rlhf-feedback-loop
Level CLocalRLHF feedback loop for AI agents. Capture signals, promote memories, block mistakes, export DPO.
Installation
MCP client config (paste into mcp.json)
{
"mcpServers": {
"rlhf-feedback-loop": {
"command": "npx",
"args": [
"rlhf-feedback-loop"
]
}
}
}Agent install prompt
Copy and paste into Cursor / Claude / other agents to install this MCP for you
Please read this MCP repository and install it into my current environment:
https://github.com/IgorGanapolsky/mcp-memory-gateway
Known working client config (can write into mcp.json):
{
"mcpServers": {
"rlhf-feedback-loop": {
"command": "npx",
"args": [
"rlhf-feedback-loop"
]
}
}
}
Please: 1) check README for deps and env vars; 2) write config for my client; 3) if secrets are missing, tell me what to fill — do not invent values.
Related servers
MCP Memory GatewayPre-action gates that block AI agents from repeating known mistakes.ThumbGateThumbGate Pre-Action Checks self-improve from ranked lessons and repeated failurREA逆向工程一体化 MCP:把 Ghidra、IDA、Hopper、JADX、Frida、ADB、浏览器等工具统一封装,Agent 无需源码即可分析二进制、App、gemini-cliAn open-source AI agent that brings the power of Gemini directly into your termiawesome-mcp-serversA collection of MCP servers.clineAutonomous coding agent as an SDK, IDE extension, or CLI assistant.