⭐ If you find this repository helpful, please consider giving it a ⭐ here on GitHub (click the star button in the top right corner) It's a quick way to show support for this openly available code. ⭐
AI Agents - The definitive Guide
This is the corresponding code for the book AI Agents - The definitive Guide The book can be found here
TOC
- Chapter 1 From LLMs to Agents: The Foundational Blueprint
- Chapter 2 Architectures and Patterns: Planning, Reactivity, and Multi-Agent-Systems
- Chapter 3 Advanced Planning, Reasoning, and Scalable Execution in Agents
- Chapter 4 Models Behind the Agents: Capabilities and Optimization
- Chapter 5 Interfaces and Tooling: System Integration and Execution
- Chapter 6 Deploying Agents in Real Products
- Chapter 7 Benchmarking LLMs and Agentic Systems for Production
- Chapter 8 Multimodal and Domain-Specific Benchmarks
- Chapter 9 Safety, Guardrails, and Risk Mitigation
- Chapter 10 Memory, Autonomy, and Long-Horizon Use
- Chapter 11 Cost Estimation and Efficiency Optimization
- Chapter 12 Future Directions
Instructions and Navigation
All of the code is organized into folders. Each folder starts with CH followed by the chapter number. For example, CH01.
The notebooks are then organized as follows: ch01_attention_mechanism_variations.ipynb, where ch01 indicates the chapter
and attention_mechanism_variations what is done in the notebook.
Repo structure
├── LICENSE
├── README.md <- The top-level README for developers using this project.
├── CH01 <- Per chapter folder with Jupyter notebooks.
├── [name].ipynb <- Jupyter notebooks with naming as mentioned above.
├── CH02 <- Per chapter folder with Jupyter notebooks.
... <- Same structure for all chapters.
├── utils <- Custom classes and functions and utility functions.
├── resources <- Some miscellaneous resources.
Running the Notebooks
Every notebook contains buttons so that the notebook can be oppend and run on Google Colab like this:
[
]()
NOTE: You may need to run the notebooks with a GPU.