Multi-Agent Systems with Autogen
How to think about, build, evaluate and deploy multi-agent apps
- Core components for multi-agent systems and their implementation
- UX design principles for multi-agent systems
- Interface agents - agents that solve tasks by driving web, mobile, desktop UIs.
- Evaluating systems using benchmarks like GAIA and SWEBench
- Performance optimization through tuning and parallel processing
- Use cases like data analysis, customer service, and creativity workflows
Published on multiagentbook.com
"Chapter 1 of the book is exceptionally well-written and provides a comprehensive understanding of the AutoGen framework. The detailed explanations and clarity in presenting the concepts are truly commendable. I particularly appreciate the effort put into making the content accessible and engaging for readers."
"Few months ago I had mixed feelings on Microsoft AutoGen. I tried it again after seeing Matthew Berman video on AutoGen Studio https://lnkd.in/d7Hse2Tg My reaction was 🤩🤩🤩 Thanks to the Microsoft Research team for the great job! I see incredible improvements and real life usage scenarios!"
"Autogen Studio is a real game changer here imho."
"Autogen gave me the same a-ha moment that I haven't felt since trying out GPT-3 for the first time."
"The same reason autogen is significant is the same reason OOP is a good idea. Autogen packages up all that complexity into an agent I can create in one line, or modify with another."
Book Chapter Guide
Multi-Agent Code Samples
Explore real-world examples of multi-agent systems across different frameworks and domains.
Loading usecases...
About the Author
Multi-Agent Systems with AutoGen is being written by leaders in the emerging field of multi-agent systems and generative AI applications.
Victor Dibia
Principal Research Software Engineer, Microsoft Research
Victor Dibia (PhD) is a Principal Research Software Engineer at Microsoft Research, where he has contributed to projects like GitHub Copilot that serves millions of customers. He is the creator of AutoGen Studio , a low-code tool for prototyping multi-agent applications, a core contributor to AutoGen, a multi-agent framework for AI applications, and LIDA, a widely used tool for automated visualizations using generative AI models. Victor holds a PhD in Information Systems from City University of Hong Kong, an MSc in Computer Science from Carnegie Mellon University and was previously at Cloudera and IBM Research.
Frequently Asked Questions
Can't find the answer you're looking for? Reach out on the GitHub repository
- Is the book limited to AutoGen?
- No. Across the book, the goal is to teach core principles and AutoGen is used as a tool to illustrate these principles. We expect that these principles can be implemented in any sufficiently expressive multi-agent framework
- How can I get the book?
- The book is being developed independently after the Manning cancellation. Stay tuned for updates on availability and pricing.
- Can I use multiple models with the agents described in the book?
- Yes! AutoGen natively supports multiple generative AI model providers - OpenAI , Microsoft Azure OpenAI, Google gemini models, Anthropic , Cohere, Groq, Mistral etc. Learn more here.
- Is there a GitHub repository for the book?
- Yes! The GitHub repository for the book is available at victordibia/multiagent-systems-with-autogen. Take a look, open issues, and share your thoughts!
- What will the book cover?
- Great question! There is a chapter outline where you see what chapters are planned and completed in the book. You can view the chapter guide here
- Who is the book for?
This book is ideal for you if you are:
- A software developer looking to expand your skills in AI-driven applications and leverage multi-agent systems for complex problem-solving
- An AI practitioner interested in understanding and applying multi-agent architectures within existing AI projects
- A system architect or engineer aiming to design more efficient and sophisticated AI solutions that require orchestration of multiple AI agents
- A technical product manager seeking a deeper understanding of multi-agent AI technologies to oversee the development of advanced AI features in products
- A designer looking to create intuitive user interfaces that are based on a multi-agent solution stack
Note: This book is developer-focused and practical. It is not written or intended as theoretical or academic text.- I found some errors or have feedback, how can I report them?
- Yes, thank you! Please report any errors or provide feedback via the GitHub repository issues
Acknowledgement
This project has benefited from the support and contributions of many individuals, especially the members of the AutoGen Open Source Community.