OpenClaw×Supabase
Add Human-in-the-Loop to OpenClaw for Supabase security.
Stop your autonomous agents from making highly destructive, hallucinated API calls to Supabase. Wrap your execution logic in LetsPing to enforce a hard pause until a human reviews the payload.
How it works
1. Intercept Supabase Logic
Instead of hitting the Supabase API directly from your OpenClaw agent, you yield the payload to LetsPing. The agent's execution thread halts completely.
2. Human Review & Patching
You get a push notification on your phone. You review the exact Supabase JSON payload the agent wanted to send. You can approve it, reject it, or patch the values directly.
3. Resume Execution
Once approved, the OpenClaw execution thread resumes, and the actual Supabase mutation is allowed to proceed using the (potentially patched) payload.
OpenClaw Example Implementation
import { LetsPing } from "@letsping/sdk";
const lp = new LetsPing();
const decision = await lp.ask({
service: "openclaw-agent",
action: "supabase_execute",
priority: "high",
payload: {
id: "123",
action: "delete"
}
});
if (decision.status === "APPROVED") {
// Actually hit the Supabase API now
await client.execute(decision.payload);
}