# OpenCLI Agent Pack: browser-use

Use this when an AI agent needs to work with `browser-use`.

## What this CLI is for
Browser automation, persistent sessions, and agent workflows from the terminal. Built by browser-use.

Best for: browser automation, persistent sessions, and agent workflows from the terminal.

## Agent readiness
Human-first CLI (35/100)
- Supports non-interactive/scripted use.

## Install
```sh
pipx install browser-use
```

## Verify before real work
```sh
browser-use --version
```
Expected signal: browser-use responds locally and is ready for the first real command.

## Safe starting commands
```sh
browser-use --version
```

```sh
browser-use open https://opencli.co
```

## Guardrails for agents
- Prefer small commands and ask the agent to summarize plain text output.
- Network access is required; avoid leaking secrets in logs.
- Require confirmation before apply, delete, deploy, transfer, merge, or write actions.

## Suggested agent instruction
You may use browser-use (`browser-use`) for browser automation, persistent sessions, and agent workflows from the terminal.. First install it if missing, then run the verify command. Start with read-only or inspection commands. Summarize what you found before changing anything. Ask for confirmation before commands that mutate remote state, spend money, deploy, delete data, merge code, or expose secrets.

Source: OpenCLI