How to Let an Open-Source AI Agent Do Your Browser Chores

An open-source project called Scout provides a browser-using AI agent that completes web tasks from plain-language instructions, reading pages, clicking, typing and scrolling until finished. On Outcrawl's cloud, Scout reached 92.5% of pages on Browser Use's 80-site benchmark, versus 81.4% for the next best, according to the project's README. The agent ships as an npm package requiring Node 22 or later, has no built-in model, and works with any service speaking the standard chat completions API.

This article was drafted with AI assistance and fact-checked against the project's README. Repeating the same website clicks eats your evening. Scout is an open-source agent that uses a real browser to finish a task for you: describe what you need in plain words, and it reads the page, clicks, types and scrolls until the job is done, then hands back the answer. On Outcrawl's cloud, runs reached 92.5% of pages on Browser Use's 80-site benchmark, scored with Browser Use's own code; the next best reached 81.4% three full runs, 7 October 2026, per the README . You need Node 22 or later. On the cloud there is no browser to install. npm i @outcrawl/scout You need an Outcrawl key for the browser free at outcrawl.ai: 1,000 credits every month, no card needed and a key for your model. Scout has no built-in model and no default; it works with any AI model service that speaks the standard chat completions API, including a model running on your own computer. export OUTCRAWL API KEY=your-outcrawl-key export SCOUT BASE URL=https://your-endpoint/v1 export SCOUT API KEY=your-model-key export SCOUT HANDS MODEL=your-model-id Write the task the way you would ask a colleague. The README's full example is a task.ts file you run with npx tsx task.ts ; see the README for the complete code. If it cannot finish, it tells you what is missing and returns what it found. Limit a run with caps on steps, duration and budget. Reaching a limit is a normal ending, with everything found so far.