Pricing
from $35.00 / 1,000 results
Researchgpt Deep Research Agent
π¬ Transform any topic into a comprehensive research report in minutes! Scrapes Wikipedia, arXiv, Semantic Scholar, news & web sources. Outputs professional JSON, HTML & PDF reports. Perfect for students, researchers, content creators & businesses. No API keys needed.
Pricing
from $35.00 / 1,000 results
Rating
0.0
(0)
Developer
Actor stats
0
Bookmarked
53
Total users
40
Monthly active users
2 months ago
Last modified
Categories
Share
π¬ ResearchGPT - Deep Research Agent
Transform any topic into a comprehensive research report in minutes, not hours.
π Apify Actor
π Python 3.11+
π License: MIT
π― What is ResearchGPT?
ResearchGPT is your AI-powered research assistant that does in 3 minutes what would take you 3+ hours manually.
Simply enter any topic, and ResearchGPT will:
β
Search across multiple engines (DuckDuckGo, Brave, Mojeek)
β
Scrape Wikipedia, arXiv, Semantic Scholar, OpenAlex, CrossRef
β
Extract the latest news articles and web content
β
Process everything with intelligent NLP analysis
β
Generate beautiful reports in JSON, HTML & PDF formats
No API keys required. No complex setup. Just results.
π Perfect For
| Use Case | How ResearchGPT Helps |
|---|---|
| π Students & Academics | Literature reviews, thesis research, citation gathering |
| βοΈ Content Creators | Blog research, fact-checking, source compilation |
| πΌ Business Analysts | Market research, competitive analysis, trend reports |
| π¬ Researchers | Cross-referencing sources, academic paper aggregation |
| π° Journalists | Background research, source verification, story development |
| π€ AI/ML Projects | Training data collection, knowledge base building |
β‘ Quick Start
1. Run on Apify (Easiest)
- Go to the ResearchGPT Actor page
- Enter your research topic
- Click Start
- Download your reports! π
2. Via API
curl-X POST "https://api.apify.com/v2/acts/YOUR_USERNAME~researchgpt-deep-research-agent/runs?token=YOUR_TOKEN"\-H"Content-Type: application/json"\-d'{"topic": "quantum computing breakthroughs 2025"}'
3. Via Apify SDK (Python)
from apify_client import ApifyClientclient = ApifyClient("YOUR_API_TOKEN")run = client.actor("YOUR_USERNAME/researchgpt-deep-research-agent").call(run_input={"topic":"artificial intelligence in healthcare"})# Get resultsfor item in client.dataset(run["defaultDatasetId"]).iterate_items():print(item)
π What You Get
Three Professional Output Formats
| Format | Best For | Contents |
|---|---|---|
| π JSON | Developers, APIs, databases | Full structured data with metadata |
| π HTML | Web publishing, sharing | Beautifully styled report with CSS |
| π PDF | Printing, presentations | Clean, professional document |
Rich Research Data
{"topic":"artificial intelligence ethics","sources":{"wikipedia":5,"academic":10,"news":5,"general":10},"processed_content":{"summary":"Comprehensive executive summary...","key_findings":["Finding 1","Finding 2","..."],"themes":["Theme 1","Theme 2","..."],"entities":["Entity 1","Entity 2","..."]}}
π§ Configuration Options
{"topic":"your research topic here","outputFormats":["json","html","pdf"],"maxSourcesPerType":10,"includeWikipedia":true,"includeAcademic":true,"includeNews":true,"includeGeneral":true,"searchProviders":["duckduckgo"],"requestTimeout":30,"maxRetries":3,"debug":false}
Parameter Reference
| Parameter | Type | Default | Description |
|---|---|---|---|
topic | string | required | π― Your research topic or question |
outputFormats | array | ["json", "html", "pdf"] | π Output formats to generate |
maxSourcesPerType | integer | 10 | π Sources per category (1-20) |
includeWikipedia | boolean | true | π Include Wikipedia articles |
includeAcademic | boolean | true | π Include academic papers |
includeNews | boolean | true | π° Include news articles |
includeGeneral | boolean | true | π Include general web content |
searchProviders | array | ["duckduckgo"] | π Search engines to use |
requestTimeout | integer | 30 | β±οΈ Request timeout (seconds) |
maxRetries | integer | 3 | π Retry attempts on failure |
proxyConfiguration | object | null | π‘οΈ Apify proxy settings |
debug | boolean | false | π Enable verbose logging |
π Data Sources
ResearchGPT taps into 6+ authoritative sources:
| Source | Type | What You Get |
|---|---|---|
| π Wikipedia | Knowledge Base | Foundational articles via MediaWiki API |
| π arXiv | Academic | Pre-print papers in physics, CS, math, and more |
| π¬ Semantic Scholar | Academic | 200M+ papers with citation analysis |
| π OpenAlex | Academic | Open catalog of scholarly works |
| π CrossRef | Academic | DOI metadata and citations |
| π° News Sources | Current Events | Latest articles via smart extraction |
| π General Web | Insights | Curated web content with readability algorithms |
π‘οΈ Production-Grade Features
Built for reliability and scale:
- β‘ Smart Caching - 5-minute TTL prevents redundant requests
- π Retry Logic - Exponential backoff with jitter
- π¦ Rate Limiting - Respects API limits automatically
- π Deduplication - MD5-based content fingerprinting
- π Connection Pooling - Efficient HTTP management
- π‘οΈ Error Handling - Graceful fallbacks, never crashes
π» Local Development
# Clone the repositorygit clone https://github.com/your-repo/researchgpt-deep-research-agentcd researchgpt-deep-research-agent# Create virtual environmentpython -m venv .venv.venv\Scripts\activate # Windowssource .venv/bin/activate # macOS/Linux# Install dependenciespip install-r requirements.txt# Run locallypython run_local.py
π Project Structure
researchgpt-deep-research-agent/βββ π .actor/β βββ actor.json # Apify configurationβββ π src/β βββ __init__.pyβ βββ main.py # π Main Apify entry pointβββ π scrapers/β βββ base_scraper.py # Base classwith retry/cachingβ βββ academic_scraper.py # arXiv, Semantic Scholar, etc.β βββ wikipedia_scraper.py # MediaWiki APIβ βββ news_scraper.py # News extractionβ βββ general_scraper.py # Web scrapingβ βββ search_engine.py # Multi-provider searchβββ π processors/β βββ content_processor.py # NLP processingβββ π output/β βββ output_generator.py # Report generationβββ π Dockerfile # Container definitionβββ π requirements.txt # Dependenciesβββ π README.md # You are here!
π Deploy to Apify
Option 1: Apify CLI (Recommended)
npminstall-g apify-cliapify loginapify push
Option 2: GitHub Integration
- Push to GitHub
- Apify Console β Create Actor β Link to GitHub
- Auto-builds on every push! π
π Performance Tips
| Tip | Impact |
|---|---|
Lower maxSourcesPerType | β‘ Faster results |
| Disable unused sources | π Skip what you don't need |
| Use single search provider | π Reduce API calls |
Enable debug mode | π Troubleshoot issues |
π€ FAQ
π Why ResearchGPT?
| Feature | ResearchGPT | Manual Research | Other Tools |
|---|---|---|---|
| β±οΈ Time | 3 minutes | 3+ hours | 30+ minutes |
| π Sources | 6+ databases | Limited | Usually 1-2 |
| π Output | JSON + HTML + PDF | Manual formatting | Single format |
| π° Cost | Pay per run | Your time = $$$$ | Subscription |
| π§ Setup | Zero | N/A | API keys needed |
π Example Topics
Get inspired! Here are some topics that work great:
"artificial intelligence ethics and regulation 2025""quantum computing practical applications""climate change solutions renewable energy""cryptocurrency DeFi market analysis""remote work productivity research""mental health digital therapeutics""gene editing CRISPR medical applications""electric vehicles battery technology"
π€ Support & Community
- π Issues: Report bugs
- π‘ Feature Requests: Suggest ideas
- π Docs: Apify Documentation
- π¬ Discord: Join Apify Community
π License
MIT License - Use it freely, commercially or personally.
