# Denario
[](https://pypi.python.org/pypi/denario) [](https://www.python.org/downloads/) [](https://pypi.python.org/pypi/denario) [](https://www.gnu.org/licenses/gpl-3.0) [](https://deepwiki.com/AstroPilot-AI/Denario)
<a href="https://www.youtube.com/@denario-ai" target="_blank">
<img src="https://img.shields.io/badge/YouTube-Subscribe-red?style=flat-square&logo=youtube" alt="Subscribe on YouTube" width="140"/>
</a>
Denario is a multiagent system designed to be a scientific research assistant. Denario implements AI agents with [AG2](https://ag2.ai/) and [LangGraph](https://www.langchain.com/langgraph), using [cmbagent](https://github.com/CMBAgents/cmbagent) as the research analysis backend.
## Resources
- [🌐 Project page](https://astropilot-ai.github.io/DenarioPaperPage/)
<!-- - [📄 Paper](arxivblabla) -->
- [📖 Documentation](https://denario.readthedocs.io/en/latest/)
- [🖥️ Denario GUI repository](https://github.com/AstroPilot-AI/DenarioApp)
- [🤗 Demo web app for Denario GUI](https://huggingface.co/spaces/astropilot-ai/Denario)
- [📝 End-to-end research papers generated with Denario](https://github.com/AstroPilot-AI/DenarioExamplePapers)
- [🎥 YouTube channel](https://www.youtube.com/@denario-ai)
## Last updates
- October 9, 2025 - A paper fully generated with Denario has been accepted for publication in the [Open Conference of AI Agents for Science 2025](https://openreview.net/forum?id=LENY7OWxmN), 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:
```bash
python -m venv Denario_env
source Denario_env/bin/activate
pip install "denario[app]"
```
Or alternatively install it with [uv](https://docs.astral.sh/uv/), initializing a project and installing it:
```bash
uv init
uv add denario[app]
```
Then, run the gui with:
```
denario run
```
## Get started
Initialize a `Denario` instance and describe the data and tools to be employed.
```python
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.
```python
den.get_idea()
```
Generate the methodology required for working on that idea.
```python
den.get_method()
```
With the methodology setup, perform the required computations and get the plots and results.
```python
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)](https://journals.aps.org/) style.
```python
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:
```python
den.set_method(path_to_the_method_file.md)
```
## DenarioApp
You can run Denario using a GUI through the [DenarioApp](https://github.com/AstroPilot-AI/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
```bash
denario run
```
Test a [deployed demo of the app in HugginFace Spaces](https://huggingface.co/spaces/astropilot-ai/Denario).
## Build from source
### pip
You will need python 3.12 or higher installed. Clone Denario:
```bash
git clone https://github.com/AstroPilot-AI/Denario.git
cd Denario
```
Create and activate a virtual environment
```bash
python3 -m venv Denario_env
source Denario_env/bin/activate
```
And install the project
```bash
pip install -e .
```
### uv
You can also install the project using [uv](https://docs.astral.sh/uv/), just running:
```bash
uv sync
```
which will create the virtual environment and install the dependencies and project. Activate the virtual environment if needed with
```bash
source .venv/bin/activate
```
## Docker
You can run Denario in a docker image. Pull the image with:
```bash
docker pull pablovd/denario:latest
```
Once built, you can run the GUI with
```bash
docker run -p 8501:8501 --rm pablovd/denario:latest
```
or in interactive mode with
```bash
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`.
## Contributing
Pull requests are welcome! Feel free to open an issue for bugs, comments, questions and suggestions.
<!-- ## Citation
If you use this library please link this repository and cite [arXiv:2506.xxxxx](arXiv:x2506.xxxxx). -->
## License
[GNU GENERAL PUBLIC LICENSE (GPLv3)](https://www.gnu.org/licenses/gpl-3.0.html)
Denario - Copyright (C) 2025 Pablo Villanueva-Domingo, Francisco Villaescusa-Navarro, Boris Bolliet
## Contact and Enquieries
E-mail: [denario.astropilot.ai@gmail.com](mailto:denario.astropilot.ai@gmail.com)
Raw data
{
"_id": null,
"home_page": null,
"name": "denario",
"maintainer": null,
"docs_url": null,
"requires_python": ">=3.12",
"maintainer_email": "Denario <denario.astropilot.ai@gmail.com>",
"keywords": "agent, biology, chemistry, cosmology, llm, machine learning, material sciences",
"author": "Pablo Villanueva-Domingo, Francisco Villaescusa-Navarro, Boris Bolliet",
"author_email": null,
"download_url": "https://files.pythonhosted.org/packages/e3/5c/3c828d293a8bf40fdcbabb54e3d7e48bc18889284ce5ec0e0e77c71ec0ae/denario-0.1.24.tar.gz",
"platform": null,
"description": "# Denario\n\n[](https://pypi.python.org/pypi/denario) [](https://www.python.org/downloads/) [](https://pypi.python.org/pypi/denario) [](https://www.gnu.org/licenses/gpl-3.0) [](https://deepwiki.com/AstroPilot-AI/Denario)\n<a href=\"https://www.youtube.com/@denario-ai\" target=\"_blank\">\n<img src=\"https://img.shields.io/badge/YouTube-Subscribe-red?style=flat-square&logo=youtube\" alt=\"Subscribe on YouTube\" width=\"140\"/>\n</a>\n\nDenario is a multiagent system designed to be a scientific research assistant. Denario implements AI agents with [AG2](https://ag2.ai/) and [LangGraph](https://www.langchain.com/langgraph), using [cmbagent](https://github.com/CMBAgents/cmbagent) as the research analysis backend.\n\n## Resources\n\n- [\ud83c\udf10 Project page](https://astropilot-ai.github.io/DenarioPaperPage/)\n\n<!-- - [\ud83d\udcc4 Paper](arxivblabla) -->\n\n- [\ud83d\udcd6 Documentation](https://denario.readthedocs.io/en/latest/)\n\n- [\ud83d\udda5\ufe0f Denario GUI repository](https://github.com/AstroPilot-AI/DenarioApp)\n\n- [\ud83e\udd17 Demo web app for Denario GUI](https://huggingface.co/spaces/astropilot-ai/Denario)\n\n- [\ud83d\udcdd End-to-end research papers generated with Denario](https://github.com/AstroPilot-AI/DenarioExamplePapers)\n\n- [\ud83c\udfa5 YouTube channel](https://www.youtube.com/@denario-ai)\n\n## Last updates\n\n- October 9, 2025 - A paper fully generated with Denario has been accepted for publication in the [Open Conference of AI Agents for Science 2025](https://openreview.net/forum?id=LENY7OWxmN), the 1st open conference with AI as primary authors.\n\n## Installation\n\nTo install denario create a virtual environment and pip install it. We recommend using Python 3.12:\n\n```bash\npython -m venv Denario_env\nsource Denario_env/bin/activate\npip install \"denario[app]\"\n```\n\nOr alternatively install it with [uv](https://docs.astral.sh/uv/), initializing a project and installing it:\n\n```bash\nuv init\nuv add denario[app]\n```\n\nThen, run the gui with:\n\n```\ndenario run\n```\n\n## Get started\n\nInitialize a `Denario` instance and describe the data and tools to be employed.\n\n```python\nfrom denario import Denario\n\nden = Denario(project_dir=\"project_dir\")\n\nprompt = \"\"\"\nAnalyze the experimental data stored in data.csv using sklearn and pandas.\nThis data includes time-series measurements from a particle detector.\n\"\"\"\n\nden.set_data_description(prompt)\n```\n\nGenerate a research idea from that data specification.\n\n```python\nden.get_idea()\n```\n\nGenerate the methodology required for working on that idea.\n\n```python\nden.get_method()\n```\n\nWith the methodology setup, perform the required computations and get the plots and results.\n\n```python\nden.get_results()\n```\n\nFinally, generate a latex article with the results. You can specify the journal style, in this example we choose the [APS (Physical Review Journals)](https://journals.aps.org/) style.\n\n```python\nfrom denario import Journal\n\nden.get_paper(journal=Journal.APS)\n```\n\nYou 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:\n\n```python\nden.set_method(path_to_the_method_file.md)\n```\n\n## DenarioApp\n\nYou can run Denario using a GUI through the [DenarioApp](https://github.com/AstroPilot-AI/DenarioApp).\n\nThe app is already installed with `pip install \"denario[app]\"`, otherwise install it with `pip install denario_app` or `uv sync --extra app`.\n\nThen, launch the GUI with\n\n```bash\ndenario run\n```\n\nTest a [deployed demo of the app in HugginFace Spaces](https://huggingface.co/spaces/astropilot-ai/Denario).\n\n## Build from source\n\n### pip\n\nYou will need python 3.12 or higher installed. Clone Denario:\n\n```bash\ngit clone https://github.com/AstroPilot-AI/Denario.git\ncd Denario\n```\n\nCreate and activate a virtual environment\n\n```bash\npython3 -m venv Denario_env\nsource Denario_env/bin/activate\n```\n\nAnd install the project\n\n```bash\npip install -e .\n```\n\n### uv\n\nYou can also install the project using [uv](https://docs.astral.sh/uv/), just running:\n\n```bash\nuv sync\n```\n\nwhich will create the virtual environment and install the dependencies and project. Activate the virtual environment if needed with\n\n```bash\nsource .venv/bin/activate\n```\n\n## Docker\n\nYou can run Denario in a docker image. Pull the image with:\n\n```bash\ndocker pull pablovd/denario:latest\n```\n\nOnce built, you can run the GUI with\n\n```bash\ndocker run -p 8501:8501 --rm pablovd/denario:latest\n```\n\nor in interactive mode with\n\n```bash\ndocker run --rm -it pablovd/denario:latest bash\n```\n\nShare 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`.\n\n## Contributing\n\nPull requests are welcome! Feel free to open an issue for bugs, comments, questions and suggestions.\n\n<!-- ## Citation\n\nIf you use this library please link this repository and cite [arXiv:2506.xxxxx](arXiv:x2506.xxxxx). -->\n\n## License\n\n[GNU GENERAL PUBLIC LICENSE (GPLv3)](https://www.gnu.org/licenses/gpl-3.0.html)\n\nDenario - Copyright (C) 2025 Pablo Villanueva-Domingo, Francisco Villaescusa-Navarro, Boris Bolliet\n\n## Contact and Enquieries\n\nE-mail: [denario.astropilot.ai@gmail.com](mailto:denario.astropilot.ai@gmail.com)\n",
"bugtrack_url": null,
"license": "GPLv3",
"summary": "Modular Automation of Scientific Research with Multi-Agent Systems",
"version": "0.1.24",
"project_urls": {
"Documentation": "https://denario.readthedocs.io/en/latest/",
"Homepage": "https://astropilot-ai.github.io/DenarioPaperPage/",
"Repository": "https://github.com/AstroPilot-AI/Denario"
},
"split_keywords": [
"agent",
" biology",
" chemistry",
" cosmology",
" llm",
" machine learning",
" material sciences"
],
"urls": [
{
"comment_text": null,
"digests": {
"blake2b_256": "2f4d2da520817b5dae762cff67497166e5b800fedefa7a4400a53dccee30cd19",
"md5": "e37fa6b0c4ccd496abd024fe76efa02b",
"sha256": "59ac4f2010b7ec555441ec2e82457854ccaa4ae8497288ca38186bb7d746c5e8"
},
"downloads": -1,
"filename": "denario-0.1.24-py3-none-any.whl",
"has_sig": false,
"md5_digest": "e37fa6b0c4ccd496abd024fe76efa02b",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.12",
"size": 227439,
"upload_time": "2025-10-21T00:06:45",
"upload_time_iso_8601": "2025-10-21T00:06:45.521714Z",
"url": "https://files.pythonhosted.org/packages/2f/4d/2da520817b5dae762cff67497166e5b800fedefa7a4400a53dccee30cd19/denario-0.1.24-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": null,
"digests": {
"blake2b_256": "e35c3c828d293a8bf40fdcbabb54e3d7e48bc18889284ce5ec0e0e77c71ec0ae",
"md5": "2b3129cccee363d5c655361d003905f0",
"sha256": "46ea500e06e847eb4cd5b13e6ec4db8d278e0bf6e83a3caa9ce8871d2a85056b"
},
"downloads": -1,
"filename": "denario-0.1.24.tar.gz",
"has_sig": false,
"md5_digest": "2b3129cccee363d5c655361d003905f0",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.12",
"size": 569946,
"upload_time": "2025-10-21T00:06:49",
"upload_time_iso_8601": "2025-10-21T00:06:49.903560Z",
"url": "https://files.pythonhosted.org/packages/e3/5c/3c828d293a8bf40fdcbabb54e3d7e48bc18889284ce5ec0e0e77c71ec0ae/denario-0.1.24.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2025-10-21 00:06:49",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "AstroPilot-AI",
"github_project": "Denario",
"travis_ci": false,
"coveralls": false,
"github_actions": false,
"lcname": "denario"
}
JSON
