Skip to main content

​
Before you begin

Make sure you have:
  • Node.js 20+ installed.
  • API key from OnCall Web Studio (stored in ~/.openbug/config).
  • A project directory to run commands in.
  • Ability to run debug in a separate terminal.

​
Step 1: Install OpenBug

npm install -g @openbug/cli

​
Step 2: Log in

debug login <your-api-key>
  • Stores API_KEY in ~/.openbug/config.

​
Step 3 : Start the OpenBug Cli Interface

Run this in a separate terminal if you have multiple services: 
debug
  • Keeps a local registry so the AI can see all services sharing the same project id.

​
Step 5: Run your first AI-assisted session

debug npm run dev
# or
debug python app.py
# or
debug docker-compose up
What happens:
  • Command runs in a pseudo-terminal; logs stream live.
  • CLI opens a WebSocket to the backend with your API_KEY + window_id.
  • You get a split UI: logs on the left, AI chat on the right.

​
Step 6: Ask your first question

Type in the chat pane:
  • “What’s causing this error?”
  • “Why are API requests failing?”
  • “What just happened?”
The CLI sends your question plus recent logs (and cluster architecture if available). The AI may call local tools:
  • Logs: tail_logs, grep_logs, get_recent_errors, read_logs (requires logs_available: true)
  • Code: read_file, grep_search (requires code_available: true)

​
Step 7: Iterate quickly

  • Ctrl+R reset chat
  • Ctrl+D cycle views (split → full chat → full logs)
  • Tab switch focus; ↑/↓ scroll focused pane
  • Ctrl+L clear logs; Ctrl+K clear chat

​
Minimal “hello” run

​
Launch OpenBug Interface

debug login <your-api-key>
debug

​
Run Command (in new terminal)

debug node -e "console.log('hello from openbug')"
Then ask in chat: “What did this command output?”