Architecture overview

What runs on your computer, on your server, on other machines and on your phone, how the parts talk, and what stays on your computer.

Your agents build the workspace they work in. They start other agents, open views, add widgets and run tools with the same hive command you use. This page shows the parts behind that, and where each one runs.

Paste this into your coding agent to map your own setup onto this page.

Show the prompt
Map my Hivemind setup onto the parts on the "Architecture overview" page. Do not change anything.

1. Run `hive --version` and `hive daemon status`: is the background process running?
2. Run `hive ctl agents --json`. If it exits 3, the app is not open on this project; say so and go on.
3. Run `hive network show`, `hive machine list` and `hive host status` (it may say no host runs here).
4. For each part on the page (desktop app, background process, hive command, network server, phone page, machines, host, HiveHub), tell me whether it runs or is set up here, and what links to it.

REFERENCE https://hivemind.griiken.com/guide/architecture.md
What runs whereOn your computer the desktop app, the background process that runs your agents, and the hive command. Your own network server relays encrypted traffic to your phone and hosts. Machines are reached over ssh, plugins come from HiveHub.YOUR COMPUTERYOUR SERVEROTHER MACHINESdrive.sockpty socketrunshookshive ctlhttpsencryptedsshhttpsrelayhive commandyou, agents, programsDesktop appwindows and viewsYour agentseach in a terminalBackground processruns every agentStays on this computer: your keys, settings,API tokens and saved screens.Closing the window leaves agents running.HiveHubpluginsNetwork serverhive-net servePhone pagea browserMachineover sshHosthive host
What runs where
  • Desktop app, on your computer: the windows, the canvas and views. It starts the background process and hive-net.
  • Background process, on your computer: runs every terminal and agent, and works out each agent's state. It talks to the app over a local socket.
  • Your agents run in terminals of the background process. Their hooks tell it what they do.
  • hive command: you, your agents and your programs drive the app through drive.sock.
  • Desktop app → HiveHub: https, to install plugins.
  • Desktop app → network server: encrypted end to end. Your server relays it, and serves the phone page over https.
  • Desktop app → machine: ssh. Network server ↔ host: relay.
  • Stays on this computer: your keys, settings, API tokens and saved screens.

The parts

For agents

Everything an agent does goes through hive ctl on the drive socket, or the same methods from your own program with a token (API). Which part each one touches:

Parthive ctlAPI methods
Agents in the background processagents, spawn, send, keys, read, stream, sessions, sleep, wake, rename, closeagent.*, status.all, terminal.*
Agents working togetherworkflow, approve, approval, report, inbox, connect, disconnectlink.connect, link.disconnect
Workspace and framesframes, frame add, list-workspacesframe.open, frame.close, worktree.list, store.*
Desktop app windowsfocus, open-reviewpresence.set, appearance.get
Pluginsplugin list, plugin open, plugin commands, plugin call, plugin close, open-tool, view emitwidget.*, tool.open, view.*
Issuesset-state, add-comment, mark-acceptance, delete-issueissue.list, issue.read
hive-net, phone, machines, hostsnone: use hive network, hive machine, hive hostnone

hive ctl needs the app or hive host running for the workspace; it exits 3 when neither is. Every command is in the CLI reference, every method in Methods.

Last validated for Hivemind 2026.10.3.

Edit on GitHub

On this page