ClawTab vs Agentlock

ClawTab puts your Mac's AI agents in your pocket. Schedule, monitor, and control Claude Code. Codex and OpenCode sessions and automated jobs from anywhere - right from your phone. Run AI coding agents on your Mac and never miss a question. When an Agent needs your input, ClawTab detects it automatically and sends you a push notification with tappable answer cards. No more babysitting terminal windows. KEY FEATURES - Remote job control: Run, pause, resume, and stop jobs on your Mac from your phone - Agent question detection: When Agent asks a question, answer it with a single tap - Live log streaming: Watch terminal output in real time - Cron scheduling: Schedule recurring jobs with standard cron expressions - Push notifications: Get notified when jobs complete or need attention - Workspace sharing: Grant colleagues access to monitor and control your agents - Run history: Review past job runs, exit codes, and logs - Secure by design: Secrets stay in your Mac's Keychain, never transmitted HOW IT WORKS Agent instances need to run in tmux to detect and control them. 1. Install the ClawTab desktop app on your Mac (free, open source) 2. Pair your phone by signing in with the same account on both Mac and iOS 3. Create jobs - shell scripts, Claude Code prompts, or folder-based agents 4. Control everything from your phone: run jobs, stream logs, answer agent questions Whether you're running a single Agent session or orchestrating dozens of AI agents across projects, ClawTab keeps you in control without being chained to your desk. Self-hosting available for teams and enterprises who want to run their own relay server.

AI agents send emails, call APIs, modify databases, and trigger payments on your behalf. Without AgentLock, they do it with direct access to your credentials — and without asking. AgentLock is a security-first approval platform that sits between your AI agents and the real world. Every action goes through you. Every credential stays encrypted. Every mistake can be undone. REAL-TIME APPROVALS When an agent wants to act, you get a push notification instantly. You see the action, the target, and the risk level — categorized as Read, Write, Financial, or Admin. Approve with Face ID or deny with a tap. Hold-to-Approve prevents accidental confirmations. Unanswered requests expire automatically. TIMELINE & UNDO Every agent action is logged in a detailed timeline — agent, action, timestamp, status, result. Like a bank statement for everything your AI does. When something goes wrong, hit Undo to reverse supported actions. Undo requires re-approval for safety. ENCRYPTED CREDENTIAL VAULT API keys, passwords, and tokens are stored with envelope encryption. Your agents never see them — not in transit, not at rest, not ever. The secure runner decrypts only at the moment of execution, in memory. No API endpoint returns a decrypted secret. POLICY ENGINE Define what gets approved automatically, what needs your confirmation, and what gets blocked entirely. Read actions pass through. Write actions require approval. Admin actions are blocked by default. Add domain allowlists for HTTP access. BUILT ON SECURITY - Ed25519 signed requests with replay protection - End-to-end encryption with per-workspace content keys - Row-level security on all database tables - Append-only audit log — no deleting, no editing - Session tokens stored in the iOS Keychain - No tracking SDKs, no ads WORKS WITH ANY AGENT AgentLock is agent-agnostic. Integrate using open SDKs for Node.js and Python. Manage agents, policies, credentials, and team members from the web dashboard at agentlock.net.