AgentX

🤖 : Empowering Multi-Agents, Crafting a Collaborative Future. 🤖

AgentX is a framework dedicated to empowering a diverse range of agents to collaborate seamlessly, forging a future where agent teamwork and innovation thrive. Discover the world of limitless possibilities with AgentX!

The AgentX  offers a comprehensive set of functionalities for configuring and deploying autonomous AI agents. With AgentX, users can define and instantiate customized AI entities, each with a unique identity, capable of autonomous task planning and execution, as well as collaboration with other AI entities to achieve specific mission objectives. Furthermore, AgentX supports adaptive learning, enabling these AI agents to continuously enhance their performance through outcome analysis.

---

👨‍🚀 Getting Started

The easiest way to kickstart your journey with AgentX is by utilizing the bundled CLI for an automatic setup. This CLI takes care of a range of essential setup tasks for AgentX, including configuring crucial:

• 🔐 Environment variables (and API Keys)
• 📖 Documentation 🚧

Prerequisites 👆

Before diving headfirst into the world of AgentX, here's a checklist of prerequisites to ensure a smooth embarkation:

• Your favorite code editor; for instance, Visual Studio Code (VS Code)
• Rust - The language that empowers all to create robust and efficient software.
• Git
• Docker. After installation, create a Docker account, launch the Docker application, and sign in.
• An OpenAI API key
• A Serper API Key (optional)

Getting Started 🎊:

1. Open your preferred code editor

2. Fire up the Terminal - Typically, this can be achieved through a 'Terminal' tab or by employing a keyboard shortcut (e.g., Ctrl + ~ for Windows or Control + ~ for Mac in VS Code).

3. Clone the Repository and Navigate to the Directory - Once your terminal is live, clone the repository and dive into the project directory using the following commands.

   For Mac/Linux/Windows users :

   git clone https://github.com/OpenAgentX/AgentX.git
   cd AgentX
   export OPENAI_API_KEY='sk-your-openapi-key'
   cargo run -- -i "your task description"    

   For example, you can execute the following command:

   cargo run -- -i "Creating a snake game using python"  

4. Adhere to the Setup Instructions Provided by the Script -

Prepare to dive into the realm of limitless possibilities! 🎉

💡 Use Open-Source Models as Backends 🚧

Using an open-sourced model as the backend is based on an external server running LLM inference service.

🎯 Agent

Following agent are implemented.

name	Description
AutoGPT	🚧
MetaGPT	✅
AgentGPT	🚧
BabyAGI	🚧
GPT Researcher	✅ cargo run --example gpt_researcher -- --task YOUR TASK --report-type outline
CAMEL	🚧

🎉 Roadmap

While AgentX currently resides in the realm of beta, our comprehensive public roadmap outlines both achieved milestones and exciting future endeavors.

🚀 Tech Stack

• ✅ Rust: rust-lang A language that empowers individuals to craft reliable and high-performance software.
• ✅ OpenAI:🗃️ GPT instances for text generation
• ✅ Code Interpreter:🗃️ OpenAI's Code Interpreter running locally

✨ Demo 🚧

For the most immersive demo experience, we invite you to explore our dedicated site directly :)🚧

Demo Video 🚧

💬 Contact Information

Should you have any inquiries or suggestions regarding this project, please do not hesitate to reach out to us. Your feedback is immensely valuable and greatly appreciated!

• 🎃 Email: sxhx.liang@gamil.com
• 🎃 WeChat ID: sxhx_liang

For more technical inquiries, you can also create a new issue in our GitHub repository.

🎯 References

For each AI Agent family, we provide an array of representative applications published in prestigious journals and conferences, including but not limited to Nature, Science, PNAS, PRL, JACS, PIEEE, and more.

• Auto-GPT:An experimental open-source attempt to make GPT-4 fully autonomous.
• MetaGPT: Meta Programming for Multi-Agent Collaborative Framework
• AgentGPT: Assemble, configure, and deploy autonomous AI Agents in your browser.
• BabyAGI: This Python script is an example of an AI-powered task management system
• CAMEL: 🐫 CAMEL: Communicative Agents for “Mind” Exploration of Large Scale Language Model Society
• GPT Researcher: GPT based autonomous agent that does online comprehensive research on any given topic
• ResearchGPT: A LLM based research assistant that allows you to have a conversation with a research paper