Metadata-Version: 2.4
Name: humemai-research
Version: 2.5.6.post2
Summary: A Machine With Human-Like Memory
Home-page: https://github.com/humemai/humemai-research-research
Author: Taewoon Kim
Author-email: info@humem.ai
Project-URL: Bug Tracker, https://github.com/humemai/humemai-research-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: rdflib
Requires-Dist: docker
Requires-Dist: sparqlwrapper
Requires-Dist: nest_asyncio
Requires-Dist: gremlinpython
Requires-Dist: transformers
Requires-Dist: torch
Provides-Extra: dev
Requires-Dist: black; extra == "dev"
Requires-Dist: black[jupyter]; extra == "dev"
Requires-Dist: flake8; extra == "dev"
Requires-Dist: mdformat; extra == "dev"
Requires-Dist: isort; extra == "dev"
Requires-Dist: pytest; extra == "dev"
Requires-Dist: ipython; extra == "dev"
Requires-Dist: ipykernel; extra == "dev"
Requires-Dist: tqdm; extra == "dev"
Requires-Dist: huggingface_hub[cli]; extra == "dev"
Requires-Dist: accelerate; extra == "dev"
Dynamic: license-file

# HumemAI Research

HumemAI Research explores **human-like memory systems** for AI — combining **episodic** (experience-based) and **semantic** (knowledge-based) memory models.

We study how machines can store, retrieve, and reason over structured memory graphs built from text, tables, and user interactions.

## Installation

```bash
pip install humemai-research
```

## Usage

```python
from humemai_research.rdflib import Humemai
# or
from humemai_research.janusgraph import Humemai
```

## Research Areas

- **Episodic Memory:** Representing conversations and experiences as temporal property graphs.  
- **Semantic Memory:** Integrating user-provided or external data (e.g. Wikidata, Wikipedia) into graph, table, and vector formats.  
- **Memory Management:** Learning what to remember, summarize, or forget across time.  
- **Graph-Based Reasoning:** Querying and updating symbolic–neural hybrid memories.  
- **Reinforcement Learning & Knowledge Graphs:** Using RL to induce hierarchies and explore knowledge structures.
