AI assistants and search decision
Connected Papers
A useful subset (seed-paper neighborhood graph + UI) is realistic for a small team using OpenAlex and OSS tooling, but reproducing the full commercial product (coverage, continuous updates, and UX polish) is nontrivial.
Visit website↗Open-source builds that already do this
Every project below is open source and already does this job today. Fork one, self-host it, or take the parts you need — the build prompt further down assumes an empty file, and this is the shortcut past that. Licences differ; check the one on each card before you ship.
What a replacement has to do
- Given a seed paper, fetch metadata and citations, compute a similarity/neighborhood graph (co-citation or bibliographic coupling), store graph, and render an interactive graph UI allowing node inspection and navigation.
What it still won’t have
- Continuously curated citation dataset and coverage completeness
- Polished, optimized graph-layout and UX refinements
- Historical crawl depth and updates across many publishers/databases
- Any proprietary similarity heuristics or tuned ranking used by the vendor
What remains hard
- Product polish and ongoing maintenance
First-year cost
No published price
Connected Papers does not publish a price we could read, so there is nothing to compare against. What building costs is below.
Money you would actually spend
Time you would spend
—
What you would spend
What we assumed
The verdict above measures whether you could build it. This one is only about money.
Runnable build prompt
Build a minimal Connected-Papers-like service using Python (FastAPI), Postgres, and a React frontend with D3 for graph rendering. In scope: (1) ingest paper metadata and citation lists from OpenAlex, normalize and store in Postgres; (2) compute neighborhood graphs using co-citation and bibliographic coupling for a seed paper; (3) expose REST endpoints to fetch a k-hop neighborhood and paper metadata; (4) implement a React + D3 UI to display an interactive graph and paper detail panel; (5) optional: compute embeddings using OpenAI for semantic neighbor suggestions. Out of scope: PDF retrieval, publisher paywalled content, enterprise-ready scaling, advanced ranking heuristics, and user accounts. Require error handling for API failures, rate limits, and invalid identifiers, plus unit tests for ingestion, graph construction, and API endpoints.
How we checked
How the score was reached
- Partly verdict base52
- An open-source build was found+5
- 3 cited sources+3
- Evidence score60
The base comes from the verdict. Everything under it is a check that either happened or did not, and each one is a fact frozen in this record rather than a judgement made at render time — so the same evidence always produces the same number.
How scoring works →Cited sources · 3
Every page the run actually retrieved.
- official productConnected Papers | Find and explore academic papers
- open sourceFahd-8/Research-Paper-Explorer-Using-LangChain
- open sourceJustin21523/openalex-research-rag
Integrity checks
What held up, and what did not.
