AI Agent Book

Active
GitHub Python Apache-2.0

Description

ai-agent-book is an open-source AI agent textbook from Tsinghua, covering principles, tool calling, memory, planning and multi-agent.

Key Features

  • Structured textbook — from principles to engineering across the agent stack
  • Rich code samples — runnable Python / LangChain examples per chapter
  • Covers classics and new — ReAct, Reflexion, AutoGPT, CrewAI
  • Chinese narration — friendly for local readers with locally relevant examples
  • Diagram-rich — heavy use of diagrams and flowcharts
  • Continuously updated — active community tracking new methods

Use Cases

💡 Adopting as an AI agent course textbook for universities or bootcamps
💡 Reliable Chinese-language resource for self-learning agent systems
💡 Standard reading material for team training
💡 Reference for unifying concepts and terminology during research

Strengths & Limitations

Strengths

  • Actively maintained, recent updates
  • High community interest (44.4k stars)
  • Permissive open-source license (Apache-2.0)
  • Responsive to issues, low backlog

Quick Start

git clone https://github.com/bojieli/ai-agent-book.git
cd ai-agent-book
pip install -r requirements.txt
jupyter notebook

Related Projects

XAgent

8.5k · Python
Normal A

An autonomous LLM agent framework for complex task solving with automatic task decomposition, tool usage, and multi-step reasoning from the OpenBMB team

task-decompositionautonomous-agenttool-use +3
  • · Autonomous task decomposition and planning: Planner automatically breaks complex tasks into subtasks with execution milestones
  • · Secure sandbox execution: all operations run inside Docker containers for environment isolation and safety
  • · Extensible tool set: ToolServer provides file editing, Python Notebook, web browser, shell, and Rapid API tools