pushary@1.9.207
Human-in-the-loop (HITL) for AI agents: ask a person for approvals or answers by push notification. One command connects Claude Code, Codex, Cursor, Gemini CLI and more.
AI security review
scanned · by lpm-firewall-aiThe flagged execution, persistence, and network behavior is consistent with an AI-agent approval and phone-control tool, and setup is exposed as an explicit CLI command rather than an install hook. Inspected credential-bearing requests go to Pushary’s own API, and remote Claude control is opt-in or limited to an interactive wrapper session.