Skip to content

This release adds 4 notable features for engineering teams evaluating rollout.

Published 2mo MCP Developer Tools
✓ No known CVEs patched
Read the diff → Tool health → What is this tool? →

✓ No known CVEs patched in this version

Topics

agent-reliability ai-agents ai-cost-optimization ai-safety amp claude-code
+14 more
codex cursor developer-tools feedback-loop gemini guardrails mcp mcp-server opencode pre-action-checks reduce-llm-cost save-llm-tokens thompson-sampling thumbgate

Summary

AI summary

Stat card highlights now correctly reflect the clicked item.

Full changelog

What's Changed

  • feat: clickable stat cards filter demo results by @IgorGanapolsky in https://github.com/IgorGanapolsky/ThumbGate/pull/374
  • feat: deployment verification gate — no more lying about done by @IgorGanapolsky in https://github.com/IgorGanapolsky/ThumbGate/pull/375
  • fix: stat card highlights the clicked card, not the wrong one by @IgorGanapolsky in https://github.com/IgorGanapolsky/ThumbGate/pull/376
  • feat: rebrand README to ThumbGate + dashboard demo + test sync by @IgorGanapolsky in https://github.com/IgorGanapolsky/ThumbGate/pull/377
  • fix: rewrite all instructions with exact values, zero placeholders by @IgorGanapolsky in https://github.com/IgorGanapolsky/ThumbGate/pull/378
  • feat: add comparison section, SEO keywords, fix 3 broken tests by @IgorGanapolsky in https://github.com/IgorGanapolsky/ThumbGate/pull/379
  • fix: bump release version to 0.8.4 and harden sync targets by @IgorGanapolsky in https://github.com/IgorGanapolsky/ThumbGate/pull/380

Full Changelog: https://github.com/IgorGanapolsky/ThumbGate/compare/v0.8.3...v0.8.4

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 IgorGanapolsky/mcp-memory-gateway

Get notified when new releases ship.

Sign up free

About IgorGanapolsky/mcp-memory-gateway

Pre-action gates that prevent AI coding agents from repeating known mistakes. Captures explicit feedback, auto-promotes failures into prevention rules, and enforces them via hooks.

All releases →

Beta — feedback welcome: [email protected]