Research Paper Intelligence (OpenAlex + AI)

Turn any research topic into a ranked reading list and a research-landscape briefing. Give it a topic — "large language models", "solid-state batteries", "CRISPR gene editing" — and the Actor searches the entire OpenAlex scholarly database for the top papers, pulls their citation counts, authors, institutions and venues, and uses OpenAI to summarise the state of the field: the key themes, the seminal papers, and where the research is heading.

You bring the question. It hands back the literature, scored and summarised.

---

The flow

1. Give a research topic        2. OpenAlex search               3. Get papers + AI landscape
   "large language models"  →      (top papers by citations   →     ranked papers · citations ·
   "CRISPR"                         or recency, no API key)          authors · venues · AI summary

1. Enter one or more topics in queries.
2. The Actor queries OpenAlex (the open index of 250M+ scholarly works) for the top papers per topic, sorted by citation count or publication date.
3. You get back one record per paper (title, year, citations, authors, institution, venue, DOI, open-access status, concepts) plus one AI landscape record per topic (key themes, seminal papers, emerging directions, leading institutions, a 2–3 sentence summary).

---

What you get per query

For every research topic, the Actor:

1. Searches OpenAlex for the top maxPapersPerQuery works matching the topic, sorted by cited_by_count (most influential) or publication_date (most recent), optionally filtered to papers published on or after fromYear.
2. Normalises each paper into a flat record: title, publication year, citation count, author list, first institution, venue, work type, open-access status, DOI, OpenAlex ID, and the top concepts.
3. Aggregates the set: total matching works, top authors by appearance, top institutions, top venues, open-access share, and a recent-vs-older year distribution.
4. Summarises the landscape with AI (OpenAI gpt-4o-mini, a fast and low-cost model), grounded strictly in the retrieved papers — it never invents citation numbers or papers:
   • landscapeSummary — 2–3 sentences on the state of research.
   • keyThemes — the dominant sub-topics in the set.
   • seminalPapers — the foundational / most-cited works, each with a one-line reason.
   • emergingDirections — where the field appears to be heading.
   • leadingInstitutions — the institutions publishing the most.

---

Three ways people use it

• R&D and competitive tech scouting — map a technology area in minutes: who the top labs and institutions are, which papers everyone cites, and what's trending. Pull structured citation data and research papers for any emerging field without manually combing through the OpenAlex API.
• Literature reviews and academia — kick-start a literature review with a ranked, de-duplicated reading list and a themes breakdown. A fast, programmatic scholarly search and a practical Semantic Scholar alternative for grabbing top works per topic.
• Competitive and biotech/pharma intelligence — track a disease area, drug modality or platform technology: leading institutions, seminal papers, publication momentum, and open-access share — intel for strategy, diligence and scouting teams.

---

Input

Field	Type	Notes
queries	array	Required. Research topics / keywords, one per line (e.g. "large language models", "CRISPR").
fromYear	integer	Optional. Only include works published in or after this year.
maxPapersPerQuery	integer	Papers to fetch and analyze per topic. Default 25 (max 200).
sortBy	string	cited_by_count (most influential) or publication_date (most recent). Default cited_by_count.
maxResults	integer	Max topics to process. Default 100.
maxConcurrency	integer	Topics processed in parallel. Default 3.
model	string	Override the OpenAI model. Default gpt-4o-mini.

Minimal input example

{
  "queries": ["large language models", "CRISPR"],
  "maxPapersPerQuery": 25,
  "sortBy": "cited_by_count"
}

---

Output example

One record per paper:

{
  "query": "large language models",
  "recordType": "paper",
  "title": "Attention Is All You Need",
  "year": 2017,
  "citedByCount": 139482,
  "authors": ["Ashish Vaswani", "Noam Shazeer", "Niki Parmar"],
  "firstInstitution": "Google (United States)",
  "venue": "Neural Information Processing Systems",
  "type": "article",
  "oaStatus": "green",
  "doi": "https://doi.org/10.48550/arxiv.1706.03762",
  "openAlexId": "https://openalex.org/W2963403868",
  "concepts": ["Computer science", "Artificial intelligence", "Transformer"]
}

Plus one landscape record per topic:

{
  "query": "large language models",
  "recordType": "landscape",
  "totalResults": 184203,
  "papersAnalyzed": 25,
  "topAuthors": [{ "name": "Yoshua Bengio", "count": 3 }],
  "topInstitutions": [{ "name": "Google (United States)", "count": 5 }],
  "topVenues": [{ "name": "Neural Information Processing Systems", "count": 4 }],
  "keyThemes": ["Transformer architectures", "Pretraining and fine-tuning", "In-context learning"],
  "seminalPapers": [
    { "title": "Attention Is All You Need", "year": 2017, "citedByCount": 139482, "why": "Introduced the Transformer, the architecture underlying modern LLMs." }
  ],
  "emergingDirections": ["Reasoning and tool use", "Efficient / small language models"],
  "landscapeSummary": "Research on large language models is dominated by Transformer-based architectures and large-scale pretraining..."
}

---

Pay-per-event pricing

This Actor uses pay-per-event billing with a single event:

Event	Charged when	Price
query-analyzed	Once per research topic searched across OpenAlex and summarized with AI.	$0.15

The Actor logs its OpenAI token usage and estimated AI cost at the end of every run, so the event price stays safely above the model cost.

---

Data source

Paper data comes from OpenAlex — a fully open, free index of the world's scholarly works (papers, authors, institutions, venues and citation counts). No API key is required. The Actor uses OpenAlex's polite pool (sends a mailto) and respects their usage guidelines. The AI layer uses OpenAI to summarise the retrieved papers.

---

Setup

The AI landscape summary calls the OpenAI API. Set the environment variable / secret OPENAI_API_KEY on the Actor. The OpenAlex search itself needs no key.

---

Use it from an AI agent (Apify MCP server)

This Actor is available through the Apify MCP server, so AI agents (Claude, ChatGPT, or anything that speaks MCP) can call it as a tool — hand it a topic and read back the top papers and the research-landscape summary — with no custom integration code.

---

Run it locally

npm install
# put your input in storage/key_value_stores/default/INPUT.json
export OPENAI_API_KEY=sk-...
apify run -p

---

Related actors

• GitHub Repo Analyzer — Analyze any GitHub repository: stars, activity, contributors and an AI health assessment.
• AI Web Extractor — Turn any URL plus a plain-English prompt into structured JSON.
• Google News Scraper — Pull news articles and headlines for any topic or query.
• SEC Filings Extractor — Extract and structure data from SEC filings.

---

Part of the No Niner toolkit — no-code web scraping, enrichment & AI data tools, all pay-per-use. Browse the full set at noniner.io.