Source: https://seerepo.com/compare/anthropics/claude-quickstarts/vs/datawhalechina/hello-agents
Markdown source: https://seerepo.com/compare/anthropics/claude-quickstarts/vs/datawhalechina/hello-agents.md
Description: claude-quickstarts and hello-agents share 19 technologies: FastAPI, anyio, starlette, uvicorn, Streamlit, React, Vite, MCP, jinja2, openpyxl, pillow, python-docx, annotated-types, jsonschema, pydantic-core, Pydantic, OpenTelemetry, Tailwind CSS, and react-markdown. claude-quickstarts is written in TypeScript and hello-agents in Python.

# claude-quickstarts vs hello-agents

claude-quickstarts and hello-agents share 19 technologies: FastAPI, anyio, starlette, uvicorn, Streamlit, React, Vite, MCP, jinja2, openpyxl, pillow, python-docx, annotated-types, jsonschema, pydantic-core, Pydantic, OpenTelemetry, Tailwind CSS, and react-markdown. claude-quickstarts is written in TypeScript and hello-agents in Python.

- [anthropics/claude-quickstarts](https://seerepo.com/r/anthropics/claude-quickstarts): A collection of projects designed to help developers quickly get started with building deployable applications using the Claude API
- [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, anyio, starlette, uvicorn, Streamlit, React, Vite, MCP, jinja2, openpyxl, pillow, python-docx, annotated-types, jsonschema, pydantic-core, Pydantic, OpenTelemetry, Tailwind CSS, react-markdown
- Only in claude-quickstarts: gitdb, pyarrow, Anthropic, tornado, Next.js, Hono, Express, Linear, altair, pydeck, Google, cryptography, markupsafe, python-pptx, jsonschema-specifications, referencing, boto3, pngjs, next-themes, tailwind-merge, class-variance-authority, Radix UI, Lucide, rehype-highlight, rehype-raw, Zod, recharts, @radix-ui/react-icons, @assistant-ui/react-markdown, react-shiki, @assistant-ui/react, assistant-stream, remark-gfm, chat, @hono/node-server, @copilotkit/runtime, @copilotkit/react-core, Cloudflare, Vercel
- Only in hello-agents: aiosqlite, asyncpg, psycopg2-binary, Postgres, chromadb, Redis, SQLite, oracledb, pymilvus, OpenAI, Qdrant, Hugging Face, Flask, fastmcp, AIOHTTP, Vue, vue-router, react-router-dom, cycler, fonttools, contourpy, Plotly, Gradio, matplotlib, Rich, alembic, SQLAlchemy, bcrypt, accelerate, onnxruntime, peft, safetensors, tavily-python, tokenizers, torch, transformers, scikit-learn, sentence-transformers, tiktoken, datasets, langchain-openai, LangGraph, paddlenlp, rank-bm25, spaCy, lxml, markdown, pdfminer.six, pypdf, reportlab, xlrd, pdfplumber, feedparser, pymupdf, beautifulsoup4, email-validator, opentelemetry-exporter-otlp-proto-grpc, loguru, D3, katex, markdown-it, vue-flow, Chart.js, vue-chartjs, highlight.js, dompurify, marked, Element, echarts, Leaflet, Mermaid, html2canvas, jspdf

## Side by side

| | claude-quickstarts | hello-agents |
|---|---|---|
| Size | 53,999 lines written, 301 code files | 226,661 lines written, 1,212 code files |
| Who writes it | 18.5% of its commits signed by AI. With Claude Code | 2.4% of its commits signed by AI. With Codex, Cursor, and Claude Code |
| Activity | Last push November 4, 2026, 108 commits, 19,117 stars | Last push October 13, 2026, 660 commits, 86,039 stars |
| Tests | 51 test files. 17.9% of its code files have a test that imports them | 97 test files. 6.9% 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, claude-quickstarts or hello-agents?

hello-agents, with 226,661 lines written; claude-quickstarts has 53,999.

The proof: [datawhalechina/hello-agents's code at commit 36f583c](https://github.com/datawhalechina/hello-agents/tree/36f583c233ea5cee4537ef93455702b55053af18)

### Which has more GitHub stars, claude-quickstarts or hello-agents?

hello-agents, with 86,039 stars; claude-quickstarts has 19,117.

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

### Which has more tests, claude-quickstarts or hello-agents?

hello-agents, with 97 test files; claude-quickstarts has 51.

The proof: [datawhalechina/hello-agents's code at commit 36f583c](https://github.com/datawhalechina/hello-agents/tree/36f583c233ea5cee4537ef93455702b55053af18)

### Which was updated more recently, claude-quickstarts or hello-agents?

claude-quickstarts: its last push was on November 4, 2026, and hello-agents's on October 13, 2026.

The proof: [anthropics/claude-quickstarts's commits on GitHub](https://github.com/anthropics/claude-quickstarts/commits)

### Which has more commits signed by AI, claude-quickstarts or hello-agents?

claude-quickstarts: an AI signed 18.5% of its commits, with Claude Code; in hello-agents, 2.4%.

The proof: [the commits each tool signed in anthropics/claude-quickstarts](https://seerepo.com/r/anthropics/claude-quickstarts/ai)

## Sources

- anthropics/claude-quickstarts: Read on November 6, 2026, at commit 8ef47d7 (https://github.com/anthropics/claude-quickstarts/tree/8ef47d719eba5379ff8f38133f5defcc499e856f)
- datawhalechina/hello-agents: Read on November 4, 2026, at commit 36f583c (https://github.com/datawhalechina/hello-agents/tree/36f583c233ea5cee4537ef93455702b55053af18)

## 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.