I built a proentropic memory layer for AI coding...

Every AI coding agent has the same problem: it makes a mistake, you correct it, and next session it makes the exact same mistake again. I built ThumbGate to fix this. It's an open-source MCP server that turns thumbs-up/down feedback into pre-action gates — hard enforcement that physically blocks the tool call before execution. How it works Your agent makes a mistake → you give 👎 with context ThumbGate auto-generates a prevention rule Next time the agent tries the same thing → PreToolUse hook fir