📌Overview

Purpose: Upsonic aims to provide a reliable framework for building and deploying trusted agent workflows in real-world applications.

Overview: Upsonic is a next-generation, reliability-focused framework designed to make agents production-ready by addressing key challenges in reliability, tool integration, and execution flexibility. It enhances agent workflows with advanced features that simplify the development process and ensure high-quality outcomes.

Key Features:

Production-Ready Scalability: Easily deploy agents on cloud platforms like AWS and GCP or locally with Docker, ensuring robust scalability.
Task-Centric Design: Focuses on practical task execution with multiple levels of complexity, ranging from basic LLM tasks to advanced automation using integrated tools.
Model Context Protocol (MCP) Integration: Simplifies the use of third-party tools and custom tools without extensive coding, enhancing functionality across applications.
Multi-Agent Support: Facilitates effective task distribution and collaborative problem-solving through automated task management.
Reliability Layers: Implements a multi-layered approach to ensure output accuracy, including verifier and editor agents that enhance the quality of outputs through iterative feedback and control.
Direct LLM Calls: Enables quick and economical execution of simple tasks without overhead, maintaining structured output organization.

Upsonic Framework

Introduction

Upsonic is a reliability-focused framework designed for real-world applications, enabling trusted agent workflows in organizations through advanced reliability features such as verification layers and validator agents.

Why Choose Upsonic?

Upsonic addresses three critical challenges to make agents production-ready:

Reliability: Easy-to-activate reliability layers without complex coding.
Model Context Protocol (MCP): Leverage diverse tools developed by official and third-party sources.
Secure Runtime: Provides an isolated environment to run agents.

📊 Reliability Layer

Upsonic employs a multi-layered reliability system to enhance output accuracy via:

Verifier Agent: Validates outputs, tasks, and formats.
Editor Agent: Refines outputs based on verifier feedback.
Rounds: Implements iterative quality improvement through scored verification cycles.
Loops: Ensures accuracy through controlled feedback loops.

Reliability Benchmark Results

Name	Reliability Score %
Upsonic	99.3
CrewAI	87.5
Langgraph	6.3

Key Features

Production-Ready Scalability: Deploy on AWS, GCP, or locally with Docker.
Task-Centric Design: Focus on practical execution, with options for basic and advanced tasks.
MCP Server Support: For high-performance tasks with multi-client processing.
Tool-Calling Server: Secure tool management with server API interactions.
Integration of Custom Tools: Add tools with ease.

📙 Documentation

Access the documentation at docs.upsonic.ai.

🛠️ Getting Started

Prerequisites

Python 3.10 or higher
Access to OpenAI or Anthropic API keys

Installation

pip install upsonic

Basic Example

Set your OPENAI_API_KEY and start the agent:

export OPENAI_API_KEY=sk-***

from upsonic import Task, Agent

task = Task("Who developed you?")
agent = Agent("Coder")
agent.print_do(task)

Tool Integration via MCP

Upsonic supports the Model Context Protocol (MCP).

Example of integrating a tool:

from upsonic import Agent, Task, ObjectResponse

class FetchMCP:
    command = "uvx"
    args = ["mcp-server-fetch"]

class WebContent(ObjectResponse):
    title: str
    content: str
    summary: str

web_agent = Agent("Web Content Analyzer", model="openai/gpt-4o")
task = Task(
    description="Fetch and analyze web content.",
    context=["https://upsonic.ai"],
    tools=[FetchMCP],
    response_format=WebContent
)

result = web_agent.print_do(task)
print(result.title)
print(result.summary)

Direct LLM Call

Direct LLM calls for simple tasks:

from upsonic import Task, Direct

direct = Direct(model="openai/gpt-4o")
task = Task("Where can I use agents in real life?")
direct.print_do(task)

Telemetry

Anonymous telemetry collects usage data. Disable it by setting the environment variable:

import os
os.environ["UPSONIC_TELEMETRY"] = "False"