Agent Approve vs BotBus

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

Your AI coding agents keep working after you leave your desk. With BotBus, so can you: approve requests, answer questions, send the next instruction, or take over the computer itself, from iPhone, iPad or Apple Watch. BotBus connects Claude Code, Codex and other coding agents on your Mac, Linux or Windows computer to your phone and watch. No SSH, no VPN, no port forwarding, no account. Install BotBus on the computer, scan one QR code, and you're set. Tasks and computer controls are end-to-end encrypted. Made for long refactors, test runs and vibe coding sessions that need a quick yes every few minutes. WORKS WITH THE AGENTS YOU ALREADY USE • Built in: Claude Code, Codex, OpenCode, Hermes, Pi, OpenClaw and DeepSeek Harness • Gemini CLI, Qwen Code, Kimi CLI, goose and other ACP (Agent Client Protocol) agents • Sessions you started at your desk show up too, sorted by computer, agent and project • Agents keep their own logins, subscriptions and API keys NEVER LEAVE AN AGENT WAITING • Get notified when an agent needs approval, waits for your reply, finishes or fails; on iPhone you see the actual command • Approve or deny in one tap and answer multiple-choice questions • Auto-approve projects you trust (Claude Code and Codex); questions still come to you • When a task fails, BotBus tells you why and what to do next RUN THE WORK FROM ANYWHERE • Start a chat: pick a computer, agent and project, then type or just speak • Follow up, interrupt, or start, stop and restart an agent • Choose the model and reasoning effort for Claude Code and Codex • Run a task in its own git worktree, then merge it back in one tap • Attach photos; location data is stripped before sending • Read the conversation with formatting, code and images SEE WHAT YOUR AGENTS BUILT • Screenshots, files, videos and links come straight to your phone • Open the dev server your agent just started and try the page on your phone (Mac) • Review uncommitted changes as a line-by-line diff before you merge CONTROL YOUR COMPUTER • Files: browse projects, view and edit text files, upload photos, share files to your phone, rename, or move to Trash (never permanently deleted) • Terminal: a real shell on your computer, with tabs, extra keys (esc, ctrl, tab, arrows) and sessions that survive dropped connections • Screen: see your Mac live; tap, drag, zoom, right-click and type, with a secure field for passwords • Changes stay locked until you unlock them and re-lock after 10 idle minutes • Files and terminal on Mac, Linux and Windows; screen control on Mac BUILT FOR APPLE WATCH • After syncing from iPhone, the watch connects on its own • Approve, answer, dictate a reply, interrupt or start a task from your wrist • See every computer's pending count at a glance MANY COMPUTERS, MANY DEVICES • Pair up to 10 computers with up to 10 phones and iPads; mix Mac, Linux and Windows • Two-column layout on iPad • Remove any device at any time PRIVATE BY DESIGN • Tasks, chats, commands, files, terminal and screen are encrypted with AES-256-GCM on your devices • The key travels only in the pairing QR code and stays in your Keychain; compare the 8-digit fingerprint to verify • Our relay sees only ciphertext; pairings idle for 30 days are erased • Dev previews pass through our relay and are not end-to-end encrypted GET STARTED IN A MINUTE 1. Install BotBus on your computer from botbus.io: a menu bar app on Mac, a one-line install on Linux and Windows (no sudo or admin rights) 2. Scan the pairing QR code with this app 3. Walk away. Your agents will find you. No computer at hand? Try demo mode first. Requires iOS or iPadOS 26 and watchOS 26 or later; macOS 26, Linux (x86_64, aarch64) or Windows 10/11 on the computer. Actions need the computer online with BotBus running; available controls depend on the agent. Claude Code, Codex and other agent names are trademarks of their respective owners. BotBus is independent and not affiliated with them.