Pushary

en inglés Pushary is human-in-the-loop for AI agents. When an agent needs a person to approve, deny, or reply, decisions.ask blocks on a real decision made on a phone, fail-closed and written to a durable ledger, and enroll(externalId) connects your own end-user's phone with one keyless tap. For your own agents it is the control panel: one permission policy across Claude Code, Codex, Cursor, and Hermes, approvals from your phone, and one immutable cross-agent audit trail.