ai-agent-book
View on GitHub《深入理解 AI Agent:设计原理与工程实践》(李博杰 著)开源主仓库:全书正文、编译版 PDF 与按章配套代码
Open-source book on AI agent design principles and engineering practice: full text in 15 languages, PDF/EPUB downloads, and 109 runnable companion experiments spanning context engineering, memory/RAG, MCP tools, coding agents, evaluation, post-training, and multi-agent collaboration.
Use Cases
Learn AI agent design principles and engineering practiceRun 109 chapter companion experimentsBuild a coding agent from scratchImplement RAG knowledge bases and structured indexesDesign cross-session user memory and knowledge graphsEvaluate agents with metrics and statistical significancePost-train models with SFT and RL for tool callingBuild multi-agent collaboration systemsBuild computer-use and voice-interaction agentsIntegrate tools and MCP servers into agentsApply context engineering and compression techniquesBuild agent self-evolution from run trajectories
Built With
- Language
- Python
- Frameworks
- OpenAI SDK · MCP · vLLM · Ollama · Unsloth · Playwright · Pydantic · browser-use · AWorld · tau-bench · uv
Tags
ai-agent · book · tutorial · multi-agent · context-engineering · agent-memory · rag · mcp · coding-agent · reinforcement-learning · agent-evaluation · computer-use · fine-tuning · multimodal · llm · python