# Agent Approve — Observe & control AI agents > Mobile app for observing and controlling AI agent activity with policy enforcement. (iPhone/iPad app by Agent Approve LLC.) - Source: https://appshunter.io/ios/app/agent-approve/id6756645367 (this page in markdown: same URL + `.md`) - Developer: [Agent Approve LLC](https://appshunter.io/developer/1862073667) - Category: Developer Tools, Productivity - Price: Free - Rating: 4.00/5 from 2 App Store ratings · 3 written reviews indexed - Age rating: 4+ - Requires: iOS 16.0 · 20 MB - Languages: American English - Released: 2026-07-04 - Data updated: 2026-08-27 - Monetization: free with in-app purchases - User reviews in markdown: https://appshunter.io/ios/app/agent-approve/id6756645367/reviews.md ## What is Agent Approve? You're racing to ship. If your agents are idle, you're not gonna make it. Every pending approval is wasted time. So you're chained to your laptop, all day and night. This isn't the AI future we were promised – go out and enjoy life. Agent Approve brings observability & control to your wrist: track AI agent activity, protect yourself with policy, and approve with a tap, wherever life takes you. HOW IT WORKS Agent Approve uses the hooks already built into your agent and coding tools, so you don't have to change how you work. When an agent goes to run a command or call a tool, it's encrypted on your machine and sent through our cloud relay, where it's evaluated against policy. Compound commands are separated to catch hidden destructive commands. Matches to your deny list or allow list are handled immediately. Those that need review are pushed to your iPhone or Apple Watch. When it reaches you, you see the full command, tap approve or deny, and can add it to your allow or deny list so you're never asked again. Everything is end-to-end encrypted: you own your data and keys. WHY IT MATTERS Some commands have no undo. Agents have wiped production databases, deleted home directories, and force-pushed away weeks of work – usually in seconds, while no one was watching. And the agents you can't see are the ones that bite: a scheduled task that drifts, a retry loop that burns thousands in tokens overnight, or a helpful agent sharing secrets with a bad actor. Agent Approve ships with a Restrictive policy that blocks 250+ destructive commands out of the box, a Permissive policy that auto-approves common safe commands, and you can always build your own. EVERYTHING YOU NEED TO STAY IN CONTROL • Approve from your wrist or phone – one tap, wherever you are. • Centralized policy – allow, deny, or ask, with 250+ destructive patterns blocked out of the box. • Compound-command parsing – catches the dangerous command hidden inside a scripted command sequence. • Full observability – every command, tool call, and action in one live feed, including subagents and agent profiles (each Hermes profile shows up as its own agent). • Readable at a glance – commands, plans, and tool payloads render as formatted markdown and JSON, not a wall of raw text. • Interactive Q&A – review the agent's plan, and answer questions from your phone (limited support). • Completion alerts + follow-ups – know the moment an agent finishes, then send its next move by voice or a quick reply. • Privacy tiers & retention – choose how much of each command is stored (tool name, short summary, or full content) and how long to keep it. • End-to-end encryption – you own your data and your keys, with optional key rotation for forward secrecy. WORKS WITH EVERY AGENT YOU USE Agent Approve runs on the hooks already native to your coding tools. Where there isn't one, we ship a plugin. 14 agents and counting, including: Antigravity, Claude Code, Codex, Cursor, Hermes, OpenClaw, OpenCode, OpenHands, Pi, VS Code Copilot, and Windsurf. It's the only cross-platform AI agent observability and control layer on your wrist. TRY BEFORE YOU COMMIT Tap "Try Demo" on the welcome screen to explore the full approval flow with sample data – no account or agent required. To try with your own agents, run 'npx agentapprove' on your computer. It installs the hooks or plugins for the agents you select, and walks you through pairing – scan the QR code, hit Subscribe, and start a 7-day free trial before you're charged. — Agent Approve requires an auto-renewable subscription after a 7-day free trial. • Agent Approve Monthly – $14.99/month • Payment is charged to your Apple ID at confirmation of purchase. • Subscription auto-renews unless turned off at least 24 hours before the end of the period. • Manage or cancel anytime in Settings → Apple ID → Subscriptions. • Privacy Policy: https://www.agentapprove.com/privacy • Terms of Use: https://www.agentapprove.com/terms ## Key features - Approve/deny commands from wrist or phone - Centralized policy management - Compound command parsing - Full command observability - Readable command rendering - End-to-end encryption ## Recent user reviews (3 of 3) All indexed reviews: https://appshunter.io/ios/app/agent-approve/id6756645367/reviews.md ### 1/5 — Unnecessary *2026-07-27* See title ### 3/5 — Too expensive for what it offers *2026-07-14* $15 a month is nearly the cost of the models themselves, or a netflix subscription. This is useful, but definitely not worth that. I found the installation impressively easy, but didn’t care for all the “awards” that kept popping up. **Developer response:** Thanks for the feedback, glad the install was smooth. Point taken on the award popups, they'll be quieter in the next release and I'm adding an option to turn them off. You're right that with only an agent or two the price is hard to justify. I'm reworking pricing now with tiers based on agents/usage. If you're open to giving it another look, email me at support@agentapprove.com and I'll set you up with a discount. ### 5/5 — Epic installation and performance *2026-07-04* i’m a Cursor user on Linux using WSL and I was extraordinarily impressed to see how quickly the installation first detected my cursor instance and then second of all just instantly started working. I instructed cursor to build a complex script, walked away and within a few minutes I was asked if the agent could proceed past a roadblock I hit yes, and it just instantly started working. No more delays in my agents. I am so incredibly happy. ## Frequently asked questions about Agent Approve ### What is Agent Approve? Agent Approve is a mobile application designed to provide users with observability and control over their AI agents. It allows you to track AI agent activity, enforce policies, and approve or deny commands directly from your iPhone or Apple Watch. ### How does Agent Approve work? The app integrates with your existing coding tools and agents. When an agent prepares to execute a command, it's sent through a secure relay for policy evaluation. Approved commands are pushed to your device for review and approval. ### What kind of policies does Agent Approve offer? Agent Approve ships with a Restrictive policy that blocks over 250 destructive commands by default. It also includes a Permissive policy for auto-approving safe commands, and you can create your own custom policies. ### Can I approve commands from my Apple Watch? Yes, Agent Approve is designed for on-the-go control. You can approve or deny commands with a single tap directly from your Apple Watch, making it convenient to stay in control wherever you are. ### Is my data secure with Agent Approve? Yes, Agent Approve uses end-to-end encryption for all data transmission. You retain ownership of your data and keys, with optional key rotation for enhanced forward secrecy. ### What AI agents are compatible with Agent Approve? Agent Approve works with a growing list of 14 agents and counting, including popular tools like Antigravity, Claude Code, Codex, Cursor, and VS Code. It utilizes native hooks or provides plugins where necessary. ### Does Agent Approve have ads? No, Agent Approve does not contain advertisements. The application is free to download and use, with optional in-app purchases for enhanced features or services. ### What is the rating for Agent Approve? Agent Approve has received a high rating of 5.0 stars based on one user review, indicating strong user satisfaction with its functionality and performance. ## Version history (last 2 releases) ### 0.8 — 2026-08-27 In response to user feedback, this update focuses on smarter policies, better control over notifications, and an improved iPad experience. POLICIES • Redesigned Policy screen lets you quickly change policy configuration • Change any policy's default behavior: Ask User, Allow by Default, Deny by Default, Allow All, Deny All • Human approval timeout option: auto-approve after a veto window (30 secs - 5 mins) • Get the latest default policies and Allow/Deny list contents with Get Policy Updates • Guarded policy: Allows all unless it matches destructive commands on the deny list AGENTS • Turn Voice Follow-up on or off per agent and per profile • Consistent icons, colors, and stats across every screen BADGES • Multiple badges now celebrate as a single "1 of N" flow • Prefer quiet? Turn off badge celebrations in Settings and earn them silently iPAD • A number of sheets and forms now use the full screen • Dark mode rendering now matches iPhone RELIABILITY • Expired approval requests now clear automatically on iPhone and Apple Watch • Fixed approval cards showing "No command provided" after a push notification • Trial and subscription reminders so agents never stop working unexpectedly ### 0.7 — 2026-07-04 No release notes. ## Related topics [agent approve](https://appshunter.io/ios/topics/agent-approve) --- *Data collected daily from the US App Store and indexed by [AppsHunter](https://appshunter.io/). User reviews are verbatim App Store reviews. Ratings, prices and chart positions refresh continuously; this snapshot is from 2026-08-27.*