This release adds 2 notable features for engineering teams evaluating rollout.
✓ No known CVEs patched in this version
Summary
AI summaryFixed a false positive in the report checking logic.
Changes in this release
| Type | Severity | Summary | CVE |
|---|---|---|---|
| Feature | Low |
Adds enhanced archival process for autopilot reports and garbage collection of old archived reports Adds enhanced archival process for autopilot reports and garbage collection of old archived reports Source: llm_adapter@2026-06-10 Confidence: high |
— |
| Bugfix | Medium |
Fixes check false issue Fixes check false issue Source: llm_adapter@2026-06-10 Confidence: high |
— |
Full changelog
Changelog
- 0f4eac0a73e5f1e28061670276790515c872e441 feat: enhance archival process for autopilot reports and implement GC for old archived reports
- 712234b0340a4375dcafc6c4c64932987223eba1 fix check false
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
About s60yucca/mnemos
Persistent memory engine for AI coding agents. Stores architecture decisions, bug root causes, and project conventions across sessions. Single Go binary with embedded SQLite, FTS5 search, context assembly within token budgets, and autopilot setup for Claude Code, Kiro, and Cursor.
Related context
Related tools
Beta — feedback welcome: [email protected]