YenochQin/llm-wiki · Agentic Research Directory

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

2026-11-01 (UTC)

AI source review of partial-documentation. Identity/version: primary snapshot matches this queued resource; exact upstream release/byte parity is not generally verified. Source classification is not a correctness or research-benefit guarantee.

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

Sources (1)

Research applicability

README documents Zotero-backed paper ingestion, PDF conversion and cited wiki queries driven by a user in Claude Code or Codex.

Getting started

uv, Python >=3.10, Claude Code or Codex, and default MinerU API token; optional local backend requires model storage. User configures external content paths.

Maintenance

Source snapshot checked 2026-11-01; ongoing maintenance, installed behavior and current-version parity not generally verified.

License

Consult original licence and data/provider terms; source access is not reuse clearance. No licence/rights audit or installation was performed.

Workflow & human oversight

Workflow level unassigned: Users select ingestion/query commands and raw originals are read-only to the LLM, but validation of generated wiki claims is not specified. Missing checking instructions; inspect canonical relevant skill next. Human control/boundary: Users select ingestion/query commands and raw originals are read-only to the LLM, but validation of generated wiki claims is not specified. Missing checking instructions; inspect canonical relevant skill next.

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

Approach

README documents Zotero-backed paper ingestion, PDF conversion and cited wiki queries driven by a user in Claude Code or Codex. Documented steps: User configures sources → ingest DOI/local PDF → convert/store structured knowledge → user asks cited question. Human validation/stopping rules not captured.

Outcomes (as reported by the originating team)

Author reports or documentation only, not independently reproduced. No independent reproduction was performed here.

Limitations

README only; no citation or conversion accuracy established. Default cloud PDF backend can process user documents externally; assess rights and provider handling before use.

Reproducibility

Primary-source text was read and preserved with provenance hashes. No candidate code, model, benchmark, data upload or claimed outcome was executed/reproduced.

Adoption requirements

uv, Python >=3.10, Claude Code or Codex, and default MinerU API token; optional local backend requires model storage. User configures external content paths.

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.