IgorGanapolsky/mcp-memory-gateway

v0.6.12 Feature

This release adds 3 notable features for engineering teams evaluating rollout.

Published 2mo MCP Developer Tools

View tool

✓ 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

Live production deployment with Stripe checkout and end‑to‑end billing.

Full changelog

What's New in v0.6.12

🚀 Live Production Deployment

Service live at https://rlhf-feedback-loop-production.up.railway.app
All Stripe keys configured — checkout creates real sessions, webhook provisions API keys
Auto-deploy on push via deploy-railway.yml

📡 Feedback Ingest Watcher

New scripts/feedback-ingest-watcher.js: auto-reingests raw JSONL entries through all 7 downstream systems (schema validation, memory promotion, vector indexing, DPO/KTO export, prevention rules, stats, log)
Zero changes required in external plugins (Amp, etc.)
npm run ingest:once / npm run ingest:watch

💳 End-to-End Billing

POST /v1/billing/checkout → live Stripe checkout session → webhook → API key provisioned
Direct buy link: https://buy.stripe.com/bJe14neyU4r4f0leOD3sI02 ($10/mo founding price)
JSONL watcher + status dashboard for operator visibility

📦 Distribution

Updated MCP adapter configs to v0.6.12
Updated mcp-hub-submission.md
1,297 npm downloads/week

Install

npx -y [email protected] serve

View diff on GitHub

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

Share on X Share on Bluesky

Track IgorGanapolsky/mcp-memory-gateway

Get notified when new releases ship.

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 →