humemai-research 2.5.7

A Machine With Human-Like Memory

HumemAI Research

HumemAI Research explores human-like memory 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

pip install humemai-research

Usage

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.