Metadata-Version: 2.4
Name: agentic-cognition
Version: 0.1.0
Summary: Longitudinal user modeling for AI agents
Project-URL: Homepage, https://github.com/agentralabs/agentic-cognition
Project-URL: Documentation, https://github.com/agentralabs/agentic-cognition/tree/main/docs
Project-URL: Repository, https://github.com/agentralabs/agentic-cognition
Author: Agentra Labs
License-Expression: MIT
Keywords: agents,ai,cognition,mcp,modeling
Classifier: Development Status :: 3 - Alpha
Classifier: Intended Audience :: Developers
Classifier: License :: OSI Approved :: MIT License
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Requires-Python: >=3.10
Provides-Extra: dev
Requires-Dist: pytest-cov>=5.0; extra == 'dev'
Requires-Dist: pytest>=8.0; extra == 'dev'
Description-Content-Type: text/markdown

# AgenticCognition Python SDK

Longitudinal user modeling for AI agents -- belief revision, world models, and cognitive state tracking.

## Install

```bash
pip install agentic-cognition
```

## Usage

```python
from agentic_cognition import CognitionStore

cs = CognitionStore("project.acog")
cs.create_model("user-prefs", domain="preferences")
cs.update_model("user-prefs", belief="prefers-dark-mode", confidence=0.9)
cs.query_model("user-prefs")
```

Requires the `acog` CLI binary on PATH. Install via:

```bash
curl -fsSL https://agentralabs.tech/install/cognition | bash
```
