server-v0.0.5

bknd-io/bkndserver-v0.0.5Jul 10, 2026by Dhravya

AI Summary

Self-hosted supermemory instances now support local or remote embedding models, offering greater flexibility for users.

Key Highlights

Pluggable embeddings support for local ONNX, OpenAI, and Google.
Safe upgrades for legacy model handling.
First-boot picker and plan lock in embedding-plan.json.

New Features

Local ONNX embedding model support.
Remote embedding support (OpenAI/Google) via environment variables.
Automatic detection and locking of embedding plans.

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
```