Hyreflow Native
Pull open roles off any careers page, with no job board subscription.
Our own scrapers read open roles straight from company career pages, LinkedIn, Indeed and the German federal board. No vendor account and no key, because we built it. Launching a scrape is free; you pay per role that comes back.
A sourcing and signal front end. Roles come back, and every one of them names a company worth contacting.
things you can ask for
- “Every engineering role this company is hiring for, right now”
- “Recruiter openings in Hamburg this week”
- “Pull the last week of postings from these ten companies and score them with Hyreflow Agent”
- “Scrape their careers page, then find the hiring manager via Apollo”
works well with Hyreflow Native
- Hyreflow Agent
pull the real requirements out of every scraped ad
- Apollo
a job ad names a company, this names the person
- TheirStack
a broader posting index when you have no company list yet
- JobAdder
file the scraped roles as live jobs on the desk
Ask for the outcome and your agent composes the run itself. Or start from a skill, a whole pipeline it already knows end to end.
browse all skills →What your agent reads before it touches Hyreflow Native
Every tool ships with a written playbook, and the agent loads it before the first call. Auth, rate limits, what each call costs, which actions need your approval, and the mistakes worth avoiding. It is the difference between an agent that knows the tool and one that guesses at it.
Read the Hyreflow Native docs →Show the raw playbookwritten for the agent
HOW in lib/hyreflow_native.py.
Kind: Hyreflow Native — read this first
- First-party capability, no external vendor. Runs on Hyreflow infrastructure.
- No BYOK, no API key. You never hold a key, so no separate scraper subscription is needed; every call is metered in Hyreflow credits. Provider-precedence waterfalls don't apply.
- Two shapes, two billing models. Job scrapes are async and pay-on-match: launching is free and you're charged per job returned on retrieval, so an empty or still-running result costs nothing. Post feeds are a single call charged per request — one page of up to 50 posts, whatever the page holds.
Job scrapes — the two-call (async) flow
A scrape takes a few minutes.
- Launch with
scrape_*→{request_id, status: "QUEUED"}. Free. - Poll with the matching
get_*, passing thatrequest_id→QUEUED→RUNNING→COMPLETED. OnCOMPLETED,result.jobsholds the scraped roles. Poll every ~10s untilCOMPLETEDorFAILED— re-polls dedup per job, so a tighter loop costs nothing; the terminal poll bills the same page whenever it lands.
career_pages (a company's own careers site) · linkedin_jobs · indeed_jobs · arbeitsagentur_jobs
(the German federal employment board).
Post feeds — one call
profile_posts (a person, from linkedin.com/in/<username>) · company_posts (a company page, from
linkedin.com/company/<username>). One call returns up to 50 posts newest-first with full text, engagement
counts, the post URL, when it was posted and any companies tagged. Page back with the next_start each
response returns.
Cost
Job scrapes: 0.05 credits per job returned, charged on retrieval — not per call. You are charged for the
jobs a poll actually delivers, so size the request to the ask: rows on the launch bounds what the scraper
collects (Indeed defaults to 25), limit on the poll bounds what one page returns (10), and advancing to a
further page bills that page's jobs. Post feeds: 0.2 credits per
request (a page of up to 50 posts), charged whether or not the handle resolves.
Handoff
The sourcing front end for a hiring-signal pipeline: scrape open roles → identify the hiring company → enrich the decision-maker → sequence. Post feeds add the timing layer — read what an account has been posting to open on a launch, a funding round or a hiring push rather than on nothing.