AI assistants and search decision
Elicit
A small team can build a narrow research-search+reporting workflow using public indexes and LLMs, but Elicit's proprietary indexed corpus, validated systematic-review tooling, and enterprise features are durable advantages that are costly to reproduce.
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.
Code Elicit publishes itself
Not a way out of the subscription — these are the vendor’s own repositories. Worth a look for how they build, and for anything you would have to integrate with.
What a replacement has to do
- User submits a research question → semantic search over academic corpus → retrieve top papers and metadata → extract passages and citations → run LLM summarization to produce a cited report → present interactive report and allow exports
What it still won’t have
- Access to Elicit's indexed proprietary corpus and integrated search over 138M+ papers
- Validated accuracy benchmarks and PRISMA-grade systematic-review tooling
- Enterprise features: SSO/SAML, admin panels, seat management, and high-usage quotas
- Live collaboration, scale optimizations, and prebuilt export templates
What remains hard
- Proprietary data
Search over 138 million academic papers and 545,000 clinical trials, with more data sources coming soon.
- Brand trust
TRUSTED BY OVER 5 MILLION RESEARCHERS, INCLUDING AT
First-year cost
Keep paying
Paying is—cheaper in year one.
On cash alone, building overtakes the subscription at 6 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 Elicit-style research assistant using: Next.js frontend, FastAPI backend, PostgreSQL for metadata, Weaviate (or Pinecone) for embeddings, and OpenAI (or compatible) for summarization. Scope: implement semantic search over an indexed set of public papers (ingest abstracts via Semantic Scholar API or arXiv), store paper metadata and PDFs, extract sentence-level citations, implement an LLM pipeline that generates a structured, cited research report, provide a web UI to query, display top papers, and export PDF/CSV. Out of scope: reproducing Elicit's full proprietary corpus, enterprise SSO, PRISMA-grade automation, and large-scale collaboration. Include error handling for failed fetches and LLM timeouts, basic unit tests for ingestion, search, and report generation, and a README with deployment steps (Docker Compose).
How we checked
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.
- official productElicit homepage
- official pricingElicit pricing
- open sourcedzhng/deep-research
- open sourcearc53/DocsGPT
Integrity checks
What held up, and what did not.
