rlhf feedback loop for Grok
io.github.igorganapolsky/rlhf-feedback-loop
RLHF feedback loop for AI agents. Capture signals, promote memories, block mistakes, export DPO.
client:Grok
transport:stdio
runtime:npm
Install rlhf feedback loop in Grok
.mcp.json (in your project root)
{
"mcpServers": {
"rlhf-feedback-loop": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"rlhf-feedback-loop"
]
}
}
}Grok Build reads Claude Code's .mcp.json and Claude Desktop's config unchanged, so a server you have already set up there needs nothing new. The Grok web app and X integration do not take custom servers. Grok docs