Agent

Interactive chat with the Browserless hosted agent. The LLM runs server-side and drives a browser for you.

Command: browserless agent [prompt]

The agent supports multi-turn conversations: type follow-up prompts at the > prompt. Previous prompts are recalled with the up arrow (history stored in ~/.browserless/agent_history, capped at 200 entries).

If the first prompt has login intent, the CLI prompts for username and password (masked) and prepends a credentials block so the agent can authenticate on your behalf.

When the agent pauses for input (e.g. an MFA code), it prompts you inline. Press Enter on an empty line or Ctrl-C to exit.

Flags

• --no-history Disable reading and writing prompt history.
• --json Emit the final structured result as JSON to stdout. Streaming events still render during the turn, but only the end payload is written to stdout.

Examples

Open the interactive REPL

browserless agent

Pass an initial prompt directly

browserless agent "Log in to GitHub and star browserless/browserless"