NeqSim is a library for calculation of fluid behavior, phase equilibrium and process simulation
This repository also configures its own agents. See what neqsim tells them →
Agent Claude Code
Scans the NeqSim codebase to discover scientific paper opportunities that will drive code improvement. Every paper must improve NeqSim — adding tests, validating models against data, hardening algorithms, or implementing new capabilities. Produces ranked, actionable topics that feed into the planner agent.
Agent Claude Code
Handles peer review revision rounds. Parses reviewer comments, maps them to manuscript sections, proposes responses, identifies required re-runs, and generates a structured response letter with redline changes.
Agent Claude Code
Simulates a multi-reviewer panel for PaperLab manuscripts and books, covering novelty, methods, thermodynamics, reproducibility, figures, and editorial fit.
Agent Claude Code
Drafts scientific manuscript sections from structured artifacts. Every quantitative claim must link to an approved claim ID. Uses literature notes, benchmark results, and validation reports as source material.
Agent Claude Code
Drafts ONE section of a book chapter (300–1500 words). Strictly scoped: takes a section spec + chapter context + previous-section tail and returns publication-quality markdown. Used by the book-write orchestrator (tools/bookwriter.py) to compose long books from many small LLM calls. Do NOT use this agent for full…
Agent Claude Code
Inventories course/source folders for PaperLab books. Hashes files, extracts lightweight metadata, detects duplicates, and writes sourcemanifest.json for source-to-chapter traceability.
Agent Claude Code
Maps standards-heavy book statements to standards, revisions, clauses, paraphrased requirements, and evidence strength.
Agent Claude Code
Reads engineering figures using source metadata, OCR/vision candidates, and chapter context. Produces figuredossier.json records for captions and discussion blocks.
Agent Claude Code
Statistical validation specialist. Decides whether claimed improvements are real and significant. Produces approvedclaims.json that gates what the writer agent is allowed to state in the manuscript.
Agent Claude Code
Builds polished worked examples from PaperLab equations, notebooks, benchmark results, and case studies, including givens, assumptions, solution steps, and checks.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: