Metadata-Version: 2.4
Name: neuronx-sdk
Version: 0.1.0
Summary: Python SDK for NeuronX AI Platform — 19 free LLMs, 185K patterns, autonomous agents
Project-URL: Homepage, https://neuronx.jagatab.uk
Project-URL: Documentation, https://neuronx.jagatab.uk/sdk
Project-URL: Repository, https://github.com/sreejagatab/neuronx-platform
Author-email: Ganesh Jagatab <sreejagatab@gmail.com>
License-Expression: MIT
Keywords: agents,ai,code-generation,llm,neuronx
Classifier: Development Status :: 3 - Alpha
Classifier: Intended Audience :: Developers
Classifier: License :: OSI Approved :: MIT License
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.8
Classifier: Programming Language :: Python :: 3.9
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Classifier: Topic :: Software Development :: Libraries
Requires-Python: >=3.8
Requires-Dist: httpx>=0.24.0
Requires-Dist: pydantic>=2.0.0
Provides-Extra: dev
Requires-Dist: pytest-asyncio>=0.21; extra == 'dev'
Requires-Dist: pytest-httpx>=0.21; extra == 'dev'
Requires-Dist: pytest>=7.0; extra == 'dev'
Requires-Dist: respx>=0.20; extra == 'dev'
Description-Content-Type: text/markdown

# neuronx-sdk

Python SDK for the [NeuronX AI Platform](https://neuronx.jagatab.uk) — 19 free LLMs, 185K+ code patterns, autonomous agents.

## Install

```bash
pip install neuronx-sdk
```

## Quick Start

```python
from neuronx import NeuronX

nx = NeuronX(api_key="nx-YOUR_KEY")

# Chat with 19 free LLM providers
response = nx.chat("explain quicksort in Python")
print(response.text)

# Generate code using 185K+ patterns
code = nx.codegen("REST API with JWT auth", language="python")
print(code.code)

# AI-powered search
results = nx.search("transformer attention mechanism")
print(results.summary)

# Problem solving
solution = nx.solve("optimize database queries for 1M rows")
print(solution.response)
```

## License

MIT
