Open source, auditable agent memory
Open source under the AGPL. Read the code, audit how your memory is handled, and fork it. The privacy is verifiable, not just promised.
Verifiable, not just promised
HiveMind keeps your agents' memory on hardware you own and claims it never leaves your network. With closed software you would have to take that on faith. Because the source is open, you (or anyone) can read exactly what it does, confirm there is no phone-home, and trust it for the right reason.
For a tool you let read and write a memory across your machines, that auditability is not a nice-to-have. It is the basis for trusting it at all.
Yours to read, fork, and run
It is licensed under the GNU AGPL v3.0. You can self-host it, study how the journal, sync, and confidence model work, and adapt it to your own needs. The repository is the contract: the same small CLI your agents call is the one you can inspect line by line.
Frequently asked
What license is HiveMind under?
The GNU AGPL v3.0. You can read, audit, fork, and self-host it. If you run a modified version as a network service, you share your changes under the same terms.
Why does open source matter for an agent memory?
Because HiveMind holds your memory locally, the privacy claim is only as good as your ability to check it. Open source means you can verify that your data stays on your own hardware, rather than taking it on faith.