Skip to the page
Get started free

SpecStream for MiroThinker

SpecStream is the live web data engine for teams and agents. Set SERPER_BASE_URL and JINA_BASE_URL to SpecStream's addresses, and MiroThinker's google_search and scrape_and_extract_info run on SpecStream, in the reply shapes its code already reads.

Read the guide

What you get

Four lines in .env
SERPER_BASE_URL, SERPER_API_KEY, JINA_BASE_URL and JINA_API_KEY. Every preset in conf/agent picks them up.
Pages on the same key
Each page scrape_and_extract_info reads is one Extract API page, and a page with no text is not charged.
Fast tier price
Each search is one fast Search API call of up to 10 results, at $1 per 1,000.

Set it up

  1. Get a SpecStream key on the Search API screen of your workspace.
  2. In apps/miroflow-agent/.env, set SERPER_BASE_URL to https://api.specstream.ai/serper and JINA_BASE_URL to https://api.specstream.ai/jina, with your key in both key lines.
  3. Run main.py with your preset and look for the calls in your request log.

The full setup guide has every step, with what to do if something doesn’t arrive.

Also in Agent frameworks & builders

The same live web data, in the other tools of this kind.

Live web data, in MiroThinker.

Ask in your own words for companies, places, people, filings or anything else the web lists.

Read the guideTalk to a human