Getting started with the apiary

This page gets you from a blank terminal to a working memory in about five minutes. No prior setup needed.

#How do I install the apiary?

Open a terminal and paste the line for your system. You do not need Node, npm, or a database set up first, the installer handles all of that for you.

macOS or Linux:

curl -fsSL https://get.theapiary.sh | sh

Windows (PowerShell):

irm https://get.theapiary.sh/install.ps1 | iex

The terminal prints a short progress log, brings up the daemons, registers the watchdog so everything survives a reboot, and opens a dashboard in your browser. That dashboard, not the terminal, is where you actually finish setup.

If you would rather read the script before you run it, visit get.theapiary.sh in a browser. It serves an inspect-before-piping page and publishes a checksum file so you can verify it first.

#What do I do in the dashboard the first time?

The dashboard opens at 127.0.0.1:3853. Click first time setup. It shows a short code right on the page and opens a tab where you approve it, creating a free Deeplake account if you do not already have one. You never copy a code out of a terminal window.

Once you approve, the dashboard lights up its connected views and you are ready to go. Nothing needs a restart.

If you already run Hivemind on this machine, the dashboard notices and offers to move you over cleanly. Running both at once is not supported, so let it handle the switch.

#Which coding assistants can I connect?

Claude Code, Cursor, and Codex are fully supported today. Hermes, pi, and OpenClaw support is in progress. Wire whichever ones you have installed with one command:

honeycomb setup

This finds the assistants already on your machine and connects each one. It is safe to run again any time, including after you install a new tool. Check that everything is wired and healthy with:

honeycomb status

#How do I save my first memory?

Teach it something true about your project, then ask for it back in your own words:

honeycomb remember "we deploy from the release branch, never from main"
honeycomb recall "how do we deploy"

That note is now saved. Write it while using one assistant, and a different assistant will recall it tomorrow, even on another machine. That is the entire point of the suite.

#What should I do next?

Open the dashboard any time with honeycomb dashboard to browse your memories, check each connected assistant, and see overall health. From here, go to whichever product docs match what you are actually trying to do, or read the glossary if a term does not make sense yet.

#Common questions

#How do I install the apiary?

Run one command in your terminal: curl -fsSL https://get.theapiary.sh | sh on macOS or Linux, or irm https://get.theapiary.sh/install.ps1 | iex in PowerShell on Windows. It sets up everything it needs, including Node, and opens the dashboard when it finishes.

#What do I do in the dashboard the first time?

Click first time setup at 127.0.0.1:3853. It shows a short code on the page and opens a tab for you to approve it, creating a free Deeplake account if you do not already have one. You never copy a code out of the terminal.

#Which coding assistants can I connect?

Claude Code, Cursor, and Codex are fully supported today. Hermes, pi, and OpenClaw support is in progress. Run honeycomb setup once and it wires every supported assistant it finds on your machine.

#How do I save and recall my first memory?

Run honeycomb remember followed by a plain sentence describing something true about your project, then honeycomb recall followed by a question about it. Recall does not need your exact original wording to find the note.