Termalin
Safe SSH for you and your AI agents
5 followers
Safe SSH for you and your AI agents
5 followers
A fast cross-platform SSH client (tabs, SFTP with a built-in editor, a database client, session recording) with a built-in MCP server: Claude Code, ChatGPT or any agent works on your servers and never holds your keys, and you decide what it may run. New: server monitoring with no agent to install, and default alerts (disk, memory, services, TLS certificates) to email, push, Telegram or Slack. Free tier, no host limits.
Free Options
Launch Team / Built With
LightfieldAI-native CRM that builds itself and does work for you
Promoted
Termalin 0.1.44 is out: Connector settings (rename, default login user, and an AI access switch per server) in the app and the web cabinet; two-factor sign-in and remote sign-out of a lost device, right in the app; snippets now sync between the app and the web; on Windows the window comes back after sleep; and the Linux AppImage runs on Ubuntu 22.04+, Debian 12+, Fedora and openSUSE. Full notes: termal.in/changelog
Update: Termalin is now in Claude's connectors directory, next to the ChatGPT app directory listing. On claude.ai open claude.ai/directory/termalin, click Connect, sign in to termal.in and approve once, and Claude can run commands, read and write files and query databases on your enrolled servers. No SSH key is pasted anywhere: servers dial out through a Connector, each call gets its own short-lived certificate, and you set per-connection access (full, an allowlist, or read-only).
Update for anyone who followed this launch: Termalin is now on the App Store, for iPhone, iPad and Apple Watch. (The "desktop only for now" line above is out of date.)
Same idea as the desktop app — install a Connector on the server once and the phone connects with no key on it at all. A real terminal too: tabs, an Esc/Ctrl/F-key row so htop and vim behave, SFTP with a built-in editor, live CPU and memory above the session.
Free: https://apps.apple.com/app/id680...
One more update: Termalin is now in the ChatGPT app directory, approved and live. Ask the chat to check disk space, tail a log, restart a service or query a database, and it runs real commands over SSH on the servers you enrolled, reporting back in the conversation.
Same model as everywhere else: a Connector on the server, a short-lived certificate per run, an OAuth grant you can revoke in one click, and every action in the audit trail.
https://chatgpt.com/plugins/plug...