Metadata-Version: 2.4
Name: shinon
Version: 0.0.1
Summary: Shinon — AI-powered conversational memory engine
Author-email: Mark Cognitive <mark@cognis.ai>
Project-URL: Homepage, https://github.com/markedcognitive/shinon
Project-URL: Repository, https://github.com/markedcognitive/shinon
Classifier: Development Status :: 1 - Planning
Classifier: Intended Audience :: Developers
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Requires-Python: >=3.10
Description-Content-Type: text/markdown

# Cognis

> Cognis gives AI agents a persistent personality that evolves over time. No chatbots that forget — just continuous, self-curating memory and mood.

Cognis is a lightweight, local-first architecture that transitions AI from stateless chatbots into continuous, embodied entities. Backed by a dynamic semantic memory stream and an internal two-dimensional affective engine (Valence & Arousal), Cognis computes expectancy deltas at every interaction turn to drive an organic, evolving personality trajectory.

## Status

**v0.0.1 — Planning**

This is a placeholder release to claim the package name on PyPI. Full API docs and features coming soon.

## Quick Start

```bash
pip install mc-cognis
```

## Features

- Fixed-section context model (SOUL, MEMORY, EXPECTANCY, CONVERSATION, WORKING_SPACE)
- LLM-driven mood management with expectancy calculus
- Personality system with configurable baselines
- Token-budget-aware context curation

## Repository

https://github.com/markedcognitive/cognis

## License

AGPL-3.0 — All modifications must be shared back, even when used as a service.
