A second pair of eyes that only reads.
With your own Claude API key, every container and the host terminal get a Claude tab. It reads logs, events, stats and inspect data and suggests a fix. It never acts on its own.
Fig. — The Claude tab next to the host terminal, ready for a question.
What you can do
On every container
And on the host terminal, where it reads what the terminal shows.
Reads, never writes
Logs, events, stats, inspect data and compose projects. That is all it sees.
Secrets masked
Passwords and tokens are masked before anything is sent.
You press the button
A proposed action, such as a restart, runs only when you click it.
Commands wait for Enter
A proposed command goes into the terminal prompt. You decide whether to run it.
Pick the model
Opus 5 by default for a stubborn problem, Sonnet 5 or Haiku 4.5 for faster, cheaper answers.
Your key, stored safely
Encrypted on your computer and readable only by your user account.
Your own bill
Each question costs a little API usage, billed to your own Anthropic account.
From the palette
Ask Claude straight from Ctrl+K, without opening a tab first.
Setup
Paste a key, pick a model, done.
Open Settings → Claude and paste an API key from the Claude Console. Leave it empty and the Claude tabs stay out of the way.
All features