Skip to main content

The Ultimate Modular Autonomous Multi AI Agent Framework.

Project description


SuperAgentX: A lightweight autonomous true multi-agent framework with AGI capabilities.


Python 3.12+ GitHub Repo stars License: MIT

SuperAgentX - Multi-Agent, Browser Intelligence and MCP - Made Easy



Quick start

pip install superagentx

Install Playwright for Browser AI Automation

pip install playwright
playwright install

Browser AI Agent

import asyncio

from superagentx.agent import Agent
from superagentx.browser_engine import BrowserEngine
from superagentx.llm import LLMClient
from superagentx.prompt import PromptTemplate


async def main():
    llm_client: LLMClient = LLMClient(llm_config={'model': 'gpt-4.1', 'llm_type': 'openai'})

    prompt_template = PromptTemplate()

    browser_engine = BrowserEngine(
        llm=llm_client,
        prompt_template=prompt_template,

    )
    query_instruction = ("Which teams have won more than 3 FIFA World Cups, and which team is most likely to win the "
                         "next one?")

    fifo_analyser_agent = Agent(
        goal="Complete user's task.",
        role="You are a Football / Soccer Expert Reviewer",
        llm=llm_client,
        prompt_template=prompt_template,
        max_retry=1,
        engines=[browser_engine]
    )

    result = await fifo_analyser_agent.execute(
        query_instruction=query_instruction
    )

    print(result)


asyncio.run(main())

Run

$ export OPENAI_API_KEY=sk-******************

Key Features

🚀 Open-Source Framework: A lightweight, open-source AI framework built for multi-agent applications with Artificial General Intelligence (AGI) capabilities.

🎯 Goal-Oriented Multi-Agents: This technology enables the creation of agents with retry mechanisms to achieve set goals. Communication between agents is Parallel, Sequential, or hybrid.

🏖️ Easy Deployment: Offers WebSocket, RESTful API, and IO console interfaces for rapid setup of agent-based AI solutions.

♨️ Streamlined Architecture: Enterprise-ready scalable and pluggable architecture. No major dependencies; built independently!

📚 Contextual Memory: Uses SQL + Vector databases to store and retrieve user-specific context effectively.

🧠 Flexible LLM Configuration: Supports simple configuration options of various Gen AI models.

🤝 Extendable Handlers: Allows integration with diverse APIs, databases, data warehouses, data lakes, IoT streams, and more, making them accessible for function-calling features.

💎 Agentic RPA (Robotic Process Automation) – SuperAgentX enables computer-use automation for both browser-based and desktop applications, making it an ideal solution for enterprises looking to streamline operations, reduce manual effort, and boost productivity.

Table of contents

What is SuperAgentX?

The Ultimate Modular Autonomous Agentic AI Framework for Progressing Towards AGI.

SuperAgentX is an advanced agentic AI framework designed to accelerate the development of Artificial General Intelligence (AGI). It provides a powerful, modular, and flexible platform for building autonomous AI agents capable of executing complex tasks with minimal human intervention. By integrating cutting-edge AI technologies and promoting efficient, scalable agent behavior, SuperAgentX embodies a critical step forward in the path toward superintelligence and AGI. Whether for research, development, or deployment, SuperAgentX is built to push the boundaries of what's possible with autonomous AI systems.

Why SuperAgentX?

SuperAgentX addresses the growing need for highly capable, autonomous AI systems that can perform complex tasks with minimal human intervention. As we approach the limits of narrow AI, there's a need for an adaptable and scalable framework to bridge the gap toward AGI (Artificial General Intelligence). Here’s why SuperAgentX stands out:

Super: Cutting-edge AI systems with exceptional capabilities, paving the way to AGI (Artificial General Intelligence) and ASI (Artificial Super Intelligence).

Agent: Autonomous Multi AI agent framework designed to make decisions, act independently, and handle complex tasks.

X: The unknown, the limitless, the extra factor that makes SuperAgentX revolutionary, futuristic, and transformative.

Getting Started

pip install superagentx
Usage - Example SuperAgentX Code

This SuperAgentX example utilizes two handlers, Amazon and Walmart, to search for product items based on user input from the IO Console.

  1. It uses Parallel execution of handler in the agent
  2. Memory Context Enabled
  3. LLM configured to OpenAI
  4. Pre-requisites

Architecture

Large Language Models

Icon LLM Name                       Status
OpenAI
Azure OpenAI
AWS Bedrock
Google Gemini
Meta Llama
Ollama
Claude AI
Mistral AI
IBM WatsonX

Environment Setup

$ python3.12 -m pip install poetry
$ cd <path-to>/superagentx
$ python3.12 -m venv venv
$ source venv/bin/activate
(venv) $ poetry install

Documentation

License

SuperAgentX is released under the MIT License.

Project details


Release history Release notifications | RSS feed

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

superagentx-0.1.18.15b1.tar.gz (121.7 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

superagentx-0.1.18.15b1-py3-none-any.whl (155.7 kB view details)

Uploaded Python 3

File details

Details for the file superagentx-0.1.18.15b1.tar.gz.

File metadata

  • Download URL: superagentx-0.1.18.15b1.tar.gz
  • Upload date:
  • Size: 121.7 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: poetry/2.0.1 CPython/3.12.10 Darwin/24.6.0

File hashes

Hashes for superagentx-0.1.18.15b1.tar.gz
Algorithm Hash digest
SHA256 f8c421514ac5e911aa8304a39dd6dd53db9e6f658899aac5723f16d94421bba2
MD5 be9bbace996c81aa577685c693b14e11
BLAKE2b-256 1bbedbc8c58efa3415fe39ea283da00564dc86b6beba3d6483ba6b4de2402c83

See more details on using hashes here.

File details

Details for the file superagentx-0.1.18.15b1-py3-none-any.whl.

File metadata

  • Download URL: superagentx-0.1.18.15b1-py3-none-any.whl
  • Upload date:
  • Size: 155.7 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: poetry/2.0.1 CPython/3.12.10 Darwin/24.6.0

File hashes

Hashes for superagentx-0.1.18.15b1-py3-none-any.whl
Algorithm Hash digest
SHA256 d0130a3a173928e5641ad7e0bc91596eb348dc7dfee423085b898b526d117c02
MD5 d744dde5b569732a704f56fc70f7d2b3
BLAKE2b-256 85f752ce39bb9fa7b861910f174f1c09dafcd12b8e442438759514005f4c46d1

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page