server-v0.0.5

supermemoryai/supermemoryserver-v0.0.5Jul 10, 2026by Dhravya

AI Summary

Adds flexibility to self-hosted instances by supporting local and remote embedding models, alongside safe upgrade mechanisms for existing stores.

Key Highlights

Pluggable embedding support for local ONNX, OpenAI, and Google
Configuration via 'SUPERMEMORY_EMBEDDING_*' environment variables
Safe upgrade path for legacy stores with automatic lock detection

Breaking Changes

Switching to same-dimension models now fails fast instead of mixing vectors.

New Features

Pluggable embedding models
Safe upgrade handling
First-boot embedding picker

Full Release Notes

Self-hosted supermemory can now use local or remote embedding models.

- **Pluggable embeddings** — local ONNX (default) or OpenAI / OpenAI-compatible / Google via `SUPERMEMORY_EMBEDDING_*`; first-boot picker + plan lock in `embedding-plan.json`
- **Safe upgrades** — populated stores without a lock assume legacy `local · Xenova/bge-base-en-v1.5 · 768d`; same-dimension model switches fail fast instead of mixing vectors

```sh
curl -fsSL https://supermemory.ai/install | bash
```

```sh
supermemory-server upgrade
```