server-v0.0.5

jitsucom/jitsuserver-v0.0.5Jul 10, 2026by Dhravya

AI Summary

Update adding pluggable embedding models for self-hosted Supermemory instances, allowing users to choose between local and remote models.

Key Highlights

Pluggable embeddings supporting local ONNX, OpenAI, and compatible providers
Safe upgrade mechanism with plan locking to prevent vector mixing
First-boot picker for embedding model selection

Breaking Changes

Safe upgrades logic: same-dimension model switches now fail fast instead of mixing vectors

New Features

Local or remote embedding model support via environment variables
Plan locking in `embedding-plan.json` to manage model selection

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
```