Source: https://seerepo.com/compare/agentscope-ai/QwenPaw/vs/datawhalechina/hello-agents
Markdown source: https://seerepo.com/compare/agentscope-ai/QwenPaw/vs/datawhalechina/hello-agents.md
Description: QwenPaw and hello-agents share 22 technologies: FastAPI, OpenAI, Hugging Face, AIOHTTP, uvicorn, anyio, Vite, react-router-dom, React, matplotlib, onnxruntime, transformers, MCP, openpyxl, pillow, Pydantic, jsonschema, D3, Mermaid, react-markdown, katex, and Tailwind CSS. Both are written in Python.

# QwenPaw vs hello-agents

QwenPaw and hello-agents share 22 technologies: FastAPI, OpenAI, Hugging Face, AIOHTTP, uvicorn, anyio, Vite, react-router-dom, React, matplotlib, onnxruntime, transformers, MCP, openpyxl, pillow, Pydantic, jsonschema, D3, Mermaid, react-markdown, katex, and Tailwind CSS. Both are written in Python.

- [agentscope-ai/QwenPaw](https://seerepo.com/r/agentscope-ai/QwenPaw): Your Personal AI Assistant; easy to install, deploy on your own machine or on the cloud; supports multiple chat apps with easily extensible capabilities.
- [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, OpenAI, Hugging Face, AIOHTTP, uvicorn, anyio, Vite, react-router-dom, React, matplotlib, onnxruntime, transformers, MCP, openpyxl, pillow, Pydantic, jsonschema, D3, Mermaid, react-markdown, katex, Tailwind CSS
- Only in QwenPaw: oss2, Google, pyside6-essentials, slack-bolt, Tauri, Tokio, @tauri-apps/api, objc2-app-kit, objc2-foundation, Textual, questionary, peewee, cryptography, pyjwt, alibabacloud-credentials, keyring, msal, agent-client-protocol, ModelScope, agentscope, dashscope, linkify-it-py, markdown-it-py, pypdfium2, imageio-ffmpeg, imap-tools, psutil, Alibaba Cloud, antd-style, antd, motion, @number-flow/react, core-graphics, dnd-kit, @ant-design/plots, monaco-editor, react-syntax-highlighter, react-window, lexical, notify-rust, react-resizable-panels, tauri-plugin-dialog, three, topojson-client, vaul, webview2-com, world-atlas, xterm, Lucide, @ant-design/icons, Ant Design, rehype-katex, remark-gfm, remark-math, yaml, jpeg-encoder, log, tauri-plugin-log, @openuidev/react-ui, @openuidev/react-lang, Zod
- Only in hello-agents: aiosqlite, asyncpg, psycopg2-binary, Postgres, chromadb, Redis, SQLite, oracledb, pymilvus, Qdrant, Flask, fastmcp, starlette, Streamlit, Vue, vue-router, cycler, fonttools, contourpy, Plotly, Gradio, Rich, alembic, SQLAlchemy, bcrypt, accelerate, peft, safetensors, tavily-python, tokenizers, torch, scikit-learn, sentence-transformers, tiktoken, datasets, langchain-openai, LangGraph, paddlenlp, rank-bm25, spaCy, lxml, markdown, pdfminer.six, pypdf, python-docx, reportlab, xlrd, pdfplumber, feedparser, pymupdf, beautifulsoup4, jinja2, annotated-types, email-validator, pydantic-core, OpenTelemetry, opentelemetry-exporter-otlp-proto-grpc, loguru, markdown-it, vue-flow, Chart.js, vue-chartjs, highlight.js, dompurify, marked, Element, echarts, Leaflet, html2canvas, jspdf

## Side by side

| | QwenPaw | hello-agents |
|---|---|---|
| Size | 1,541,254 lines written, 2,654 code files | 226,661 lines written, 1,212 code files |
| Who writes it | 0.3% of its commits signed by AI. With Claude Code, Gemini CLI, GitHub Copilot, and Cursor | 2.4% of its commits signed by AI. With Codex, Cursor, and Claude Code |
| Activity | Last push November 6, 2026, 2,685 commits, 37,425 stars | Last push October 13, 2026, 660 commits, 86,039 stars |
| Tests | 2,051 test files. 63.3% 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, QwenPaw or hello-agents?

QwenPaw, with 1,541,254 lines written; hello-agents has 226,661.

The proof: [agentscope-ai/QwenPaw's code at commit 2cf28d1](https://github.com/agentscope-ai/QwenPaw/tree/2cf28d14a20c9f9c769cce2a9c0568ccf84e459c)

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

hello-agents, with 86,039 stars; QwenPaw has 37,425.

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

### Which has more tests, QwenPaw or hello-agents?

QwenPaw, with 2,051 test files; hello-agents has 97.

The proof: [agentscope-ai/QwenPaw's code at commit 2cf28d1](https://github.com/agentscope-ai/QwenPaw/tree/2cf28d14a20c9f9c769cce2a9c0568ccf84e459c)

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

QwenPaw: its last push was on November 6, 2026, and hello-agents's on October 13, 2026.

The proof: [agentscope-ai/QwenPaw's commits on GitHub](https://github.com/agentscope-ai/QwenPaw/commits)

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

hello-agents: an AI signed 2.4% of its commits, with Codex, Cursor, and Claude Code; in QwenPaw, 0.3%.

## Sources

- agentscope-ai/QwenPaw: Read on November 6, 2026, at commit 2cf28d1 (https://github.com/agentscope-ai/QwenPaw/tree/2cf28d14a20c9f9c769cce2a9c0568ccf84e459c)
- 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.