What frameworks does Denario use?

Denario is built on the AG2 and LangGraph frameworks to coordinate specialized AI agents for different stages of the research process.

Can I use my own research ideas instead of AI-generated ones?

Yes, Denario is highly flexible and allows you to provide custom hypotheses, methodologies, or pre-computed results at any stage of the pipeline.

Which journals are supported for paper generation?

It currently supports American Physical Society (APS) formatting, with additional journal styles available via the research pipeline configuration.

Does Denario require a specific Python environment?

Yes, Denario requires Python 3.12 or higher. It is recommended to install it using the uv package manager for the best experience.

Denario Research Assistant

Name: Denario Research Assistant
Author: Microck

byMicrock

•

108

Ciencia de Datos y ML

Automates the end-to-end scientific research lifecycle from data analysis and hypothesis generation to publishing LaTeX-formatted papers.

Acerca de

Denario is a comprehensive multiagent AI system designed to streamline scientific workflows by coordinating specialized agents for data exploration, methodology development, and computational analysis. Built on robust frameworks like AG2 and LangGraph, it enables researchers to transform raw datasets into publication-ready manuscripts with minimal manual intervention. Whether you are stuck at the hypothesis stage or need to generate journal-compliant LaTeX source, Denario provides a structured, reproducible pipeline that bridges the gap between data science and academic publishing.

Características Principales

108 GitHub stars
Multiagent orchestration using AG2 and LangGraph frameworks
Publication-ready LaTeX generation for journals like APS
Interactive GUI and Python API for flexible workflow management
End-to-end research pipeline from methodology to results
Automated hypothesis generation from raw datasets

Casos de Uso

Automating exploratory data analysis and hypothesis testing for new datasets
Streamlining the creation of structured research methodologies and computational experiments
Generating formatted academic papers and visualizations directly from analysis results

Acerca de

Características Principales

108 GitHub stars
Multiagent orchestration using AG2 and LangGraph frameworks
Publication-ready LaTeX generation for journals like APS
Interactive GUI and Python API for flexible workflow management
End-to-end research pipeline from methodology to results
Automated hypothesis generation from raw datasets

Casos de Uso

Automating exploratory data analysis and hypothesis testing for new datasets
Streamlining the creation of structured research methodologies and computational experiments
Generating formatted academic papers and visualizations directly from analysis results