# Local: Run Supermemory locally: self-hosted server for macOS and Linux

[Changelog](https://supermemory.ai/changelog) · [Local](https://supermemory.ai/changelog/local)

LocalJune 10, 2026

## Run Supermemory locally: self-hosted server for macOS and Linux[#](https://supermemory.ai/changelog/run-supermemory-locally)

Install the self-hosted server from a published macOS or Linux binary with local authentication and encrypted embedded storage.

### Improvements

* Codex now preserves whether a saved memory belongs to you, the project, or a custom container.
* Integrations now shows active connections, sync status, and recently imported documents in an activity rail.
* [Cursor and Granola now appear in the Integrations catalog.](https://supermemory.ai/docs/connectors/granola)

### Fixes

* The Conversations API now appends turns without replacing, dropping, or duplicating earlier messages.
* The web app now loads the memory profile for the selected space.
* Integration upgrade buttons now open checkout for the intended plan.
* Integration dialogs now close on outside click and show a working Connect action.

## Start building with supermemory.

Memory and continual learning for any model, any harness. Available through our API, plugins, and MCP.

[Build with supermemory ](https://console.supermemory.ai/)