Metadata-Version: 2.4
Name: humemai-research
Version: 1.0.1.post2
Summary: A Machine With Human-Like Memory Systems.
Home-page: https://github.com/humemai/humemai-research
Author: Taewoon Kim
Author-email: info@humem.ai
Project-URL: Bug Tracker, https://github.com/humemai/humemai-research/issues
Classifier: Programming Language :: Python :: 3
Classifier: License :: OSI Approved :: MIT License
Classifier: Operating System :: OS Independent
Requires-Python: >=3.10
Description-Content-Type: text/markdown
License-File: LICENSE
Requires-Dist: gymnasium>=0.27.1
Requires-Dist: torch>=1.12.1
Requires-Dist: PyYAML>=6.0
Requires-Dist: tqdm
Requires-Dist: ipython>=8.20.0
Requires-Dist: matplotlib>=3.8.2
Dynamic: license-file

# humemai

[![DOI](https://zenodo.org/badge/614376180.svg)](https://zenodo.org/doi/10.5281/zenodo.10876440)
[![PyPI
version](https://badge.fury.io/py/humemai-research.svg)](https://badge.fury.io/py/humemai-research)

This repo hosts a package `humemai`, a human-like memory systems that are modeled with
knowledge knoweldge graphs (KGs). At the moment they are nothing but a Python list of
quadruples, but soon it'll be a better object type so that they can be compatible with
graph databases, e.g., RDFLib, GraphDB, Neo4j, etc. There have been both [academic
papers](#list-of-academic-papers-that-use-humemai) and
[applications](#list-of-applications-that-use-humemai) that have used this package.

## List of academic papers that use HumemAI

- ["A Machine With Human-Like Memory Systems"](https://arxiv.org/abs/2204.01611).
- ["A Machine with Short-Term, Episodic, and Semantic Memory
  Systems"](https://doi.org/10.1609/aaai.v37i1.25075).
- ["Capturing Dynamic Knowledge Graphs with Human-like Memory Systems by Reinforcement
  Learning"](<>).

## List of applications that use HumemAI

## pdoc documentation

Click on [this link](https://humemai.github.io/humemai) to see the HTML rendered
docstrings

## Contributing

Contributions are what make the open source community such an amazing place to be learn,
inspire, and create. Any contributions you make are **greatly appreciated**.

1. Fork the Project
1. Create your Feature Branch (`git checkout -b feature/AmazingFeature`)
1. Run `make test && make style && make quality` in the root repo directory, to ensure
   code quality.
1. Commit your Changes (`git commit -m 'Add some AmazingFeature'`)
1. Push to the Branch (`git push origin feature/AmazingFeature`)
1. Open a Pull Request

## License

[MIT](https://choosealicense.com/licenses/mit/)
