claude-scientific-writer and claude-scholar

These are complements—the scientific writer provides domain-specific content generation for manuscripts while the scholar tool offers a CLI framework that orchestrates the full research workflow, so they could be integrated together to automate writing within a broader research pipeline.

claude-scientific-writer
59
Established
claude-scholar
56
Established
Maintenance 16/25
Adoption 10/25
Maturity 13/25
Community 20/25
Maintenance 25/25
Adoption 10/25
Maturity 3/25
Community 18/25
Stars: 1,043
Forks: 123
Downloads:
Commits (30d): 3
Language: Python
License: MIT
Stars: 1,341
Forks: 108
Downloads:
Commits (30d): 53
Language: Python
License:
No Package No Dependents
No License No Package No Dependents

About claude-scientific-writer

K-Dense-AI/claude-scientific-writer

A general purpose scientific writer

Integrates real-time literature search via Perplexity Sonar Pro and AI diagram generation to produce publication-ready scientific papers, grant proposals, and clinical reports with verified citations. Available as a Claude Code plugin, Python package, or CLI, supporting multiple document formats (IMRaD papers, NSF/NIH proposals, LaTeX posters) with automatic data file ingestion and figure embedding. Built on Claude's API with optional OpenRouter integration for research lookup and Nano Banana Pro for scientific diagram generation.

About claude-scholar

Galaxy-Dawn/claude-scholar

Personal AI CLI configuration for academic research & software development. Supports Claude Code, OpenCode, and Codex CLI — covering the full research lifecycle from ideation to publication.

Provides filesystem-first project knowledge management via Obsidian with auto-synced experiment reports and results, plus Zotero MCP integration for remote bibliography access (DOI/arXiv import, collection management). Architecture uses skill-based command routing across 40+ Claude Code/Codex/OpenCode-compatible skills and agents, with Node.js hooks for cross-platform session management, security filtering, and 30-day log auto-cleanup—designed around human-centered semi-automation where the researcher retains decision authority over problem selection, hypothesis validation, and manuscript direction.

Scores updated daily from GitHub, PyPI, and npm data. How scores work