Pricing

from $15.00 / 1,000 answered questions

Try for free

Go to Apify Store

Research Agent – Web Search API for RAG & AI, Cited Sources

Try for free

LLM web search and web research for AI agents and RAG: ask a question, get cited passages (not a written answer) with source URL, date and evidence level from Google web and news, EU and German law, Wikipedia, open-access papers, Stack Overflow and GitHub. Facts cross-checked, old pages flagged.

Pricing

from $15.00 / 1,000 answered questions

Rating

0.0

(0)

Developer

Perceptron Data

Actor stats

Bookmarked

Total users

Monthly active users

4 days ago

Last modified

Categories

Agents

Developer tools

query

Optional

Question

status

Optional

found / partial (Google did not answer, not charged) / no_relevant_text / no_sources / not_readable / skipped (time or cost limit) / error (internal, not charged)

reason

Optional

Why nothing was found (empty when found)

context

Optional

Ready-to-paste context for an LLM: numbered sources with URL and date, then their passages. Cite as [n].

contextTokens

Optional

Approximate tokens of the selected passages

passages

Optional

Selected passages: rank, citation number, text, heading, url, title, site, publishedAt, sourceType, score, tokens

sources

Optional

Every source considered: citation number (if used), url, title, site, publishedAt, sourceType, engine, rank, read, reason if not read

coverage

Optional

Per source type: status and number of results; candidates, read, failed, passages scored

warnings

Optional

Sources that failed for this question

language

Optional

Language code used

checkedAt

Optional

Time of the research (UTC)

durationSeconds

Optional

Seconds for this question

schemaVersion

Optional

Output schema version

rank

Optional

Passage rank (passage mode)

citation

Optional

Source number (passage mode)

text

Optional

Passage text (passage mode)

heading

Optional

Section heading (passage mode)

url

Optional

Source URL (passage mode)

title

Optional

Source title (passage mode)

site

Optional

Site (passage mode)

publishedAt

Optional

Publication date (passage mode)

sourceType

Optional

web, news, law, wikipedia, science, discussion, code or given (passage mode)

score

Optional

Relevance score (passage mode)

tokens

Optional

Approximate tokens (passage mode)

evidence

Optional

Evidence levels of the cited sources and the strongest level

agreement

Optional

Facts (numbers, amounts, dates) compared across independent sites: confirmed, single-source, conflicts

freshness

Optional

Age of the cited sources, notes and change signals (amended, repealed, replaced …)

Optional

Stable passage ID for vector-database upserts (passage mode)

evidenceLevel

Optional

official, academic, preprint, institution, reference, news, documentation, community or commercial (passage mode)

updatedAt

Optional

Last edit of the source (Wikipedia revision, GitHub push) — not its publication date (passage mode)

Web Fetch

apify/web-fetch

Download any web page by URL and convert it to clean Markdown, plain text, HTML, and other formats. Automatically renders JavaScript and works around bot blocking. The Actor provides a real-time API for quick response times.

Apify

45K

5.0

(4)

Impressum & Imprint Scraper – Company Data, VAT Number & ID

perceptr0n/imprint-impressum-website-contact-scraper

Website domains – or a trade and a city, e.g. dentists in Graz – in, one company record per site out from the imprint (Impressum, legal notice): company name, managing directors (opt-in), address, register number, VAT number (VAT ID) checked in EU VIES, email, phone. Germany, Austria, Switzerland.

Perceptron Data

AI Company Research Agent

constant_quadruped/ai-company-research-agent

Get comprehensive company intelligence in seconds. Research any company for tech stack, key employees, competitors, news sentiment & AI insights.

RAG Web Browser — Web Content for AI & LLMs

nexgendata/rag-web-browser

Web browser for RAG pipelines and AI agents. Searches DuckDuckGo, scrapes the top results, returns clean Markdown with citation URLs. Feed your LLM with real-time web data. Works with Claude, GPT, LangChain, CrewAI. No API key needed.

NexGenData

Agent Skills Scraper

parsebird/agent-skills-scraper

Extract deep metadata from skills.sh, the open agent skills directory. Scrape weekly installs, GitHub stars, security audits, agent adoption breakdown, SKILL.md content, and more from every skill listing.

ParseBird

Arbeitsagentur Jobs – German Jobs, Bundesagentur Jobbörse

perceptr0n/arbeitsagentur-jobs-scraper

Keyword and place in, one row per job listing out from the Jobbörse of the Bundesagentur für Arbeit (Arbeitsagentur): title, employer, full text, salary range, home-office flag, location with coordinates, publish date. German jobs via the Jobsuche API, no browser; schedule it to see who is hiring.

Perceptron Data

Google Keyword Research Tool

powerai/google-keyword-research-tool

Scrape keyword research data including search volume, CPC, and competition metrics from Google.

PowerAI

Brave Search MCP Server - Super-Fast Web, Image & AI Answers

clearpath/brave-search-mcp

Search web, images, and videos through AI agents via MCP. Get AI answers with source references. 4 tools: web search with discussions/news/FAQ/locations, image search (200 results), video search (60 results), and AI answers. No Brave API key needed. Works with Claude, ChatGPT, any MCP client.

ClearPath

News Aggregator AI Agent

harvestlabs/news-aggregator-ai-agent

Scrapes and aggregates top news stories based on a given search query. It uses AI to extract the core topic from the query, fetch relevant articles, and compile a well-structured newsletter summarizing the most important stories.

harvest-org

168

4.6

(3)

Firecrawl Agent - Web Crawler

alizarin_refrigerator-owner/firecrawl-agent

Advanced web crawling with Firecrawl. Extract clean markdown, handle JavaScript sites & manage large-scale crawls with built-in rate limiting & error handling.