Metadata-Version: 2.4
Name: accuralai-cache
Version: 0.1.0
Summary: Caching providers for the AccuralAI LLM pipeline.
Project-URL: homepage, https://github.com/accuralai/accuralai-cache
Project-URL: repository, https://github.com/accuralai/accuralai-cache
Author: AccuralAI Maintainers
License: Apache-2.0
License-File: LICENSE
Requires-Python: >=3.10
Requires-Dist: accuralai-core
Requires-Dist: pydantic>=2.5
Provides-Extra: dev
Requires-Dist: pytest; extra == 'dev'
Requires-Dist: pytest-anyio; extra == 'dev'
Requires-Dist: pytest-mock; extra == 'dev'
Description-Content-Type: text/markdown

# accuralai-cache

`accuralai-cache` provides cache implementations for the AccuralAI pipeline. The initial release ships an in-memory cache with TTL support, statistics, and deterministic cache-key helpers. It registers the `advanced` cache plugin that `accuralai-core` can load automatically.

Install alongside the core orchestrator:

```bash
pip install accuralai-core accuralai-cache
```

Once installed, the CLI pipeline will cache responses in-memory, honoring TTL and capacity limits defined in your configuration.
