Starstruk Logo MarkStarstruk

server-v0.0.5

google-gemini/gemini-cliserver-v0.0.5Jul 10, 2026by Dhravya

AI Summary

Self-hosted instances now support pluggable embedding models, allowing the use of local ONNX or remote OpenAI/Google APIs. The update also introduces safe upgrades to prevent vector mixing.

Key Highlights

  • Pluggable embeddings (local ONNX or remote APIs)
  • Safe upgrades with plan locking
  • First-boot picker for embedding models

New Features

  • Pluggable embeddings
  • Safe upgrades
  • Legacy model fallback support

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
```