AFK vs Agentlock

Move your AI coding sessions from desktop to phone without SSH, VPNs, or exposing your computer to the internet. AFK streams your live terminal session to your iPhone over outbound WebSockets, so it works in most restricted networks where inbound SSH or remote desktop setups are blocked. Use Claude Code, OpenAI Codex, Gemini CLI, OpenCode, or any terminal command on your computer. When you step away, AFK keeps the same session in your pocket so you can monitor progress, approve prompts, type replies, and steer the work from anywhere. Try AFK instantly with the free live demo, or connect your own machine in minutes. WHY DEVELOPERS USE AFK AI coding agents can work for hours, but they still need you for tool approvals, error decisions, direction changes, and quick replies. AFK keeps your agent moving without keeping you at your desk. - Start work on desktop and continue from iPhone - Watch terminal sessions live with GPU-accelerated rendering - Approve prompts and tool calls remotely - Type commands or use precision voice input - Get mobile alerts when your agent needs attention - Works without SSH, VPNs, port forwarding, or remote desktop HOW IT WORKS 1. Install the AFK CLI on your machine 2. Run your agent or terminal command with AFK 3. Open the iPhone app 4. Monitor, approve, and respond from anywhere AFK uses outbound WebSocket streaming, so your computer does not need to accept inbound connections. No router changes. No public ports. No messy network setup. BUILT FOR AI CODING WORKFLOWS AFK works with any terminal command, and is designed for modern AI-assisted development: - Claude Code - OpenAI Codex - Gemini CLI - OpenCode - Custom scripts and long-running CLI tools REAL-TIME TERMINAL STREAMING - Low-latency WebSocket streaming - GPU-accelerated terminal rendering with Metal - Full bidirectional I/O - Automatic terminal resize - Push notifications for agent activity - Smooth terminal experience on mobile SECURE BY DESIGN Your terminal data is end-to-end encrypted. The backend acts as a relay and cannot read your session contents. - End-to-end encrypted terminal streams - X25519 key exchange - AES-256-GCM encryption - TLS 1.3 for transport security FREE TO START Free: - 2 concurrent sessions - End-to-end encryption - 20 voice commands per month Pro: - Unlimited sessions - Unlimited precision voice input - Push notifications when your AI agent needs input - Priority support Start with a 7-day free Pro trial. Refer 3 friends to earn a free month of Pro. AFK is built by Thaker Innovations. Website: https://getafk.dev Support: https://getafk.dev/support Privacy Policy: https://getafk.dev/legal/privacy Terms of Service: https://getafk.dev/legal/terms

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.