Authorization notice. Scout is dual-use. Only use it on software, sites and systems you own or have explicit permission to test.
Who it is forAn analyst, researcher or founder who needs the current top items from a public site and wants them pulled without manual browsing.
The problemReading through a site page by page to collect the same few facts is slow and easy to get wrong.
The outcomeA short, sourced answer such as the top three stories with their links and comment counts, plus a replay link to check how Scout got there.
What you need first
- Node 22 or later
- An Outcrawl key from outcrawl.ai for the cloud browser (1,000 free credits every month, no card needed)
- A model service that speaks the standard chat completions API, hosted or running on your own computer
- Optional: a local browser via `npm i playwright-core && npx playwright install chromium` if you do not use the cloud
Steps
- Run
npm i @outcrawl/scoutin your project folder. - Run
export OUTCRAWL_API_KEY=your-outcrawl-key, then setSCOUT_BASE_URL,SCOUT_API_KEYandSCOUT_HANDS_MODELto your model service. - Save the README's three-step example as
task.tsand change the task text to your research question. - Run
npx tsx task.tsand readresult.data. - Open
result.replayUrland confirm the answer matches what the page shows.
Prompt for your agent
Use the outcrawl/scout repo (TypeScript, npm package @outcrawl/scout). Build a task.ts that opens <target site URL> on Outcrawl's cloud browser and reports <the items you need> with links. Print result.data and result.replayUrl. Verify that result.status is completed and that each reported item appears on the replay.
Caveat. Scout runs model calls against the service you configure, so answer quality depends on the model you choose for the hands job.
Get 5 new use cases every morning. Free, one short email, unsubscribe anytime.
Get them freeShare: X LinkedIn Hacker News Email Copy link
Disclaimer
Deduped lists open-source repositories that belong to other people. We do not own, maintain, audit, or vouch for any of them, and a repo appearing here is not an endorsement or a safety check. The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong. Where a use case is marked "Seen in the wild", we link to public posts where someone described something similar, but we have not verified those posts and the use case itself is still our AI's own write-up. Use all of this at your own risk. Only run code, commands, or agents on systems and accounts you are authorized to use, and read the code and every command before you run it, especially anything that touches credentials, files, or the network. Nothing here is professional, security, legal, or financial advice. All trademarks and project names belong to their respective owners, and their use here does not imply affiliation. Content is provided as is, without warranties of any kind. Found a mistake, a safety problem, or something you want removed? Email [email protected] and we will look at it promptly. Full disclaimer page