grami-ai 0.3.131

A dynamic and flexible AI agent framework for building intelligent, multi-modal AI agents

GRAMI-AI: Dynamic AI Agent Framework

📋 Table of Contents

• Overview
• Key Features
• Installation
• Quick Start
• Example Configurations
• Memory Providers
• Working with Tools
• Development Roadmap
• Communication Interfaces
• Contributing
• License

🌟 Overview

GRAMI-AI is a cutting-edge, async-first AI agent framework designed to solve complex computational challenges through intelligent, collaborative agent interactions. Built with unprecedented flexibility, this library empowers developers to create sophisticated, context-aware AI systems that can adapt, learn, and collaborate across diverse domains.

🚀 Key Features

• Async AI Agent Creation
• Multi-LLM Support (Gemini, OpenAI, Anthropic, Ollama)
• Extensible Tool Ecosystem
• Multiple Communication Interfaces
• Flexible Memory Management
• Secure and Scalable Architecture

💻 Installation

Using pip

pip install grami-ai==0.3.130

From Source

git clone https://github.com/YAFATEK/grami-ai.git
cd grami-ai
pip install -e .

🎬 Quick Start

import asyncio
from grami.agent import AsyncAgent
from grami.providers.gemini_provider import GeminiProvider

async def main():
    agent = AsyncAgent(
        name="AssistantAI",
        llm=GeminiProvider(api_key="YOUR_API_KEY"),
        system_instructions="You are a helpful digital assistant."
    )

    response = await agent.send_message("Hello, how can you help me today?")
    print(response)

asyncio.run(main())

🔧 Example Configurations

1. Async Agent with Memory

from grami.memory.lru import LRUMemory

agent = AsyncAgent(
    name="MemoryAgent",
    llm=provider,
    memory=LRUMemory(capacity=100)
)

2. Async Agent with Streaming

async for token in agent.stream_message("Tell me a story"):
    print(token, end='', flush=True)

💾 Memory Providers

GRAMI-AI supports multiple memory providers:

1. LRU Memory: Local in-memory cache
2. Redis Memory: Distributed memory storage

LRU Memory Example

from grami.memory import LRUMemory

memory = LRUMemory(capacity=50)

Redis Memory Example

from grami.memory import RedisMemory

memory = RedisMemory(
    host='localhost',
    port=6379,
    capacity=100
)

🛠 Working with Tools

Creating Tools

Tools are simple Python functions used by AI agents:

def get_current_time() -> str:
    return datetime.now().strftime("%Y-%m-%d %H:%M:%S")

def calculate_age(birth_year: int) -> int:
    current_year = datetime.now().year
    return current_year - birth_year

Adding Tools to AsyncAgent

agent = AsyncAgent(
    name="ToolsAgent",
    llm=gemini_provider,
    tools=[get_current_time, calculate_age]
)

🌐 Communication Interfaces

GRAMI-AI supports multiple communication interfaces, including WebSocket for real-time, bidirectional communication between agents.

WebSocket Communication

Create a WebSocket-enabled agent using the built-in setup_communication() method:

from grami.agent import AsyncAgent
from grami.providers.gemini_provider import GeminiProvider
from grami.memory.lru import LRUMemory

# Create an agent with WebSocket communication
agent = AsyncAgent(
    name="ToolsAgent", 
    llm=GeminiProvider(api_key=os.getenv('GEMINI_API_KEY')),
    memory=LRUMemory(capacity=100),
    tools=[calculate_area, generate_fibonacci]
)

# Setup WebSocket communication
communication_interface = await agent.setup_communication(
    host='localhost', 
    port=0  # Dynamic port selection
)

Key Features of WebSocket Communication

• Real-time bidirectional messaging
• Dynamic port allocation
• Seamless tool and LLM interaction
• Secure communication channel

Example Use Cases

• Distributed AI systems
• Real-time collaborative agents
• Interactive tool-based services
• Event-driven agent communication

🗺 Development Roadmap

Core Framework Design

• Implement AsyncAgent base class with dynamic configuration
• Create flexible system instruction definition mechanism
• Design abstract LLM provider interface
• Develop dynamic role and persona assignment system
• Comprehensive async example configurations
  • Memory with streaming
  • Memory without streaming
  • No memory with streaming
  • No memory without streaming
• Implement multi-modal agent capabilities (text, image, video)

LLM Provider Abstraction

• Unified interface for diverse LLM providers
  • Google Gemini integration (start_chat(), send_message())
    • Basic message sending
    • Streaming support
    • Memory integration
  • OpenAI ChatGPT integration
    • Basic message sending
    • Streaming implementation
    • Memory support
  • Anthropic Claude integration
  • Ollama local LLM support
• Standardize function/tool calling across providers
• Dynamic prompt engineering support
• Provider-specific configuration handling

Communication Interfaces

• WebSocket real-time communication
• REST API endpoint design
• Kafka inter-agent communication
• gRPC support
• Event-driven agent notification system
• Secure communication protocols

Memory and State Management

• Pluggable memory providers
  • In-memory state storage
  • Redis distributed memory
  • DynamoDB scalable storage
  • S3 content storage
• Conversation and task history tracking
• Global state management for agent crews
• Persistent task and interaction logs
• Advanced memory indexing
• Memory compression techniques

Tool and Function Ecosystem

• Extensible tool integration framework
• Default utility tools
  • Kafka message publisher
  • Web search utility
  • Content analysis tool
• Provider-specific function calling support
• Community tool marketplace
• Easy custom tool development

Agent Crew Collaboration

• Inter-agent communication protocol
• Workflow and task delegation mechanisms
• Approval and review workflows
• Notification and escalation systems
• Dynamic team composition
• Shared context and memory management

Use Case Implementations

• Digital Agency workflow template
  • Growth Manager agent
  • Content Creator agent
  • Trend Researcher agent
  • Media Creation agent
• Customer interaction management
• Approval and revision cycles

Security and Compliance

• Secure credential management
• Role-based access control
• Audit logging
• Compliance with data protection regulations

Performance and Scalability

• Async-first design
• Horizontal scaling support
• Performance benchmarking
• Resource optimization

Testing and Quality

• Comprehensive unit testing
• Integration testing for agent interactions
• Mocking frameworks for LLM providers
• Continuous integration setup

Documentation and Community

• Detailed API documentation
• Comprehensive developer guides
• Example use case implementations
• Contribution guidelines
• Community tool submission process
• Regular maintenance and updates

Future Roadmap

• Payment integration solutions
• Advanced agent collaboration patterns
• Specialized industry-specific agents
• Enhanced security features
• Extended provider support

🤝 Contributing

Contributions are welcome! Please read our contributing guidelines and code of conduct.

📄 License

This project is licensed under the MIT License.