HumanAuth: Human in the Loop

HumanAuth is a human-in-the-loop (HITL) app for AI agents. When your agent wants to do something that matters — deploy to production, send money, delete data — it pauses and asks. You get a push notification, see exactly what was requested with every parameter, and approve or deny with Face ID. Every decision mints a signed receipt bound to the exact action you saw. Your backend verifies the receipt offline and rejects anything no human approved. No receipt, no execution — so the human in the loop is something your systems can check, not just a button someone pressed. HOW IT WORKS • Your agent sends an approval request — through the MCP server (Claude Code, Cursor and other MCP clients), the n8n node, the SDK, or the HTTP API • The request reaches your phone as a push notification • You review the action and its parameters — nothing is hidden • Approve with Face ID, or deny with a reason • A cryptographically signed receipt goes back; your systems verify it independently BUILT FOR TEAMS • Join your organization with an invite code — scan the QR or type it • Approval groups with quorum policies — require 2 of 3 approvers for the big stuff • Blind ballots: other approvers' votes stay hidden until the request resolves • Full history of every request and decision • Time-boxed requests: approvals expire if nobody answers SECURITY FIRST • Biometric authentication on every approval • Ed25519-signed receipts your backend verifies offline • Signing keys are generated on your device and never leave it • Report suspicious requests in one tap HumanAuth is human-in-the-loop approval for developers and teams running AI agents in production. A free tier of 1,000 approval requests per month is included — every security feature, no card required. Request access at humanauth.ai — six lines of code on the agent side.