Rlhf Feedback Loop

Name: Rlhf Feedback Loop
Author: igorganapolsky

by igorganapolskycommunityv0.6.13

ThumbGate is a control plane for AI coding agents that transforms feedback into enforcement, preventing repeated mistakes and ensuring compliance with team standards during development.

From the registry: RLHF feedback loop for AI agents. Capture signals, promote memories, block mistakes, export DPO.

GitHub Repository

Install & configure

Prerequisites

required
Node.js
Required to run via npx. Node.js >= 18
https://nodejs.org

Install in your client

Paste into the AI you're chatting with — it will figure out the rest

Please install the `rlhf-feedback-loop` MCP server into my current AI client (that's you).

Required prerequisites (do these first if not already done):
- **Node.js** — Required to run via npx. Node.js >= 18 (https://nodejs.org)

Canonical MCP server config (stdio transport):
- command: `npx`
- args: ["--yes","thumbgate","serve"]

Note: ThumbGate: AI agent feedback loop and enforcement system. Captures thumbs-up/down, distills lessons, enforces gates via PreToolUse hooks. Initialize with `npx thumbgate init`. Free tier: 3 captures/day, 5 searches/day. Pro $19/mo, Team $99/seat/mo.

Add this MCP server to my current client's config in the correct format for you. If you need secrets or credentials I haven't provided, ASK me — do not invent values or leave raw placeholders. After adding it, tell me how to verify the server is connected.

Note: ThumbGate: AI agent feedback loop and enforcement system. Captures thumbs-up/down, distills lessons, enforces gates via PreToolUse hooks. Initialize with `npx thumbgate init`. Free tier: 3 captures/day, 5 searches/day. Pro $19/mo, Team $99/seat/mo.