Trust is the first feature.
The Apiary remembers the most sensitive thing a developer tool can touch: your code and how you work. So trust is not an afterthought, it is the starting point. Your memory is private by default, it stays in a store you own, and every product is AGPL open source. Memory lives on Deeplake, reached only by a local daemon that binds to your machine.
DownloadWhy you can trust it, not just take it on faith
Trust here is a property of the system, not a promise on a page. Three things back it up. Your memory is private by default: nothing is shared across a company, team, or project unless you widen sharing on purpose. Your data is yours: it lives on Deeplake, which you can run in your own cloud, so it stays inside your perimeter rather than on a vendor server you cannot see. And every product is open source under AGPL-3.0-or-later, so you can read exactly what runs on your machine. You are never asked to trust a black box, because there isn't one.
How your data is protected
Loopback only
The daemons bind to 127.0.0.1, so nothing off your device can reach them. hive passes your session through and stores nothing itself.
Isolated at the storage layer
Companies, teams, and projects are separated where the data is stored, not just hidden in the app, so nothing bleeds across a boundary.
Secrets kept apart
API keys are stored separately from memory, encrypted, tied to your machine, and never shown to an assistant. An agent can use a secret without seeing it.
Versioned and auditable
Every memory is versioned, so you can always see what was known and when. Nothing is silently overwritten.
Your own store
Deeplake can run in your own cloud account, so your memory stays on infrastructure you own. Only the local daemon talks to it.
Read-only when you need it
Flip the stack to read-only for a session and nothing new is written, while recall still works. Good for sensitive material.
What leaves your machine, and what does not
Your actual memories go only to the store you control. The only outbound traffic is the sign-in with Deeplake and, optionally, anonymous product-usage counts that help the makers understand adoption. That usage signal never includes your code, prompts, memories, file paths, or names, and you can turn it off entirely.
doctor, the watchdog, has no code that can read or delete your credentials. If it ever needs to send a diagnostic report, that report is scrubbed and never carries your code or secrets, and you can turn it off.
Common questions
Where does my data live?
On Deeplake, which you control and can host in your own cloud account. A small local daemon is the only thing that connects to it, and on a single machine it listens only to your own computer.
Can other people or teams see my memories?
No, unless you choose to share. Companies, teams, and projects are isolated at the storage layer, and within a team the default leans private. You widen sharing on purpose.
Are my API keys and secrets safe?
Yes. Secrets are stored separately from memory, encrypted, tied to your machine, and never shown to an assistant. An agent can use a secret without ever seeing its value.
Does The Apiary send my code or prompts anywhere?
The only outbound traffic is the sign-in and optional anonymous usage counts that never include your code, prompts, memories, paths, or names. You can turn the usage signal off.
Can I stop it from recording?
Yes. Put the stack in read-only mode for a session, so recall still works but nothing new is written.
Keep your memory yours.
Install the stack and keep your data on hardware you control.
Windows (PowerShell): irm https://get.theapiary.sh/install.ps1 | iex
Download