# bojieli/ai-agent-book

《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

Repository: https://github.com/bojieli/ai-agent-book
Canonical: https://ross.abutalabs.com/products/ai-agent-book
Language: Python
License: Apache-2.0
License Family: permissive
Topics: agent, agent-memory, ai-agent, book, coding-agent, context-engineering, large-language-models, llm, mcp, multi-agent, multimodal, rag, reinforcement-learning
Last push: 2026-08-26T15:32:04+00:00

## Health v2 (maintenance only)
Score: 71/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 99, release rhythm 60, longevity 25
- inputs: {"age_days": 358, "days_push": 7, "days_rel": 43, "gap_med": null, "n_releases_24m": 1}
- flags: prerelease_only
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 42509, forks 4700 (observed 2026-08-28T04:12:08.811537+00:00)

## What it is
An open-source Chinese-language book, 'AI Agents in Depth: Design Principles and Engineering Practice', covering AI agent design across 10 chapters with 103+ hands-on companion experiments. The repository contains the full book text, compiled PDF/EPUB releases in 14 languages, and per-chapter code examples.

## Use cases
- learn how AI agents work from first principles
- study agent memory and context engineering
- find hands-on labs for building LLM agents
- understand multi-agent and multimodal agent design
- learn RAG and MCP in an agent context
- get a free ebook on AI agent engineering
- learn how coding agents are built

## When to choose
- you want a structured, chapter-based curriculum on AI agents with runnable experiments
- you prefer reading a comprehensive book over scattered blog posts
- you need multilingual (Chinese/English/etc.) agent learning material
- you want to understand both theory and production engineering of agents

## When to avoid
- you need a production-ready agent framework or library rather than educational material
- you want a quick reference or API documentation
- you need a non-Python codebase for your stack

## Facets
- artifact type: learning-resource
- maturity: active
- function: agent-framework, rag, mcp, llm-training, documentation
- domain: artificial-intelligence, large-language-models, tutorials, education
- platform: python, cross-platform
- tags: open-source-book, ai-agents, context-engineering, multi-agent, exercises, ebook, pdf, multilingual, retrieval-augmented-generation

## Member repositories
- bojieli/ai-agent-book (main) score 71

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:12:08.811537+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T16:22:38.359088+00:00, confidence not recorded.
  - readme: https://github.com/bojieli/ai-agent-book (fetched 2026-08-28T04:12:08.811537+00:00, sha 1097c2dcb52b)
- Data as of 2026-08-30T08:39:29.467469+00:00.