Lit Review: local scholarly search and AI abstract ranking

Locally run literature-search tool whose README describes searching OpenAlex, PubMed, Semantic Scholar and Scopus, then grading abstracts against a research question with a user-selected AI provider.

Workflow level n/a Source Repository-documented Outcome Not empirically evaluated here

Evidence & verification

Source level

Repository-documented
Grounded in a maintainer repository/README. Availability, stars and forks do not establish research benefit or correctness.

Outcome verification

Not empirically evaluated here
A documented resource or intended workflow, not a demonstrated academic outcome. No empirical benefit is established by its inclusion.

Sources checked

2026-10-17 (UTC)

Primary README-only source-semantic review. Capability assertions attributed to documentation; not-evaluated describes the adopted outcome claims, not an assertion the authors never evaluated their tool.

Source-checked does not mean independently reproduced. See the Method page for how these labels are assigned.

Sources (1)

Research applicability

Locally run literature-search tool whose README describes searching OpenAlex, PubMed, Semantic Scholar and Scopus, then grading abstracts against a research question with a user-selected AI provider.

Getting started

Editorial suggestion, not executed: read the repository and INSTALL.md linked there, assess data-sharing and licence terms, then test a small known set of papers and inspect false exclusions instead of trusting relevance order as comprehensive coverage.

Maintenance

Live mutable HEAD README reviewed; no pinned release/commit or maintenance guarantee.

License

README states FSL-1.1-MIT with competing commercial-product/service restrictions and eventual MIT conversion per version; not an unrestricted-current-MIT claim. Licence file not audited.

Workflow & human oversight

Resource-level automation varies; no fixed workflow level assigned. Researchers define criteria, oversee data access and validate outputs. AI roles are not human editorial review.

Workflow level is not an evidence score; higher is not better evidence.

Approach

The documentation describes storing datasets and prompts locally while sending searches to selected databases and titles/abstracts to the selected AI company. It describes user-funded API calls with an estimated cost and a user-controlled run limit.

Limitations

README-only review; releases, installation, encryption, cost controls and retrieval/ranking quality were not tested. The README describes mandatory version checks and external transmission of searches and abstracts; this is not a fully offline or no-egress tool. Researcher judgment is needed for relevance and coverage.

Reproducibility

Source content saved and hashed; no install, execution or independent outcome experiment.

Adoption requirements

A compatible documented Windows or Mac build, scholarly database access as required, and the user's own AI provider key and budget. Review provider terms and permission to transmit abstracts; local storage does not mean offline inference.

Comments

No comments yet.

Add a comment

Comments are held for moderation before appearing. Critical or corrective comments are welcome — especially evidence that an entry overstates what has been verified.