Skip to content

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

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

Indexing progress calculation now accurately reflects parsing and embedding ratios with a weighted formula.

Full changelog

This release focuses on significantly improving the developer experience (UX) by providing a realistic and monotonically increasing progress metric during the codebase indexing phase.

📊 Indexing Progress Overhaul

  • Two-Phase Weighted Formula: The overall indexing progress is no longer a simple ratio of embedded_chunks / total_chunks. Since total_chunks was dynamically growing as files were parsed, the old metric misleadingly sat at ~97% even when the system had only parsed 20% of the project's files.
  • Accurate Metric: The new calculation properly weights the operation:
    overall_progress = parse_ratio * (70% + embed_ratio * 30%).
    This guarantees a smooth, realistic 0% to 100% climb based on the total number of files in the project.
  • Premature Completion Guard: Added strict parsing_done safeguards. The system can no longer incorrectly mark graph or vector indexing as completed simply because the job queues momentarily emptied before the AST parser had a chance to enqueue the next batch of files.

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]