Tempest AI Assistant integrates Claude, GPT, Gemini, and self-hosted LLMs into your SSH terminal — explain commands, debug errors, generate one-liners.
The Tempest AI Assistant is an in-app chat panel that knows what's happening in your SSH session. Ask it to explain a stack trace, generate a one-liner, debug a failing systemd unit, or draft a migration script — and pipe the answer straight into the terminal. Think of it as Claude / GPT / Gemini sitting next to your shell, with full context.
The AI sees only what you give it — by default that's:
The current command output you highlight
Files you explicitly attach (drag-and-drop into the chat)
Your typed question
It does not silently scrape your terminal history, your hosts list, or your keys. You stay in control of what reaches the model.
Explain: paste an error → get a plain-English diagnosis
Generate: "give me a one-liner to find files modified in the last hour" → get the command, optionally one-click "run in terminal"
Investigate: "the disk is full, show me the biggest directories" → get a du invocation, run it, AI sees the output and follows up
Refactor: paste a Bash script → get an idiomatic rewrite, side-by-side diff
Bridge to coding agents: combine with the Use AI Agents preset on a connection to drop straight into Claude Code, Gemini CLI, Codex CLI, or OpenCode on the remote host
Tempest doesn't lock you into one provider. Configure any of:
Anthropic Claude (Sonnet, Opus, Haiku) — recommended default
OpenAI GPT-4 / GPT-5 family
Google Gemini
Self-hosted — point at any OpenAI-compatible endpoint (Ollama, vLLM, llama.cpp, your enterprise gateway)
Configure your API key once in Settings → AI and the assistant is available in every connection tab.
Tempest never proxies AI requests through our servers — they go directly from your device to the provider you configured.
When you use a self-hosted model, prompts stay entirely inside your network.
See How Tempest Protects Your Privacy for the full data-handling story.
Set the model temperature in Settings — lower for deterministic command generation, higher for creative refactoring suggestions.
The connection edit form has a Use AI Agents quick-config: pick Claude Code, Gemini CLI, Codex CLI, or OpenCode, give a working directory, and Tempest will cd <dir> && <agent> on connect — perfect for jumping straight into a coding session on a remote dev box.
See the dropdown next to the Startup Command field in any SSH host's edit form.
Kubernetes Profiles — pair the AI with kubectl for cluster troubleshooting
Tempest Monitoring — when a gauge spikes, ask the AI what to do
SSH Snippets — save AI-generated commands as reusable snippets
Last updated
