unisonai 1.1

UnisonAI Multi-Agent Framework provides a flexible, light-weight experience and extensible environment for creating and coordinating multiple AI agents.

Table of Contents

• Overview

• Why UnisonAI?

• Installation

• Core Components

• Configuration

• Parameter Reference Tables

• Usage Examples

• FAQ

• Contributing And License

UnisonAI

Orchestrate the Future of Multi-Agent AI

---

Overview

UnisonAI is a flexible and extensible Python framework for building, coordinating, and scaling multiple AI agents—each powered by the LLM of your choice.

• Agent: For solo, focused tasks or as part of a clan for teamwork.

• Clan: For coordination and distributed problem-solving with multiple agents.

• Tool System: Easily augment agents with custom, pluggable tools (web search, time, APIs, your own logic).

Supports Cohere, Mixtral, Groq, Gemini, Grok, OpenAI, Anthropic, HelpingAI, and any custom model (just extend BaseLLM). UnisonAI is designed for real-world, production-grade multi-agent AI applications.

---

Quick Start

pip install unisonai

from unisonai import Agent

from unisonai.llms import Gemini

from unisonai import config



config.set_api_key("gemini", "your-api-key")

agent = Agent(

    llm=Gemini(model="gemini-2.0-flash"),

    identity="Assistant",

    description="A helpful AI assistant"

)

print(agent.unleash(task="Explain quantum computing"))

---

What Makes UnisonAI Special

UnisonAI stands out with its unique Agent-to-Agent (A2A) communication architecture, enabling seamless coordination between AI agents as if they were human team members collaborating on complex tasks.

A2A Communication Architecture

Latest Enhancements

• 🔒 Strong Type Validation: All tool parameters validated against ToolParameterType enum before execution

• 🛡️ Enhanced Error Handling: Comprehensive error catching with detailed metadata for debugging

• 📊 Standardized Results: All tools return ToolResult objects with success status and metadata

---

Perfect For:

• Complex Research Tasks: Multiple agents gathering, analyzing, and synthesizing information

• Workflow Automation: Coordinated agents handling multi-step business processes

• Content Creation: Specialized agents for research, writing, editing, and publishing

• Data Analysis: Distributed agents processing large datasets with different expertise

---

Core Components

| Component | Purpose | Key Features |

|-----------|---------|--------------|

| Agent | Standalone or clan member agent | Own history, tool integration, configurable LLMs, inter-agent messaging |

| Clan | Multi-agent orchestration | Team management, shared goals, coordinated execution |

| Tool System | Extensible capability framework | Type validation, error handling, standardized results |

---

Usage Examples

Individual Agent

from unisonai import Agent

from unisonai.llms import Gemini

from unisonai.tools.memory import MemoryTool



agent = Agent(

    llm=Gemini(model="gemini-2.0-flash"),

    identity="Research Assistant",

    description="An AI assistant with memory capabilities",

    tools=[MemoryTool]

)

agent.unleash(task="Store important project details")

Multi-Agent Clan

from unisonai import Agent, Clan



research_agent = Agent(llm=Gemini(), identity="Researcher", task="Gather information")

analysis_agent = Agent(llm=Gemini(), identity="Analyst", task="Analyze findings")



clan = Clan(

    clan_name="Research Team",

    manager=research_agent,

    members=[research_agent, analysis_agent],

    goal="Comprehensive market analysis"

)

clan.unleash()

Custom Tools

from unisonai.tools.tool import BaseTool, Field

from unisonai.tools.types import ToolParameterType



class CalculatorTool(BaseTool):

    def __init__(self):

        self.name = "calculator"

        self.description = "Mathematical operations"

        self.params = [

            Field(name="operation", field_type=ToolParameterType.STRING, required=True),

            Field(name="a", field_type=ToolParameterType.FLOAT, required=True),

            Field(name="b", field_type=ToolParameterType.FLOAT, required=True)

        ]

        super().__init__()



    def _run(self, operation: str, a: float, b: float) -> float:

        return a + b if operation == "add" else a * b

---

Configuration

API Keys

from unisonai import config



# Method 1: Configuration system

config.set_api_key("gemini", "your-key")

config.set_api_key("openai", "your-key")



# Method 2: Environment variables

export GEMINI_API_KEY="your-key"

export OPENAI_API_KEY="your-key"



# Method 3: Direct LLM initialization

llm = Gemini(api_key="your-key")

---

Documentation Hub

🚀 Getting Started

• Quick Start Guide - 5-minute setup guide

• Installation - Detailed installation options

📖 Core Documentation

• API Reference - Complete API documentation

• Architecture Guide - System design and patterns

• Usage Guidelines - Best practices and patterns

🛠️ Advanced Features

• Tool System Guide - Custom tool creation and validation

• Parameter Reference - Complete parameter documentation

💡 Examples & Tutorials

• Basic Examples - Simple agent patterns

• Advanced Examples - Multi-agent coordination

• Tool Examples - Custom tool implementations

---

FAQ

What is UnisonAI?

Python framework for building and orchestrating AI agents with A2A communication.

When should I use a Clan?

For complex, multi-step tasks requiring specialized agents working together.

Can I add custom LLMs?

Yes! Extend BaseLLM class to integrate any model provider.

What are tools?

Reusable components that extend agent capabilities (web search, APIs, custom logic).

How do I manage API keys?

Use config system, environment variables, or pass directly to LLMs.

---

Contributing

Founder: Anant Sharma (E5Anant)[https://github.com/E5Anant]

PRs and issues welcome! See our Contributing Guide.

Open Issues •

Submit PRs •

Suggest Features

---