A tri-layer memory framework for LLM solutions.

Grizabella is a sophisticated memory layer designed for Large Language Model (LLM) solutions. It provides a unified interface to manage and query data across relational, vector, and graph databases, enabling complex memory and knowledge retrieval for AI applications.

• Tri-layer Storage: Integrates SQLite (relational), LanceDB (vector), and Kuzu (graph) for comprehensive data management.
• Unified Python API: Offers a simple and consistent Python interface to interact with all three database layers.
• Complex Query Engine: Allows for sophisticated queries that can span across the different data storage paradigms.
• PySide6 UI: Includes an optional desktop application for visualizing and managing data.
• MCP Server: Can operate as a Model Context Protocol (MCP) server, allowing other tools to leverage its memory capabilities.

• User Guide
• API Reference
• Examples
• MCP Server Startup

For production use (once published):

pip install grizabella

For development:

git clone https://github.com/pwilkin/grizabella.git
cd grizabella
poetry install

from grizabella import Grizabella

# Initialize Grizabella (connects to default in-memory databases)
gz = Grizabella()

# Define an object type (implicitly creates a table/node type)
gz.create_object_type("document", {"text": str, "source": str})

# Add an object
doc1 = gz.add_object(
    object_type="document",
    data={"text": "This is the first document.", "source": "manual"},
    vector_data={"text": "This is the first document."} # Data for embedding
)

print(f"Added document with ID: {doc1.id}")

# Further operations (querying, adding relations, etc.) would go here.

Contributions are welcome! Please see CONTRIBUTING.md (to be added) for guidelines on how to contribute to Grizabella.

Grizabella is licensed under the MIT License. See the LICENSE file for details.