Documents and notes decision

Litmaps

A small-team DIY can reproduce a usable seed-search + visualization + alerts workflow using public bibliographic APIs and open-source libs, but Litmaps' large proprietary index, production-scale infra, and brand reach are durable advantages you won't match; keep paying if you need coverage/scale.

Visit website
Subscription$10/month ✓ verified
Initial build80 hours
Monthly upkeep8 hours + $50
Evidence3/3 runs agree

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

  • Ingest citation metadata, index citation graph, seed-based search, render interactive citation graph, monitor for new papers and send alerts, sync/import bibliographic library (Zotero).

What it still won’t have

  • Proprietary indexed catalogue (270+ million papers) and its coverage/quality
  • Scale and reliability of production search/index infrastructure
  • Built-in Zotero one-click sync and polished UI refinements
  • Institutional/team licensing and enterprise support

What remains hard

  • Proprietary dataSearch for articles in our catalogue of 270+ million papers.
  • Brand trustUsed by 350,000+ researchers worldwide
Read the build prompt

First-year cost

Keep paying

Paying ischeaper in year one.

On cash alone, building overtakes the subscription at 6 seats.

Paid seatsseats

Money you would actually spend

Keep paying

Subscription price × seats × 12

Build it

AI build APIs + hosting

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

Not run yet
Build a minimal self-hosted Literature-Map service using PostgreSQL + Neo4j (for citation graph), a Node.js/Express backend, and a React frontend with Cytoscape.js for graph visualization. Core features in scope: (1) ingest metadata and citation edges from OpenAlex/Semantic Scholar for a focused subgraph, (2) seed-paper search returning nearby citation graph and ranked results, (3) interactive map view with node detail and basic annotations, (4) save/load maps per user with simple JWT auth, (5) scheduled monitoring that emails users when new papers match saved maps, and (6) optional Zotero import via OAuth. Out of scope: building a 270M-paper global index, enterprise billing/SSO, advanced relevance ML models, and mobile apps. Include error handling, retries for API harvests, rate-limit backoff, and unit/integration tests for ingestion, search, and alerting.
How we checked4 sources · 3/3 runs agreed · evidence score 64

How the score was reached

  • Partly verdict base52
  • An open-source build was found+5
  • 4 cited sources+3
  • Price verified on pricing page+3
  • 3/3 assessment runs agreed+4
  • Hard moats found in the evidence-3
  • Evidence score64

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 · 4

Every page the run actually retrieved.

Integrity checks

What held up, and what did not.

✓ Price read off the page✓ 3 independent runs, one answer✓ Citations limited to fetched pages! 2 moats quoted from the page