Rlhf Feedback Loop runs on your own machine — the client starts it, so there is no endpoint to ping. 103 installs a week from npm. Last commit 6 Nov 2026.
RLHF feedback loop for AI agents. Capture signals, promote memories, block mistakes, export DPO.
We read the source, 1 d ago · rules 995398eba69f
A value the model can set ends up inside a file or shell call. That is not a flaw by itself — for a terminal server it is the job — but it is where things go wrong when it is not.
fs.writeFileSync(outputPath, result.jsonl);
What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.
пакет rlhf-feedback-loop ссылается на igorganapolsky/rlhf-feedback-loop
try { execSync(`which ${cmd}`, { stdio: 'pipe' }); return true; } catch (_) { return false; }
const refFile = path.join(gitDir, 'refs', 'heads', branch);
target.innerHTML = gates.map(function (g) {
/id_rsa|id_ed25519/,
for (const fileName of fs.readdirSync(directory)) {
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
That is not a flaw by itself — but it is where things go wrong when it is not the job. We re-read this code on every release. Watch it and you hear from us the day another one appears.
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add rlhf-feedback-loop -- npx -y rlhf-feedback-loop
{
"mcpServers": {
"rlhf-feedback-loop": {
"command": "npx",
"args": [
"-y",
"rlhf-feedback-loop"
]
}
}
}
[mcp_servers.rlhf-feedback-loop]
command = "npx"
args = ["-y", "rlhf-feedback-loop"]
{
"mcpServers": {
"rlhf-feedback-loop": {
"command": "npx",
"args": [
"-y",
"rlhf-feedback-loop"
]
}
}
}
{
"servers": {
"rlhf-feedback-loop": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"rlhf-feedback-loop"
]
}
}
}
Pre-action gates that block AI agents from repeating known mistakes.
Webhook Ai tools for AI agents. Capabilities: validate webhook signature, log webhook event, replay
Local-first project memory and mistake-prevention guardrails for AI coding agents.
Pre-action gates that block AI agents from repeating known mistakes.
Local-first memory brain for AI coding agents: hooks capture sessions, beliefs injected per prompt.
Local design engine for AI agents: create, edit and export real, editable designs.
Persistent memory + vibe-loop engine for AI agents. Single Go binary, SQLite-backed, stdio MCP.
Shared memory for AI agents: query proven fixes, avoid known mistakes, and find skills and MCPs.
Answers built from our own checks of this server.