Skip to content
Divinci AI SDK

Search & Scraping

Copy page
Section titled “Web search”

Backs the web-search skill in the tool loop.

Tool id Vendor Credentials Status Divinci usage
brave-web
Independent web search via Brave Search API. Privacy-focused search with web results, descriptions, and metadata.		 Brave Search BYOK available —
exa-web
AI-native web search via Exa API. Semantic web search with AI-curated results, highlights, and metadata.		 Exa BYOK available —
serper-google
Google Search results via Serper API. Fast, reliable web search with organic results, snippets, and metadata.		 Serper BYOK available —

Usage figures for this category are not collected yet — the weekly job populates them.

All three are BYOK. They differ in what they are good at: Serper proxies Google results, Brave returns an independent index, and Exa is embedding-based — it finds pages that are semantically like a description rather than pages containing your keywords. For "find me more pages like this one", Exa is the one that behaves the way you want.

Provider health is tracked, so a provider erroring or rate-limiting does not take the skill down with it.

Scraping

Section titled “Scraping”

Backs crawls, the scrape-url skill, and the web-crawl connector.

Tool id Vendor Credentials Status Divinci usage
@cloudflare/browser-rendering
Renders pages in a headless browser, capturing JavaScript-rendered content and images.		 Cloudflare Divinci-managed available —
@divinci-ai/fetch-scraper
Fetches Url, processes html and turns it into markdown. **Doesn't wait for javascript to load.**		 Divinci AI Divinci-managed available —
@divinci-ai/firecrawl
Renders pages in a headless browser with JavaScript execution. Powered by self-hosted FireCrawl.		 Divinci AI Divinci-managed available —
@mendable/firecrawl
Premium web scraping with anti-bot protection, IP rotation, and advanced features. Requires FireCrawl API key.		 mendable.ai BYOK available —

Usage figures for this category are not collected yet — the weekly job populates them.

They form a cascade, cheapest first:

  1. @divinci-ai/fetch-scraper — a plain HTTP fetch. Handles the majority of pages, costs nothing, no third party involved.
  2. Firecrawl — for pages that need rendering or that reject naive clients. Available on Divinci's account (@divinci-ai/firecrawl) or on your own key (@mendable/firecrawl).
  3. Cloudflare Browser Rendering — a real browser, for pages that only exist after JavaScript runs.

See also

Section titled “See also”