This repository provides a practical, hands-on tutorial for building multi-agent systems from scratch using the CAMEL framework. It targets developers and researchers interested in Large Language Model (LLM) applications and agent societies, offering a structured learning path from basic agent components to complex applications like RAG.

How It Works

The tutorial guides users through the CAMEL framework, a leading multi-agent system framework. It breaks down agent construction into core components: Models, Messages, Prompt Engineering, Memory, and Tools. Users learn to build individual agents and then orchestrate them into societies and workforces, culminating in practical applications such as Retrieval-Augmented Generation (RAG) and integrated case studies.

Quick Start & Requirements

• Install CAMEL: pip install "camel-ai[all]==0.2.38"
• Requirements: Python 3.10-3.12.
• Setup: Follow the docs directory for theory and code directory for executable Jupyter notebooks.
• Links:
  • GitHub Pages: https://datawhalechina.github.io/handy-multi-agent/
  • Feishu Docs: https://fmhw1n4zpn.feishu.cn/docx/AF4XdOZpIo6TOaxzDK8cxInNnCe

Highlighted Details

• Comprehensive tutorial covering agent fundamentals, CAMEL framework, RAG, and integrated case studies.
• Practical, code-first approach with accompanying Jupyter notebooks for each chapter.
• Focus on building agent societies and workforces.
• Includes exercises and assignments to reinforce learning.

Maintenance & Community

The project is led by core contributors from DataWhale and CAMEL-AI. Community interaction is encouraged via GitHub Issues for feedback and Discussions for general exchange.

Licensing & Compatibility

Licensed under Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0). This license restricts commercial use and requires derivative works to be shared under the same terms.

Limitations & Caveats

The CC BY-NC-SA 4.0 license may restrict integration into commercial, closed-source projects. The roadmap indicates plans for more examples and new features, suggesting the project is still evolving.