Metadata-Version: 2.4
Name: llmgovernor
Version: 0.2.0
Summary: LLM Cost Governance — budget enforcement, cost tracking, and smart model routing for AI agent fleets.
Author-email: EarlyBrightGlobal <earlybrightkids@gmail.com>
License-Expression: MIT
Classifier: Development Status :: 4 - Beta
Classifier: Intended Audience :: Developers
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Classifier: Topic :: Software Development :: Libraries :: Python Modules
Requires-Python: >=3.10
Description-Content-Type: text/markdown
License-File: LICENSE
Requires-Dist: httpx>=0.27
Requires-Dist: pydantic>=2.0
Provides-Extra: openai
Requires-Dist: openai>=1.0; extra == "openai"
Provides-Extra: anthropic
Requires-Dist: anthropic>=0.30; extra == "anthropic"
Provides-Extra: bedrock
Requires-Dist: boto3>=1.34; extra == "bedrock"
Provides-Extra: all
Requires-Dist: openai>=1.0; extra == "all"
Requires-Dist: anthropic>=0.30; extra == "all"
Requires-Dist: boto3>=1.34; extra == "all"
Dynamic: license-file

# LLMGovernor

**LLM Cost Governance — budget enforcement, cost tracking, and smart model routing for AI agent fleets**

LLMGovernor provides intelligent cost monitoring and budget enforcement for AI agent applications. Track spending, set limits, and route to the right model across OpenAI, Anthropic, and AWS Bedrock.

## Installation

Install the core package:
```bash
pip install llmgovernor
```

Or install with all provider dependencies:
```bash
pip install llmgovernor[all]
```

Provider-specific installations:
```bash
pip install llmgovernor[openai]     # OpenAI support
pip install llmgovernor[anthropic]  # Anthropic support
pip install llmgovernor[bedrock]    # AWS Bedrock support
```

## Quick Start

```python
from llmgovernor import Fleet

# Initialize your fleet
fleet = Fleet(api_key="your-llmgovernor-api-key")

# Decorate your agent functions
@fleet.agent(name="research-assistant", budget_limit=50.00)
async def research_assistant(query: str):
    # Your agent logic here
    response = await openai_client.chat.completions.create(...)
    return response

# Monitor via dashboard
print(f"Dashboard: {fleet.dashboard_url}")
```

## Features

- **Real-time cost tracking** — Monitor LLM spend across providers
- **Budget enforcement** — Set limits per agent or fleet-wide
- **Usage analytics** — Detailed breakdowns by model, provider, and agent
- **Multi-provider support** — OpenAI, Anthropic, AWS Bedrock
- **Smart model routing** — Route to the right model for the job
- **Dashboard monitoring** — Web interface for fleet oversight

## Documentation

Full documentation: [llmgovernor.ai](https://llmgovernor.ai)

## License

MIT License — see LICENSE file for details.
