Source: https://seerepo.com/compare/bojieli/ai-infra-book/vs/datawhalechina/hello-agents
Markdown source: https://seerepo.com/compare/bojieli/ai-infra-book/vs/datawhalechina/hello-agents.md
Description: ai-infra-book and hello-agents share 40 technologies: FastAPI, Redis, Hugging Face, anyio, Flask, starlette, uvicorn, AIOHTTP, cycler, fonttools, contourpy, Gradio, Plotly, seaborn, matplotlib, alembic, SQLAlchemy, Google, accelerate, MCP, OpenAI, peft, scikit-learn, spaCy, tiktoken, torch, transformers, safetensors, datasets, tokenizers, lxml, markdown, pillow, pymupdf, jinja2, annotated-types, jsonschema, Pydantic, OpenTelemetry, and loguru. Both are written in Python.

# ai-infra-book vs hello-agents

ai-infra-book and hello-agents share 40 technologies: FastAPI, Redis, Hugging Face, anyio, Flask, starlette, uvicorn, AIOHTTP, cycler, fonttools, contourpy, Gradio, Plotly, seaborn, matplotlib, alembic, SQLAlchemy, Google, accelerate, MCP, OpenAI, peft, scikit-learn, spaCy, tiktoken, torch, transformers, safetensors, datasets, tokenizers, lxml, markdown, pillow, pymupdf, jinja2, annotated-types, jsonschema, Pydantic, OpenTelemetry, and loguru. Both are written in Python.

- [bojieli/ai-infra-book](https://seerepo.com/r/bojieli/ai-infra-book): 《深入理解 AI Infra：量化分析与系统设计》（李博杰 著）开源书稿：从硬件约束和模型架构出发，量化推导 LLM 推理与训练系统设计。含全书正文、PDF、配套计算工具与实验
- [datawhalechina/hello-agents](https://seerepo.com/r/datawhalechina/hello-agents): 📚 《从零开始构建智能体》——从零开始的智能体原理与实践教程

## What they share and what sets them apart

- In common: FastAPI, Redis, Hugging Face, anyio, Flask, starlette, uvicorn, AIOHTTP, cycler, fonttools, contourpy, Gradio, Plotly, seaborn, matplotlib, alembic, SQLAlchemy, Google, accelerate, MCP, OpenAI, peft, scikit-learn, spaCy, tiktoken, torch, transformers, safetensors, datasets, tokenizers, lxml, markdown, pillow, pymupdf, jinja2, annotated-types, jsonschema, Pydantic, OpenTelemetry, loguru
- Only in ai-infra-book: blobfile, gitdb, huey, pyarrow, s3fs, s3transfer, smart-open, tensorboard-data-server, transferqueue, pyzmq, Anthropic, flask-cors, graphene, graphql-core, graphql-relay, hypercorn, jupyter-core, kui, Lightning, quart, tornado, werkzeug, Ray, mkdocs-material, blessed, kaleido, matplotlib-inline, prompt-toolkit, pyecharts, cryptography, itsdangerous, apache-tvm-ffi, comet-ml, cuda-core, cuda-python, cuda-toolkit, cupy-cuda13x, decord2, descript-audio-codec, e2b, einx, emerging-optimizers, evaluate, fla-core, flash-linear-attention, flashinfer-cubin, flashinfer-python, jaxlib, llvmlite, loralib, mamba-ssm, math-verify, megatron-bridge, mistral-common, ml-dtypes, MLflow, mlx, mlx-lm, mooncake-transfer-engine-cuda13, nixl, nltk, nvidia-cublas, nvidia-cudnn-cu12, nvidia-cudnn-cu13, nvidia-cudnn-frontend, nvidia-cufft, nvidia-cusolver, nvidia-cusparse, nvshmem4py-cu13, onnx-ir, onnxscript, open-clip-torch, openai-agents, opt-einsum, pythainlp, qwen-vl-utils, rouge-score, sacrebleu, sentencepiece, sglang-router, silero-vad, sklearn-crfsuite, skops, spacy-legacy, stanza, thinc, timm, torch-c-dlpack-ext, torchvision, tensordict, triton, einops, flash-attn, megatron-core, xformers, ONNX, deepspeed, diffusers, jax, librosa, torchaudio, causal-conv1d, cuda-bindings, ModelScope, nvidia-cuda-runtime, torchdata, transformer-engine, cairosvg, defusedxml, imageio, imageio-ffmpeg, mako, markdown-it-py, markupsafe, mdurl, nbformat, pylatexenc, pytablewriter, python-magic, av, dacite, fastjsonschema, jsonschema-specifications, pathvalidate, referencing, typepy, msgspec, aiobotocore, boto3, botocore, colorlog, docker, gpustat, Gunicorn, opencensus-context, opentelemetry-exporter-prometheus, opentelemetry-semantic-conventions, spacy-loggers, swanlab, psutil, prometheus-client
- Only in hello-agents: aiosqlite, asyncpg, psycopg2-binary, Postgres, chromadb, SQLite, libsql-client, oracledb, pymilvus, Qdrant, python, React, react-dom, fastmcp, Streamlit, Vite, Vue, vue-router, react-router-dom, soupsieve, ipywidgets, Rich, python-jose, passlib, bcrypt, bitsandbytes, camel-ai, mermaid, onnxruntime, tavily-python, textblob, hello-agents, agentscope, sentence-transformers, autogen-agentchat, autogen-ext, langchain-openai, langdetect, LangGraph, paddlenlp, rank-bm25, imaplib2, openpyxl, pdfminer.six, pypdf, python-docx, reportlab, xlrd, pdfplumber, feedparser, pypdf2, beautifulsoup4, pymupdf4llm, email-validator, kubernetes, opentelemetry-exporter-otlp-proto-grpc, ant-design-vue, D3, @ant-design/icons-vue, katex, Tailwind CSS, markdown-it, vue-flow, @monaco-editor/loader, Chart.js, vue-chartjs, highlight.js, dompurify, marked, react-markdown, Element, vue-echarts, echarts, @element-plus/icons-vue, Leaflet, @amap/amap-jsapi-loader, html2canvas, jspdf

## Side by side

| | ai-infra-book | hello-agents |
|---|---|---|
| Size | 1,438,355 lines written, 1,748 code files | 251,996 lines written, 1,282 code files |
| Who writes it | 16.6% of its commits signed by AI. With Claude Code and Codex | 3.6% of its commits signed by AI. With Codex, Claude Code, and Cursor |
| Activity | Last push October 1, 2026, 314 commits, 8,032 stars | Last push November 13, 2026, 670 commits, 87,189 stars |
| Tests | 1,093 test files. 17.8% of its code files have a test that imports them | 103 test files. 6.5% 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-infra-book or hello-agents?

ai-infra-book, with 1,438,355 lines written; hello-agents has 251,996.

The proof: [bojieli/ai-infra-book's code at commit 3bdcb4f](https://github.com/bojieli/ai-infra-book/tree/3bdcb4fcab73010eeaccf31cc10a8242a895d82e)

### Which has more GitHub stars, ai-infra-book or hello-agents?

hello-agents, with 87,189 stars; ai-infra-book has 8,032.

The proof: [datawhalechina/hello-agents on GitHub](https://github.com/datawhalechina/hello-agents)

### Which has more tests, ai-infra-book or hello-agents?

ai-infra-book, with 1,093 test files; hello-agents has 103.

The proof: [bojieli/ai-infra-book's code at commit 3bdcb4f](https://github.com/bojieli/ai-infra-book/tree/3bdcb4fcab73010eeaccf31cc10a8242a895d82e)

### Which was updated more recently, ai-infra-book or hello-agents?

hello-agents: its last push was on November 13, 2026, and ai-infra-book's on October 1, 2026.

The proof: [datawhalechina/hello-agents's commits on GitHub](https://github.com/datawhalechina/hello-agents/commits)

### Which has more commits signed by AI, ai-infra-book or hello-agents?

ai-infra-book: an AI signed 16.6% of its commits, with Claude Code and Codex; in hello-agents, 3.6%.

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

## Sources

- bojieli/ai-infra-book: Read on November 17, 2026, at commit 3bdcb4f (https://github.com/bojieli/ai-infra-book/tree/3bdcb4fcab73010eeaccf31cc10a8242a895d82e)
- datawhalechina/hello-agents: Read on November 17, 2026, at commit 2eb1c75 (https://github.com/datawhalechina/hello-agents/tree/2eb1c7547018b519b85cb57acf5533f12d65bf8e)

## 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.
