Agentic Research Directory

Tool

scrapeTx

A documented literature workspace connects topic and source selection, review, optional AI synthesis/extraction, editing and citation-linked document or slide export.

L2Research workflow (workflow level, not a quality rating) Source: Repository-documented Outcome: Not empirically evaluated here

Research applicability

Primary README describes literature search/screening, evidence-table extraction and source-linked academic drafting workflows; clinical validity is not established.

Getting started

Untested editorial guidance: read the pinned README and its linked workflow/limitations guides, inspect dependencies and data handling, then plan a small isolated public/synthetic-document trial. Check every claim against its source before reuse. No trial was executed for this review.

Maintenance

Current commit/README saved2026-10-19; ongoing support or future availability not established.

License

README states MIT for independent source code. Licence file and third-party components not audited.

Workflow & human oversight

Scoped documented L2: researchers choose topics/templates and sources, review literature, explicitly request bounded AI generation/extraction, then edit/export. This does not classify every gallery workflow or establish autonomous planning, docking validity or clinical effectiveness.

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

Approach

The Topic→Sources→Create process keeps researchers choosing templates and reviewing literature before editing outputs. Abstract-based evidence-table cells require an explicit Generate action and documented batch/concurrency bounds; broader app features are outside this scoped classification.

Limitations

Commit-pinned README documentation only; repository code, linked guides, figures, dependencies and claimed tests were not executed/audited. No independent scientific or engineering result verified. Original queued repository Zntx-space now brands its README scrapeTx. Review is limited to the documented literature workflow, not endorsement of pharmaceutical/clinical/docking claims, security isolation, every gallery workflow or provider coverage. Optional AI uses configured providers; public search availability does not establish unrestricted full-text rights. README claims tests/local verification were not repeated on this Mac.

Reproducibility

Documentation only; no model inference, provider requests, source-code execution, installation, independent tests or outcome reproduction.

Adoption requirements

README specifiesNode24 or22.13+, local SQLite fallback, optionalSupabase and user-configured AI/search integrations. Credentials/permissions and source rights are user responsibilities; no installation/provider connection performed.

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.

Submitting stores your comment text, the optional name and email, and a pseudonymised connection identifier used only for spam limiting (the raw IP address is not stored).