Skip to content

This release includes breaking changes for platform teams planning a safe upgrade.

Published 3mo MCP Data & Storage
✓ No known CVEs patched
Read the diff → Tool health → What is this tool? →

✓ No known CVEs patched in this version

Summary

AI summary

Fixed re‑downloading of the embedding model on server restart and prevented crashes during initial download.

Full changelog

What's Changed

Bug Fixes

  • Model caching: Fixed an hf-hub issue that caused the 1.2 GB embedding model to be re-downloaded on every server restart. The cache directory is now respected correctly so the model is fetched only once.
  • SIGTERM / MCP timeout during download: MCP clients were timing out or the server was crashing with SIGTERM while the embedding model was still being downloaded on first run. This is fixed by an ensure_embedding_ready! wait loop that transparently blocks tool calls until the model is fully loaded, preventing both the timeout and the signal-induced crash.
  • Clippy warning: Fixed a minor Clippy lint (&PathBuf argument changed to &Path).

Maintenance

  • Removed unused HF_HOME environment variable entries from dev configuration files.
  • Clarified Docker volume documentation — the correct cache path for the model inside the container is /data/models.

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 pomazanbohdan/memory-mcp-1file

Get notified when new releases ship.

Sign up free

About pomazanbohdan/memory-mcp-1file

A self-contained Memory server with single-binary architecture (embedded DB & models, no dependencies). Provides persistent semantic and graph-based memory for AI agents.

All releases →

Beta — feedback welcome: [email protected]