needs a GPU. Work that belongs on the other machine waits for you to carry it there.
A wall of terminals
Every agent is a tab or a pane. Finding out who is working, who has finished and who gave up means reading scrollback, one session at a time.
Blocked agents wait in silence
An agent that needs a permission or an answer stops, and stays stopped until you happen to look at its terminal.
You are the message bus
Agents in separate sessions cannot hand each other work or ask each other a question, so you copy results out of one and paste them into the next.
One vendor's CLI
A tool built around a single agent CLI leaves the others you are signed in to unused, and ties every job to one family of models.
03The space
See all of it at once.
The console opens on a 3D space. Nothing in it is decoration: every shape is something real, and it stays put so you can find it again.
Planets are projects
A project is a folder registered with orrery. Its halo shows its status.
Rings hold codebases
The apps, services and packages inside a project sit on a ring around its planet.
Agents stand by their work
Each agent has a fixed place next to the project or codebase it works in, so it is where you left it.
Moons are finished tasks
Active tasks float above their planet. A completed one becomes a moon.
Your own sessions show too
A Claude Code, Codex or OpenCode you started in a terminal appears at its project as a hollow wireframe: watched, not controlled.
An agent's body is its status
- Working
- Idle
- Paused
- Error
- Offline
Its ring is its runner
- Claude Code
- Codex
- OpenCode
04Machines
Built around machines that are not the same.
Join the computers you own into one cluster and tell orrery what each is good for. They appear side by side, each on its own platform.
- laptopA Mac with Xcode
- workstationA Linux box with an NVIDIA card
- build-serverA server with the Android SDK
Each machine keeps its own
Its own database, projects and agents. Agents run natively on the machine that owns them, and the space on any machine shows and drives all of them.
Say what each one can do
Tag a machine with capabilities such as ios-development, android-development or gpu. orrery suggests tags from what it finds installed (Xcode, the Android SDK, Docker, an NVIDIA GPU) and tags nothing until you say so.
Work lands where it can be done
Every root agent is told each machine's operating system, hardware, capabilities and runners, so it knows which machine a job belongs on. From any machine you can start an agent on the one that has what the work needs.
Joined by a code, linked over TLS
Machines on the same network join with a join code. The links between them are encrypted with TLS 1.3. A machine that drops out stays visible as last seen and is reconnected when it returns.
05Orchestration
Delegation comes first, whichever CLI does the work.
You talk to one agent. It knows every project on its machine, and who to hand the work to.
A root agent per machine
It belongs to no project and is told about every project and agent on its machine. Ask it to create a project, start an agent or say what needs you first.
A lead per project
Each project has one agent that answers for it. The root agent asks the lead instead of reading the project itself, and hands it the work that belongs there.
A shared task queue
Agents create tasks, break work down into subtasks and hand them to each other. A breakdown shows in the space as a tree, and the agent that created a task is told how it ended.
Messages instead of copy and paste
Every agent session gets orrery's MCP server, whichever CLI runs it. Agents message each other by name, report progress and ask you a question with one-click answers.
Your CLIs, your sign-ins
orrery has no model of its own. It runs Claude Code, Codex and OpenCode as they are installed and signed in on the machine. Each agent has its runner and model, and you can change either.
06Your attention
Interrupted only when it matters. Deep when you choose.
Many agents mean many interruptions. orrery shows you which one is next, lets you answer it where you are, and gets out of the way when one problem deserves a terminal and your whole attention.
What needs you finds you
Permission requests, questions, results to review, failures and stalled sessions raise an amber beam in the space and line up in a Needs you strip. Off-screen ones get an arrow at the edge.
Answer, and go back to what you were doing
A permission is a click and a question comes with its answers. The agent carries on and you have not opened its terminal.
Hand a conversation to a terminal
When one problem needs you properly, press t on the agent: orrery steps back and the same conversation continues in the runner's own CLI. Or join the live session from a terminal, and orrery keeps running it.
Autonomy, agent by agent
Supervised asks before it acts, auto-edit approves reading and editing on its own, autonomous approves everything. What the policy does not approve waits for your answer.
Local until you say otherwise
The console listens on 127.0.0.1 only. Open it to your network in Settings and it is served over HTTPS, behind a sign-in.
Use it your way
In a browser, in the desktop app for Linux and macOS, or from a phone on the same network. The space has hotkeys for everything you do often.
07Get started
Put your machines in orbit.
You need
- Node.js 22 or newer
- At least one agent CLI, installed and signed in: claude, codex or opencode
- Linux x64 or macOS on Apple silicon
These builds are unsigned. macOS will warn before it opens one, and you have to allow it yourself. They are built from the source by the release workflow on GitHub.
Desktop app
A window onto the console, with the daemon inside it.
Daemon only
The server on its own, with the Erlang runtime included. It uses the Node.js on your PATH.
From source
With Erlang/OTP 28, Elixir 1.19 and Node.js 24, then open http://localhost:4000.
cd orrery
mix setup
bin/serverThe first visit leads to the welcome screen, which creates your account, sets up the agents folder and asks which runners orrery may use.