Metadata-Version: 2.4
Name: plugai
Version: 0.1.0
Summary: A lightweight, zero-dependency alternative to LangChain for Agentic AI
Home-page: https://github.com/yourusername/plugai
Author: PlugAI
Classifier: Programming Language :: Python :: 3
Classifier: License :: OSI Approved :: MIT License
Classifier: Operating System :: OS Independent
Classifier: Topic :: Software Development :: Libraries :: Application Frameworks
Requires-Python: >=3.8
Description-Content-Type: text/markdown
Dynamic: author
Dynamic: classifier
Dynamic: description
Dynamic: description-content-type
Dynamic: home-page
Dynamic: requires-python
Dynamic: summary

# PlugAI

A lightweight, zero-dependency alternative to LangChain for Agentic AI.

## Features
- **Zero Dependencies**: Core logic relies purely on standard Python. Bring your own LLM client.
- **Instant Tools**: Wrap any Python function with `@tool` to automatically generate JSON schemas.
- **Built-in Memory Safety**: Automatic memory pruning prevents token limit crashes.
- **Provider Agnostic**: Swap seamlessly between OpenAI, Groq, Anthropic, or local models.

## Quick Start

```python
import os
from groq import Groq
from plugai import PlugAgent, tool, GroqProvider

@tool
def get_weather(location: str) -> str:
    """Gets the current weather for a specific location."""
    return f"The weather in {location} is 72°F and sunny."

client = Groq(api_key=os.getenv("GROQ_API_KEY"))
provider = GroqProvider(client)

agent = PlugAgent(
    provider=provider,
    model="llama-3.3-70b-versatile",
    tools=[get_weather]
)

response = agent.run("What is the weather in Tokyo?")
print(response)
```
