Denario
Denario is a multiagent system designed to be a scientific research assistant. Denario implements AI agents with AG2 and LangGraph, using cmbagent as the research analysis backend. Denario and Cmbagent are Open Source Software projects under GPL-3 and Apache 2 licenses respectively. No private or public organizations/individuals other than the three copyright holders can claim IP and/or ownership on these software packages.
Resources
Last updates
-
October 1, 2026 - Denario paper has been published in PRX Intelligence.
-
February 3, 2026 - Denario has been featured in Nature Materials.
-
January 20, 2026 - Denario and Cmbagent featured in the LSST DESC AI Roadmap.
-
December 7, 2025 - Cmbagent, the research analysis backend of Denario, won a first place award at the NeurIPS 2025 Fair Universe Competition.
-
November 3, 2025 - Version 1.0 is released and the Denario paper is out at arxiv!
-
October 9, 2025 - A paper fully generated with Denario has been accepted for publication in the Open Conference of AI Agents for Science 2025, the 1st open conference with AI as primary authors.
Installation
To install denario create a virtual environment and pip install it. We recommend using Python 3.12:
python -m venv Denario_env
source Denario_env/bin/activate
pip install "denario[app]"
Or alternatively install it with uv, initializing a project and installing it:
uv init
uv add denario[app]
Then, run the gui with:
denario run
Credentials
Denario makes use of LLMs from OpenAI, Claude and Gemini. See the documentation on LLM API keys for setup instructions.
Get started
Initialize a Denario instance and describe the data and tools to be employed.
from denario import Denario
den = Denario(project_dir="project_dir")
prompt = """
Analyze the experimental data stored in data.csv using sklearn and pandas.
This data includes time-series measurements from a particle detector.
"""
den.set_data_description(prompt)
Generate a research idea from that data specification.
den.get_idea()
Generate the methodology required for working on that idea.
den.get_method()
With the methodology setup, perform the required computations and get the plots and results.
den.get_results()
Finally, generate a latex article with the results. You can specify the journal style, in this example we choose the APS (Physical Review Journals) style.
from denario import Journal
den.get_paper(journal=Journal.APS)
You can also manually provide any info as a string or markdown file in an intermediate step, using the set_idea, set_method or set_results methods. For instance, for providing a file with the methodology developed by the user:
den.set_method(path_to_the_method_file.md)
DenarioApp
You can run Denario using a GUI through the DenarioApp.
The app is already installed with pip install "denario[app]", otherwise install it with pip install denario_app or uv sync --extra app.
Then, launch the GUI with
denario run
Test a deployed demo of the app in HugginFace Spaces.
Build from source
pip
You will need python 3.12 or higher installed. Clone Denario:
git clone https://github.com/Denario-AI/Denario.git
cd Denario
Create and activate a virtual environment
python3 -m venv Denario_env
source Denario_env/bin/activate
And install the project
pip install -e .
uv
You can also install the project using uv, just running:
uv sync
which will create the virtual environment and install the dependencies and project. Activate the virtual environment if needed with
source .venv/bin/activate
Docker
You can run Denario in a Docker image, which includes all the required dependencies for Denario including LaTeX. Pull the image with:
docker pull pablovd/denario:latest
Once built, you can run the GUI with
docker run -p 8501:8501 --rm pablovd/denario:latest
or in interactive mode with
docker run --rm -it pablovd/denario:latest bash
Share volumes with -v $(pwd)/project:/app/project for inputing data and accessing to it. You can also share the API keys with a .env file in the same folder with -v $(pwd).env/app/.env.
You can also build an image locally with
docker build -f docker/Dockerfile.dev -t denario_src .
Read more information on how to use the Docker images in the documentation.
Contributing
Pull requests are welcome! Feel free to open an issue for bugs, comments, questions and suggestions.
Citation
If you make use of Denario, please cite the following references:
@article{villaescusanavarro2025denarioprojectdeepknowledge,
title={The Denario project: Deep knowledge AI agents for scientific discovery},
author={Francisco Villaescusa-Navarro and Boris Bolliet and Pablo Villanueva-Domingo and Adrian E. Bayer and Aidan Acquah and Chetana Amancharla and Almog Barzilay-Siegal and Pablo Bermejo and Camille Bilodeau and Pablo Cárdenas Ramírez and Miles Cranmer and Urbano L. França and ChangHoon Hahn and Yan-Fei Jiang and Raul Jimenez and Jun-Young Lee and Antonio Lerario and Osman Mamun and Thomas Meier and Anupam A. Ojha and Pavlos Protopapas and Shimanto Roy and David N. Spergel and Pedro Tarancón-Álvarez and Ujjwal Tiwari and Matteo Viel and Digvijay Wadekar and Chi Wang and Bonny Y. Wang and Licong Xu and Yossi Yovel and Shuwen Yue and Wen-Han Zhou and Qiyao Zhu and Jiajun Zou and Íñigo Zubeldia},
year={2025},
eprint={2510.26887},
archivePrefix={arXiv},
primaryClass={cs.AI},
url={https://arxiv.org/abs/2510.26887},
}
@software{Denario_2025,
author = {Pablo Villanueva-Domingo, Francisco Villaescusa-Navarro, Boris Bolliet},
title = {Denario: Modular Multi-Agent System for Scientific Research Assistance},
year = {2025},
url = {https://github.com/Denario-AI/Denario},
note = {Available at https://github.com/Denario-AI/Denario},
version = {latest}
}
@software{CMBAGENT_2025,
author = {Boris Bolliet},
title = {CMBAGENT: Open-Source Multi-Agent System for Science},
year = {2025},
url = {https://github.com/CMBAgents/cmbagent},
note = {Available at https://github.com/CMBAgents/cmbagent},
version = {latest}
}
License
GNU GENERAL PUBLIC LICENSE (GPLv3)
Denario - Copyright (C) 2026 Pablo Villanueva-Domingo, Francisco Villaescusa-Navarro, Boris Bolliet
Contact and enquiries
E-mail: denario.astropilot.ai@gmail.com