aihawk 0.2.0

An AI agent with a real browser. You say what you want in plain language, it goes and does it on the actual web.

_{FEATURED IN}
Business Insider · TechCrunch · Semafor · Wired · The Verge · Vanity Fair · 404 Media

First, one prerequisite for both ways

Python 3.11 or newer, on Windows (x86_64) or Linux (x86_64, arm64) - macOS is not supported, the last engine build for it was firefox-20. Then uv, because both commands below start with uvx:

curl -LsSf https://astral.sh/uv/install.sh | sh              # Linux

irm https://astral.sh/uv/install.ps1 | iex                   # Windows

Now pick one

Do you already use an AI assistant that can run tools - Claude Code, Claude Desktop, Cursor? If yes, it brings the model and you add this browser to it. If no, or if you would rather watch the work happen, run our interface instead.

claude mcp add -s user stealth -- uvx invisible-playwright-mcp

uvx aihawk ui --openrouter-key sk-or-...

Same patched Firefox behind both. AIHawk reaches it through that MCP server, over MCP, exactly as your assistant would - so anything the interface can do, your assistant can do too.

The download nobody warns you about

The browser is about a quarter of a gigabyte and it is not fetched when you install either side. It arrives on the first request that needs a page, which means your first instruction sits there doing nothing for a while, and on a slow connection the assistant may report a timeout that says nothing about a download.

Get it over with first, in a terminal where you can watch it:

uvx invisible-playwright fetch

Cached afterwards, and shared by both ways in. Per-platform sizes are in the engine's README.

Without a page, for scripts and cron

Same machinery, no interface, the answer on stdout.

uvx aihawk do "Go to example.com and tell me the top headline" --openrouter-key sk-or-...

The keyless placeholder from column 2 takes exactly these: go <url>, read [selector], click <selector>, type <selector> <text>, tab (opens a new browser tab), shot.

What it is good at

Anything that needs a browser rather than an API, and needs a person's judgement about what is on the page.

Go to <paste the URL>. One way, Milan to Lisbon, economy, one checked bag, one adult. Check every date from the 12th to the 16th of next month, one at a time, and read the cheapest fare for each day. The date field is a calendar widget, so click the days rather than typing them. If a date has no availability, say so. Do not guess a number.

It drives the page the way a person would: the pointer moves, keys are pressed, and it will refuse to set a form field from JavaScript even when that would be quicker, because a page can tell the difference.

Options

ui and do share all of these except the last row, which is ui only.

Passing --openrouter-key puts the key in your shell history, and on Linux in the process list for every user on the machine. OPENROUTER_API_KEY in the environment avoids both.

Either way it does not reach the browser process. It is removed from the environment the engine starts with, by name and by value, so a copy kept under a second name - OPENAI_API_KEY is the usual one - goes too. tests/test_key_isolation.py fails if that stops being true.

The rest of the family

Contributing

Issues and pull requests welcome on whichever of those the problem lives in. If you are not sure, open it here. See CONTRIBUTING.

When something fails on a page, say which step, what the page did, what the tool returned and which exit country you were on. "It got blocked" is not something anyone can act on.

Using it responsibly

This automates a browser under your control. Read the terms of the sites you point it at, respect their rate limits, and do not submit anything a human has not read.

License

MIT. Everything distributed before 2 September 2026 was released under AGPL-3.0 and stays under it.