Agentlock vs iVerb

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.

Your coding assistants run on your machines. Follow their work from your iPhone or iPad. iVerb is an SSH terminal and companion for remote development. Connect to your own Mac, Linux host, or WSL environment to read conversations, review code changes, reply to tasks, and use a real terminal. Works with Claude Code, Codex CLI, OpenCode, and DeepSeek Harness running on your own server. Available interactions depend on the CLI and supported transcript formats. CONVERSATIONS AND PROJECTS • Read project conversations, code diffs, and tool activity • Swipe to quote messages and add images from Photos or the clipboard • Preview remote images, text, code, and Markdown through links in project chats • Review recognized collaborating agents, work rounds, results, and separate conversations • Keep editable project to-dos on your device A TERMINAL FOR YOUR PHONE • Connect over SSH to home, office, or cloud hosts • Use Zellij or tmux sessions with terminal function keys • Customize shortcut order and preview terminal themes • CJK input, Dynamic Type, and accessibility support NOTIFICATIONS AND ACTIONS • Receive task-completion and input-needed alerts • Reply or use quick actions for compatible tasks • Optional encrypted hosted push relay access is included with Pro CONNECTIONS AND DATA • You choose the hosts; connection credentials are stored in the device Keychain • SSH encrypts transfers; conversation caches and app to-dos are stored locally • Images you choose to attach are uploaded to your configured server • iVerb does not provide a VPN or an AI model service. Use a network path or networking tools that can reach your host START FREE, UPGRADE WHEN YOU NEED MORE • Try the built-in demo without a server • iVerb Pro is a one-time purchase for additional servers and projects, fonts, Live Activity, the hosted push relay, and alternate icons • No subscriptions. Tips are optional Full remote functionality requires an accessible SSH host and the relevant command-line tools.