Denario

If you're doing computational research and want to automate the grunt work from hypothesis to LaTeX paper, this is worth checking out. It chains together specialized agents to handle data analysis, methodology development, literature search, and journal-formatted writing. Built on AG2 and LangGraph, so you get proper multiagent orchestration. You can let it run the full pipeline or drop in at any stage with your own ideas or results. The Journal.APS formatting is nice if you're publishing in physics. Requires Python 3.12+ and API keys for your LLM provider. The GUI exists but the programmatic workflow is where this shines for reproducible research pipelines.

skills.sh installs: 246
GitHub stars: 33.2K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add davila7/claude-code-templates --skill denario --agent claude-code

Installs into .claude/skills of the current project.

Files

Denario

Overview

Denario is a multiagent AI system designed to automate scientific research workflows from initial data analysis through publication-ready manuscripts. Built on AG2 and LangGraph frameworks, it orchestrates multiple specialized agents to handle hypothesis generation, methodology development, computational analysis, and paper writing.