rlhf-feedback-loop

About rlhf-feedback-loop

Use rlhf-feedback-loop with your agent

claude mcp add rlhf-feedback-loop -- npx -y rlhf-feedback-loop

{
  "mcpServers": {
    "rlhf-feedback-loop": {
      "command": "npx",
      "args": [
        "-y",
        "rlhf-feedback-loop"
      ]
    }
  }
}

Frequently asked questions

What is rlhf-feedback-loop?

rlhf-feedback-loop is an MCP (Model Context Protocol) server by igorganapolsky in the Autonomous Agents category. RLHF feedback loop for AI agents. Capture signals, promote memories, block mistakes, export DPO.

How do I connect rlhf-feedback-loop to Claude, Cursor, or another MCP client?

Install rlhf-feedback-loop from its npm package (rlhf-feedback-loop) and register it under "mcpServers" in your client's MCP configuration — for example claude_desktop_config.json or Cursor's mcp.json — then restart the client.

Is rlhf-feedback-loop open source?

Yes — the source code is public at github.com/igorganapolsky/mcp-memory-gateway, with 23 GitHub stars.

Can AI agents pay to use rlhf-feedback-loop?

Not yet through Loomal — rlhf-feedback-loop is listed as a free directory entry. If its maintainer verifies ownership, they can set per-call USDC pricing that agents pay over x402, with settlement on Base.