Metadata-Version: 2.4
Name: dualmemory
Version: 0.0.1
Summary: Episodic + semantic memory layer for LLM agents, with provenance and validity windows
Keywords: llm,memory,agents,rag,episodic,semantic
Author: CyberSmart02
Author-email: CyberSmart02 <jagarlamudisai0602@gmail.com>
License-Expression: MIT
Classifier: Development Status :: 3 - Alpha
Classifier: Intended Audience :: Developers
Classifier: Intended Audience :: Science/Research
Classifier: License :: OSI Approved :: MIT License
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Requires-Dist: pydantic>=2.7
Requires-Dist: sqlalchemy>=2.0
Requires-Dist: faiss-cpu>=1.8
Requires-Dist: numpy>=1.26
Requires-Python: >=3.11
Project-URL: Homepage, https://github.com/CyberSmart02/dualmem
Project-URL: Repository, https://github.com/CyberSmart02/dualmem
Project-URL: Issues, https://github.com/CyberSmart02/dualmem/issues
Description-Content-Type: text/markdown

# dualmem

A memory layer for LLM agents with two cooperating stores:

- **Episodes** — atomic, timestamped events, each linked to its source messages.
- **Facts** — durable statements with validity windows, so changed information is superseded, never silently overwritten.

Every memory is traceable back to the conversation that produced it (provenance), and a consolidation pass promotes recurring evidence from episodes into durable facts.

> **Status: early development (v0).** API will change.

## Install

```bash
pip install dualmem
```

## License

MIT