Your first session

This is a literal, start-to-finish walkthrough of a first session with the apiary, every command included.

#Step 1: install

Open a terminal and paste the line for your system.

macOS or Linux:

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

Windows (PowerShell):

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

The installer sets up anything missing, brings up the daemons, and opens a dashboard in your browser when it finishes.

#Step 2: confirm the install is healthy

Back in your terminal:

honeycomb status

You want to see the daemon reported as running. If honeycomb comes back as "command not found," open a fresh terminal window and try again, a new shell picks up the freshly installed command.

#Step 3: finish sign-in in the dashboard

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 have one yet. You never copy a code out of the terminal. Once you approve, the dashboard's connected views light up.

If the dashboard did not open on its own, run:

honeycomb dashboard

#Step 4: save your first memory

Teach it one durable fact about your work:

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

This is the kind of thing you would otherwise re-explain to an assistant every morning: a decision, a convention, a gotcha.

#Step 5: recall it

Ask for it back, in your own words rather than the exact original phrasing:

honeycomb recall "how do we deploy"

If it comes back empty, the most common reasons are being in a different project folder than where you saved the note, or semantic search not having warmed up yet. See troubleshooting if that happens.

#Step 6: wire your coding assistant

So far you have driven everything by hand. The real payoff is automatic capture and recall inside the tools you actually use:

honeycomb setup

This finds every supported assistant on your machine (Claude Code, Cursor, and Codex today, with Hermes, pi, and OpenClaw in progress) and connects each one. It is safe to run again any time, including after you install a new tool. Confirm the wiring:

honeycomb status

#Step 7: watch a session start informed

Open one of your wired assistants in the same project and start a new session. Instead of starting blank, it begins with a short briefing of what the apiary already knows, including the deploy note you just saved. You do not have to ask for it, and it stays small on purpose so it never clutters the conversation.

From here, you mostly stop thinking about it. As you work, useful moments get captured, and the right notes come back next time, in any wired tool, on any machine you sign in to.

#Step 8: see the whole picture

Browse the dashboard any time:

honeycomb dashboard

You will find your memories, the state of each connected assistant, shared skills, a map of your codebase, and overall health, all on one page.

#What next?

Read everyday use for the ongoing flow, teams if you want a discovery by one person to reach the whole team, or troubleshooting if any step here did not behave as described.

#Common questions

#What are the exact steps for a first session?

Install with one command, confirm the daemon is healthy with honeycomb status, sign in through the dashboard's first time setup button, save a memory with honeycomb remember, recall it with honeycomb recall, then run honeycomb setup to wire your assistants so it happens automatically from then on.

#How do I know the install actually worked?

Run honeycomb status. You want to see the daemon reported as running and your sign-in as connected. If the command is not found, open a fresh terminal and try again.

#What happens the first time I open a wired assistant?

It starts with a short briefing of what the apiary already knows about the project, including anything you just saved by hand. You do not have to ask for it, it is handed over automatically at the start of the session.