FireCrawl StrawberryHand the FireCrawl crawl datas to a companion
Hand a companion the outcome. It reads the FireCrawl crawl datas, does the 7-operation version of the job, and stops for your click on anything that changes a record.
Open the crawl data. Check it against something else. Write the change. Move to the next one. That is the FireCrawl afternoon nobody can hand off, and a companion does the whole pass and gives you back the batch, with nothing changed until you say so.
What it can do is exactly what FireCrawl exposes to an account you authorise and nothing beyond it: 7 operations, 7 reads and no writes. In practice that means it can search, scrape page and map URL, and work across the crawl datas, crawl urls and extract datas.
The FireCrawl API stops at FireCrawl. A companion does not. The same run opens the customer's website, the supplier portal, the internal tool somebody built in 2019, because it is working the browser you are already signed into rather than calling in from outside it.
Can it search on its own?
All 7 operations read.
Your account, not a guess at it: a companion can search, scrape page and map URL, and the full list below is the whole list, with nothing inferred from FireCrawl's documentation.
The crawl datas are what most of this inventory is about, alongside the crawl urls. A companion can hold all 7 of these operations and forty open tabs in the same pass, which is how an afternoon of FireCrawl admin becomes a queue you review.
- Search
- Scrape Page
- Map URL
- Get Extract Data
- Get Crawl Data
- Extract Data
- Crawl URL
Nothing writes back. So what moves the crawl datas?
Through the screens you already use.
FireCrawl exposes no write operation to a connected account, so a companion drives FireCrawl in the session you are already signed into instead, filling the same forms you would to move a crawl data, and anything consequential stops for an approval card before it happens.
That is the ordinary case rather than the exception. Most of what a crawl data in FireCrawl touches has no API pointed at it, and a companion is useful precisely because it does not need one.
Can it search every morning by itself?
Yes.
Saved as a routine, the FireCrawl crawl datas pass runs at the hour you pick: the Monday sweep, the overnight refresh, the Friday check. Keep Awake holds the machine awake for the length of a run, so a scheduled pass finishes with the lid closed.
The product and engineering playbook catalogues the other recurring shapes of the site work, the FireCrawl crawl datas sweep among them, and finished runs are published at real runs.
Experience Strawberry for free
DownloadTrusted by fast-growing companies worldwide
Frequently asked questions
Strawberry is free to download and includes AI credits to start. Paid plans begin at $20/month. See pricing. · Reviewed · Canonical facts for AI agents