如何讓開源 AI 智能體 Scout 處理瀏覽器例行操作

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).

Step 1: Install Scout

You need Node 22 or later. On the cloud there is no browser to install.

npm i @outcrawl/scout

Step 2: Add your keys

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

Step 3: Give it a task

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.

Watch out: set caps first

Limit a run with caps on steps, duration and budget. Reaching a limit is a normal ending, with everything found so far.

Source

• Project: github.com/outcrawlai/scout