Grami AI: Dynamic AI Agent Framework¶
Welcome to Grami AI’s documentation!¶
Grami AI is a cutting-edge, flexible framework for creating dynamic and intelligent AI agents. Designed with modern Python async/await paradigms, Grami enables developers to build powerful AI-driven applications with ease.
Features¶
Multi-LLM Support: Compatible with multiple Language Models
Dynamic Agent Creation: Define agents with specific roles and capabilities
Streaming Responses: Token-by-token response generation
Extensible Tool Ecosystem: Easily add custom tools and capabilities
Asynchronous Design: Built for high-performance, non-blocking operations
Quick Start¶
Installation¶
pip install grami-ai
Basic Usage¶
from grami.agent import Agent
from grami.providers import GeminiProvider
from grami.tools import CalculatorTool
async def main():
math_agent = Agent(
name="MathAssistant",
role="Mathematical Problem Solver",
llm_provider=GeminiProvider(api_key="your_api_key"),
tools=[CalculatorTool()],
initial_context=[
{
"role": "system",
"content": "You are a helpful math assistant."
}
]
)
response = await math_agent.send_message("Calculate the area of a circle with radius 5")
print(response)
Supported Language Models¶
Google Gemini
OpenAI GPT
Anthropic Claude (Coming Soon)