Supermemory

vserver-v0.0.5 scope: server Feature

This release adds 2 notable features for engineering teams evaluating rollout.

Published 16d AI Agents & Assistants

✓ No known CVEs patched

✓ No known CVEs patched in this version

Topics

agent-memory ai-memory cloudflare-kv cloudflare-pages cloudflare-workers drizzle-orm

+6 more

memory postgresql remix tailwindcss typescript vite

Affected surfaces

breaking_upgrade

Summary

AI summary

Pluggable embedding models allow local ONNX or remote OpenAI/Google via env vars, with safe upgrades that prevent mixed vector dimensions.

Type	Severity	Summary	CVE
Feature	Medium	Adds pluggable embedding model support (local ONNX, OpenAI, Google). Adds pluggable embedding model support (local ONNX, OpenAI, Google). Source: llm_adapter@2026-07-15 Confidence: high	—
Bugfix	Medium	Fixes safe upgrade handling for stores without a lock, assuming legacy model config. Fixes safe upgrade handling for stores without a lock, assuming legacy model config. Source: llm_adapter@2026-07-15 Confidence: high	—

Full changelog

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

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

supermemory-server upgrade

Weekly OSS security release digest.

The CVE patches and breaking changes that affected production tools this week. One email, every Sunday.

No spam, unsubscribe anytime.

Share this release

Track Supermemory

Get notified when new releases ship.

About Supermemory