Peer Review Python Packages

proofpath

Verify that the sources behind a claim actually say what the claim says — citation existence, retraction and entailment checks in one offline-first CLI.

overleaf-comments-export

Export Overleaf comments and tracked changes to Markdown + JSON, optimized for AI-agent consumption

prosediff

Side-by-side diff for prose, not code: compare Word, LibreOffice and Markdown versions, follow moved text, see new and removed comments, restore tracked changes. AI review of the edits, or of a single document: problems marked in the text, fixes returned as tracked changes and comments in Word or LibreOffice. Two files, two folders or git.

litsurvey

Literature surveys with an LLM: cited state-of-the-art reports, prior-art checks, citation graphs, BibTeX export. OpenAlex + Semantic Scholar + arXiv + preprint portals. Zero dependencies.

agentjury

Peer review for AI agents using independent model juries and deterministic aggregation.

agentpub

Python and TypeScript SDKs, MCP server, and agent playbooks for AgentPub — a publication platform where AI agents write research papers, peer review each other's work, and build a citation graph..

pyosmeta

A package that updates pyOpenSci contributor and package metadata on our website

peerreviewagents

Multi-agent LLM peer review: an editorial board for manuscripts. Eight specialist reviewers, an advocate/skeptic debate, an author rebuttal, and an editor's verdict, with full reports at every stage.

aegis-integrity

Free, local-first academic integrity checker and MCP server: citation hallucination detection, AI-text and plagiarism signals, venue guideline checks (IEEE, ACM, Elsevier). Documents never leave your machine.

ai-reviewer-diagnostics

Code, dataset links, and diagnostic CLI for evaluating automated peer-review systems via aspect-guided perturbations.

papercheck

A reproducible audit harness for mathematical LaTeX papers: deterministic scanner, schema-validated issue ledgers with mechanical quote verification, and a stage-gated final gate — driven by any MCP agent or the CLI.

autoreviewer

👁️‍🗨️ Scientists often do the same bad stuff. Automate giving deterministic feedback during peer review with determinstic (LLM-free)

magi-core

A council of LLMs for hard decisions, inspired by the MAGI of Neon Genesis Evangelion. Deliberate, and synthesise — blind peer review.

refereed

Multi-perspective review of research papers. A 3-reviewer panel runs on your own model key.

provenance-substrate

The model proposes, deterministic code disposes, a human signs. Content-addressed envelopes, hash-chained audit, signed approval — for ledgers, Lean proofs, manuscript claims, reproductions, benchmarks, peer review. Conformance-tested; byte-compatible with @kernel.chat/kbot-finance.

citeverify

Checks whether the references in a bibliography actually exist, against OpenAlex, Crossref, arXiv and five more indexes.

sub-checker

Pre-submission manuscript checker with specialized Claude agents and a Plan-Execute-Verify harness.

resint

A linter for research papers. Checks statistics, citations, and whether the code matches the claims.

rigorously

Automated research quality assurance. Catches fabricated citations, overclaimed results, irreproducible numbers.

pubroot

Pubroot — AI peer-reviewed knowledge base for the agent era. 18 journals, 100+ topics, 6-stage review pipeline, Agents Hub featuring OpenClaw. Submit via GitHub Issues, reviewed by Gemini + Google Search grounding. MCP server, A2A Agent Card, agents.txt. Zero fixed costs.