Documents and notes decision
ResearchRabbit
A capable developer can build a useful seed-based discovery and visualization tool in ~1 week, but ResearchRabbit's claimed large aggregated index and adaptive proprietary discovery algorithms are durable advantages that are costly to replicate, so rebuilding a full replacement is impractical.
Visit website↗No open-source build does this yet
Nothing published replaces this one, so a replacement starts from an empty file. Here is what it would have to cover.
What a replacement has to do
- Start with seed papers, expand related papers/authors, save to collections, and view simple relationship visualizations.
What it still won’t have
- Access to a claimed aggregated index of 310+ million papers
- Proprietary discovery algorithms that "learn from how you explore"
- Institution-scale features (LibKey integration, usage analytics, dedicated support)
- Signals alerts and other premium workflow conveniences
What remains hard
- Proprietary data
Access over 310 million academic papers
First-year cost
Keep paying
Paying is—cheaper in year one.
On cash alone, building overtakes the subscription at 3 seats.
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 research-discovery web app on Node.js + Express, Postgres (or Neo4j) and React. Core features in scope: user sign-up/login; accept a list of seed DOIs; fetch paper metadata, references, and citations from public scholarly APIs; store papers/authors and citation edges in the DB; implement a server endpoint to expand a seed by one or two hops with simple scoring; implement a React UI to add seeds, browse results, save to per-user collections, and show an interactive graph visualization (d3 or cytoscape). Out of scope: training proprietary recommendation models, indexing 300M+ documents, LibKey/institution admin features, and paid subscription management. Include error handling for API failures, rate limits, and invalid DOIs, and provide unit tests for API endpoints and integration tests for the expansion flow.
How we checked
How the score was reached
- Partly verdict base52
- 3 cited sources+3
- Price verified on pricing page+3
- 3/3 assessment runs agreed+4
- Hard moats found in the evidence-3
- Evidence score59
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 productResearchRabbit (home)
- official pricingResearchRabbit Pricing
- official docsResearchRabbit Features
Integrity checks
What held up, and what did not.
