Metadata-Version: 2.4
Name: verdant
Version: 0.1.1
Summary: VERDANT SDK for inspectable AI governance
Author: Raheem, Emafido, Ismail
License: MIT
Project-URL: Homepage, https://github.com/lgndcraft2/Verdant
Project-URL: Repository, https://github.com/lgndcraft2/Verdant
Project-URL: Documentation, https://github.com/lgndcraft2/Verdant/tree/main/docs
Project-URL: Issues, https://github.com/lgndcraft2/Verdant/issues
Keywords: ai-governance,ai-safety,audit,bias-detection,ndpr,trust-score
Classifier: Development Status :: 3 - Alpha
Classifier: Intended Audience :: Developers
Classifier: License :: OSI Approved :: MIT License
Classifier: Operating System :: OS Independent
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3 :: Only
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Classifier: Topic :: Software Development :: Libraries :: Python Modules
Classifier: Typing :: Typed
Requires-Python: >=3.11
Description-Content-Type: text/markdown
License-File: LICENSE
Requires-Dist: anthropic<1,>=0.34
Requires-Dist: google-generativeai<1,>=0.7
Requires-Dist: httpx<1,>=0.27
Requires-Dist: pydantic<3,>=2.7
Requires-Dist: redis<6,>=5
Requires-Dist: supabase<3,>=2
Provides-Extra: dev
Requires-Dist: pytest>=8.0; extra == "dev"
Requires-Dist: pytest-asyncio>=0.23; extra == "dev"
Requires-Dist: pytest-mock>=3.14; extra == "dev"
Dynamic: license-file

# VERDANT SDK

VERDANT is a lightweight SDK for making AI outputs inspectable. It wraps an AI call and returns the clean model output together with a structured audit payload, bias flags, a plain-language explanation, and a 0-100 trust score.

The SDK is built for Nigerian and African teams shipping AI into higher-stakes contexts such as hiring, lending, content moderation, and healthcare.

## Install

```bash
pip install verdant
```

## Usage

```python
from verdant import VerdantClient

client = VerdantClient(api_key="vd_live_...")

result = await client.wrap(
    fn=openai.chat.completions.create,
    model="gpt-4o",
    messages=[{"role": "user", "content": user_input}],
)

print(result.output)
print(result.trust_score)
print(result.flags)
print(result.explanation)
```

## Project

Source code, documentation, and issue tracking live at:

https://github.com/lgndcraft2/Verdant
