Metadata-Version: 2.4
Name: powerailabs
Version: 0.1.2
Summary: The PowerAI Labs stack — installs the full suite of composable AI-engineering primitives.
Author: Raghav Mishra
License-Expression: Apache-2.0
License-File: LICENSE
License-File: NOTICE
Requires-Python: >=3.11
Requires-Dist: powerailabs-acttrace
Requires-Dist: powerailabs-cassette
Requires-Dist: powerailabs-contextkit
Requires-Dist: powerailabs-core
Requires-Dist: powerailabs-squeeze
Requires-Dist: powerailabs-tokenguard
Description-Content-Type: text/markdown

# powerailabs

The umbrella meta-package for the **PowerAI Labs** stack — *developer tools for the AI engineering
era*. Installing it pulls the whole suite of composable Python primitives for context, cost,
testing, and governance.

**One install, the entire stack — `pip install powerailabs`.**

![PyPI](https://img.shields.io/pypi/v/powerailabs) ![license](https://img.shields.io/badge/license-Apache_2.0-blue)

This package ships **no code** of its own — it only declares the others as dependencies, so they
share the `powerailabs.*` import namespace:

| | Import | Role |
|---|---|---|
| `powerailabs-core` | `powerailabs.core` | foundation (types · tokens · prices · `instrument` · bus · OTel) |
| `powerailabs-contextkit` | `powerailabs.contextkit` | assemble context within a budget |
| `powerailabs-squeeze` | `powerailabs.squeeze` | reversible, content-aware compression |
| `powerailabs-tokenguard` | `powerailabs.tokenguard` | pre-flight cost caps + attribution |
| `powerailabs-cassette` | `powerailabs.cassette` | record/replay agent runs |
| `powerailabs-acttrace` | `powerailabs.acttrace` | tamper-evident audit log |

Prefer to install only what you need — each package works standalone and pulls `powerailabs-core`
transitively. See the [project README](https://github.com/PowerAI-Labs/powerailabs) for the
composition story and examples.

*Part of [PowerAI Labs](https://powerailabs.dev). Apache-2.0 licensed; provided "as is", without warranty — use at your own risk (LICENSE §7–8).*
