Metadata-Version: 2.1
Name: kloom-litellm
Version: 0.0.1.post1
Summary: A LiteLLM plugin for intelligent model routing and request tracking with Kloom
Author-email: Kloom <support@kloom.ai>
Maintainer-email: Kloom <support@kloom.ai>
License: Apache License 2.0
Project-URL: Homepage, https://kloom.ai
Project-URL: Documentation, https://docs.kloom.ai/quickstart/litellm
Project-URL: Repository, https://github.com/kloom-ai/kloom-litellm-plugin
Project-URL: Issues, https://github.com/kloom-ai/kloom-litellm-plugin/issues
Keywords: litellm,llm,ai,kloom,model-routing,observability,logging,openai,anthropic
Classifier: Development Status :: 3 - Alpha
Classifier: Intended Audience :: Developers
Classifier: Programming Language :: Python :: 3
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: Programming Language :: Python :: 3.13
Classifier: Topic :: Software Development :: Libraries :: Python Modules
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Requires-Python: >=3.9
Description-Content-Type: text/markdown
License-File: LICENSE
License-File: NOTICE
Requires-Dist: litellm>=1.79.3
Requires-Dist: httpx>=0.27.0

# kloom-litellm

A LiteLLM plugin for intelligent model routing and request tracking with [Kloom](https://kloom.ai).

## Features

- **Intelligent Model Routing** (LiteLLM Proxy): Automatically select the best model based on cost, performance, and availability
- **Request Tracking** (SDK & Proxy): Log all LLM requests and responses for analytics and monitoring
- **Seamless Integration**: Works with any LiteLLM-supported model provider

## Quick Start

### Installation

```bash
pip install kloom-litellm
```

### Basic Usage (Request Tracking)

```python
import litellm
from kloom_litellm import KloomPlugin

# Initialize the plugin
kloom_logger = KloomPlugin()
litellm.callbacks = [kloom_logger]

# Use LiteLLM as normal - requests will automatically be tracked
response = litellm.completion(
    model="gpt-5",
    messages=[{"role": "user", "content": "Hello!"}]
)
```

## Documentation

For complete documentation, including:

- LiteLLM Proxy setup for model routing
- Configuration options
- Advanced usage examples
- Troubleshooting

Visit: **[https://docs.kloom.ai/quickstart/litellm](https://docs.kloom.ai/quickstart/litellm)**

## Development

### Installation from Source

```bash
uv sync
```

## License

See [LICENSE](LICENSE) file.
