Agentic Research Directory

Tool

Papyrus: embedding-backed research-paper corpus search

Source-documented research assistant with a Rust CLI for ingesting paper lists or local PDF/Markdown collections and querying the corpus through embeddings, alongside a Qt/C++ paper-manager GUI.

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

Research applicability

Intended to help researchers organize and find material inside a paper corpus; search results remain evidence candidates requiring source inspection.

Getting started

Editorial suggestion, not executed: inspect current CLI/configuration sources and reconcile GUI build notes with the maintainer. Start with rights-cleared non-sensitive local documents and compare returned snippets to originals; do not assume the download path is lawful or reliable.

Maintenance

Snapshot source review only; no ongoing maintenance guarantee.

License

License terms not audited; inspect applicable licenses and third-party terms before reuse.

Workflow & human oversight

Resource-level automation unspecified. Researchers select the corpus and embedding configuration, control data transfer, and verify retrieved material and any subsequent claims.

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

Approach

CLI source defines ingestion, embedding-client setup, vector-store access and natural-language queries, with optional section filtering and source snippets in displayed results.

Limitations

Partial source/documentation review, not a build, security audit or runtime test. GUI README mixes a Qt5 build heading with Qt6 dependencies; setup may need maintainer clarification. No retrieval-quality benchmark verified. Audit document rights and embedding endpoint privacy before use; repository tree also includes a Sci-Hub bridge, which was not exercised or endorsed.

Reproducibility

Primary repository documentation/source inspected on 2026-10-17; no software installed, built or executed.

Adoption requirements

Source build and dependencies, configured embedding service/model, document collection and storage. Reviewed code references Ollama; complete installation compatibility was not established. Check document rights and endpoint privacy before ingestion.

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).