Source: https://seerepo.com/compare/bojieli/ai-agent-book/vs/datahub-project/datahub
Markdown source: https://seerepo.com/compare/bojieli/ai-agent-book/vs/datahub-project/datahub.md
Description: ai-agent-book and datahub share 12 technologies: React, FastAPI, Google, anyio, AIOHTTP, Vite, beautifulsoup4, Pydantic, loguru, psutil, D3, and react-syntax-highlighter. Both are written in Python.

# ai-agent-book vs datahub

ai-agent-book and datahub share 12 technologies: React, FastAPI, Google, anyio, AIOHTTP, Vite, beautifulsoup4, Pydantic, loguru, psutil, D3, and react-syntax-highlighter. 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
- [datahub-project/datahub](https://seerepo.com/r/datahub-project/datahub): The Context Platform for your Data and AI Stack

## What they share and what sets them apart

- In common: React, FastAPI, Google, anyio, AIOHTTP, Vite, beautifulsoup4, Pydantic, loguru, psutil, D3, react-syntax-highlighter
- Only in ai-agent-book: uvicorn, azure-search-documents, azure-storage-blob, chromadb, psycopg2-binary, Postgres, pyarrow, OpenAI, Anthropic, Hugging Face, Mistral AI, PostHog, fastmcp, Flask, Next.js, Express, Astro, mkdocs-material, Rich, matplotlib, seaborn, Plotly, authlib, google-auth, google-auth-httplib2, google-auth-oauthlib, pyotp, accelerate, bitsandbytes, cut-cross-entropy, faiss-cpu, graphrag, lightgbm, mem0ai, minicpmo-utils, nltk, openai-whisper, raptor-rag, scikit-image, sentencepiece, trackio, triton, umap-learn, unsloth-zoo, xformers, xgboost, browser-use, torch, transformers, MCP, peft, datasets, tiktoken, unsloth, litellm, Ollama, scikit-learn, rank-bm25, groq, librosa, trl, fish-audio-sdk, snac, torchaudio, annoy, flagembedding, opencv-python, sentence-transformers, gradio-client, hnswlib, langchain-openai, memobase, mlx-audio, vLLM, lxml, python-magic, torchcodec, xlrd, xlsxwriter, pillow, python-pptx, pypdf2, reportlab, html2text, pypdf, python-docx, openpyxl, aiosmtplib, markdown, pdfplumber, pymupdf, sendgrid, youtube-transcript-api, yt-dlp, structlog, colorlog, pptxgenjs, sharp, Tailwind CSS, recharts, onnxruntime-node, class-variance-authority, tailwind-merge, Radix UI, Lucide, react-markdown, remark-gfm, fontsource-variable, katex
- Only in datahub: Spring, s3, spark-sql_2.12, org.springframework.kafka:spring-kafka, org.apache.iceberg:iceberg-core, org.apache.iceberg:iceberg-aws, AWS S3, Google Cloud Storage, Mixpanel, Sentry, pyspark, react-router-dom, React Router, history, click-spinner, org.springframework.security:spring-security-oauth2-jose, software.amazon.awssdk:sts, com.google.auth:google-auth-library-oauth2-http, software.amazon.awssdk:bedrockruntime, velocity-engine-core, jsonschema, io.swagger.parser.v3:swagger-parser, log4j-core, org.apache.logging.log4j:log4j-jul, python-json-logger, slf4j-log4j12, org.slf4j:slf4j-api, software.amazon.awssdk:regions, ch.qos.logback:logback-classic, ch.qos.logback:logback-core, docker, styled-components, Ant Design, antd, reactflow, visx, @remirror/react, react-intersection-observer, dnd-kit, @monaco-editor/react, rc-table, react-helmet-async, react-js-cron, react-color, @floating-ui/react-dom, react-diff-viewer, react-window, virtualizedtableforantd4, @phosphor-icons/react, @ant-design/icons, dompurify, js-yaml, html-to-image, mammoth, marked, turndown-plugin-gfm, opentelemetry

## Side by side

| | ai-agent-book | datahub |
|---|---|---|
| Size | 422,447 lines written, 1,067 code files | 2,991,794 lines written, 8,430 code files |
| Who writes it | 20.8% of its commits signed by AI. With Claude Code | 8.2% of its commits signed by AI. With Cursor, Claude Code, CodeRabbit, GitHub Copilot, and Devin |
| Activity | Last push October 8, 2026, 1,610 commits, 57,596 stars | Last push November 10, 2026, 16,381 commits, 12,975 stars |
| Tests | 624 test files. 34.3% of its code files have a test that imports them | 5,307 test files. 54% 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 datahub?

datahub, with 2,991,794 lines written; ai-agent-book has 422,447.

The proof: [datahub-project/datahub's code at commit 0d9b954](https://github.com/datahub-project/datahub/tree/0d9b95469f4b98109939b0c97826fa3787926604)

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

ai-agent-book, with 57,596 stars; datahub has 12,975.

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

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

datahub, with 5,307 test files; ai-agent-book has 624.

The proof: [datahub-project/datahub's code at commit 0d9b954](https://github.com/datahub-project/datahub/tree/0d9b95469f4b98109939b0c97826fa3787926604)

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

datahub: its last push was on November 10, 2026, and ai-agent-book's on October 8, 2026.

The proof: [datahub-project/datahub's commits on GitHub](https://github.com/datahub-project/datahub/commits)

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

ai-agent-book: an AI signed 20.8% of its commits, with Claude Code; in datahub, 8.2%.

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 10, 2026, at commit dbc046e (https://github.com/bojieli/ai-agent-book/tree/dbc046eb896ac4e39aa19c7774c8bf49583b89a6)
- datahub-project/datahub: Read on November 10, 2026, at commit 0d9b954 (https://github.com/datahub-project/datahub/tree/0d9b95469f4b98109939b0c97826fa3787926604)

## 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.