Source: https://seerepo.com/compare/bojieli/ai-agent-book/vs/microsoft/RD-Agent
Markdown source: https://seerepo.com/compare/bojieli/ai-agent-book/vs/microsoft/RD-Agent.md
Description: ai-agent-book and RD-Agent share 26 technologies: pyarrow, OpenAI, Hugging Face, Flask, Vite, Rich, matplotlib, seaborn, Plotly, accelerate, torch, transformers, peft, datasets, tiktoken, litellm, scikit-learn, rank-bm25, trl, vLLM, beautifulsoup4, pypdf, pymupdf, Pydantic, loguru, and katex. Both are written in Python.

# ai-agent-book vs RD-Agent

ai-agent-book and RD-Agent share 26 technologies: pyarrow, OpenAI, Hugging Face, Flask, Vite, Rich, matplotlib, seaborn, Plotly, accelerate, torch, transformers, peft, datasets, tiktoken, litellm, scikit-learn, rank-bm25, trl, vLLM, beautifulsoup4, pypdf, pymupdf, Pydantic, loguru, and katex. Both are written in Python.

- [bojieli/ai-agent-book](https://seerepo.com/r/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
- [microsoft/RD-Agent](https://seerepo.com/r/microsoft/RD-Agent): Research and development (R&D) is crucial for the enhancement of industrial productivity, especially in the AI era, where the core aspects of R&D are mainly focused on data and models. We are committed to automating these high-value generic R&D processes through R&D-Agent, which lets AI drive data-driven AI. 🔗https://aka.ms/RD-Agent-Tech-Report

## What they share and what sets them apart

- In common: pyarrow, OpenAI, Hugging Face, Flask, Vite, Rich, matplotlib, seaborn, Plotly, accelerate, torch, transformers, peft, datasets, tiktoken, litellm, scikit-learn, rank-bm25, trl, vLLM, beautifulsoup4, pypdf, pymupdf, Pydantic, loguru, katex
- Only in ai-agent-book: React, uvicorn, FastAPI, azure-search-documents, azure-storage-blob, chromadb, psycopg2-binary, Postgres, Anthropic, Google, PostHog, fastmcp, anyio, AIOHTTP, Next.js, Express, Astro, mkdocs-material, authlib, google-auth, google-auth-httplib2, google-auth-oauthlib, pyotp, bitsandbytes, cut-cross-entropy, faiss-cpu, lightgbm, mem0ai, nltk, openai-whisper, scikit-image, sentencepiece, triton, xformers, MCP, Ollama, groq, librosa, snac, torchaudio, opencv-python, sentence-transformers, langchain-openai, mlx-audio, lxml, python-magic, torchcodec, xlrd, xlsxwriter, pillow, python-pptx, pypdf2, reportlab, html2text, python-docx, openpyxl, markdown, pdfplumber, sendgrid, youtube-transcript-api, yt-dlp, structlog, psutil, pptxgenjs, sharp, Tailwind CSS, D3, recharts, onnxruntime-node, class-variance-authority, tailwind-merge, Radix UI, react-syntax-highlighter, Lucide, react-markdown, remark-gfm
- Only in RD-Agent: werkzeug, tables, Kaggle, flask-cors, Streamlit, Vue, vue-router, furo, sphinx-rtd-theme, gym, pydantic-ai-slim, pyserini, spaCy, MLflow, LangChain, myst-parser, nbformat, genson, docker, Prefect, github-markdown-css, Element, echarts, highlight.js, marked, markdown-it, markdown-it-texmath, prismjs

## Side by side

| | ai-agent-book | RD-Agent |
|---|---|---|
| Size | 422,447 lines written, 1,067 code files | 83,518 lines written, 505 code files |
| Who writes it | 20.8% of its commits signed by AI. With Claude Code | 0.7% of its commits signed by AI. With GitHub Copilot and Claude Code |
| Activity | Last push October 8, 2026, 1,610 commits, 57,240 stars | Last push October 21, 2026, 1,013 commits, 15,282 stars |
| Tests | 624 test files. 34.3% of its code files have a test that imports them | 41 test files. 9.5% of its code files have a test that imports them |

- Size: Lines written by people and agents, without generated ones; code files, without tests.
- Who writes it: A commit counts as AI's when it carries its signature: a Co-Authored-By line, its author name or the merge of its branch.
- Activity: From GitHub and its history, on the day SeeRepo read it.
- Tests: The files that test the code, and the share of code files a test imports.

## Frequently asked questions

### Which is bigger, ai-agent-book or RD-Agent?

ai-agent-book, with 422,447 lines written; RD-Agent has 83,518.

The proof: [bojieli/ai-agent-book's code at commit dbc046e](https://github.com/bojieli/ai-agent-book/tree/dbc046eb896ac4e39aa19c7774c8bf49583b89a6)

### Which has more GitHub stars, ai-agent-book or RD-Agent?

ai-agent-book, with 57,240 stars; RD-Agent has 15,282.

The proof: [bojieli/ai-agent-book on GitHub](https://github.com/bojieli/ai-agent-book)

### Which has more tests, ai-agent-book or RD-Agent?

ai-agent-book, with 624 test files; RD-Agent has 41.

The proof: [bojieli/ai-agent-book's code at commit dbc046e](https://github.com/bojieli/ai-agent-book/tree/dbc046eb896ac4e39aa19c7774c8bf49583b89a6)

### Which was updated more recently, ai-agent-book or RD-Agent?

RD-Agent: its last push was on October 21, 2026, and ai-agent-book's on October 8, 2026.

The proof: [microsoft/RD-Agent's commits on GitHub](https://github.com/microsoft/RD-Agent/commits)

### Which has more commits signed by AI, ai-agent-book or RD-Agent?

ai-agent-book: an AI signed 20.8% of its commits, with Claude Code; in RD-Agent, 0.7%.

The proof: [the commits each tool signed in bojieli/ai-agent-book](https://seerepo.com/r/bojieli/ai-agent-book/ai)

## Sources

- bojieli/ai-agent-book: Read on November 5, 2026, at commit dbc046e (https://github.com/bojieli/ai-agent-book/tree/dbc046eb896ac4e39aa19c7774c8bf49583b89a6)
- microsoft/RD-Agent: Read on November 8, 2026, at commit 484776c (https://github.com/microsoft/RD-Agent/tree/484776c211e4fbbeef03e0ec00d6bbee7362a4f4)

## What is your repo built with?

Any public repo, with no account: https://seerepo.com/r/owner/repo/built, with the owner and name it has on GitHub.