Source: https://seerepo.com/compare/datawhalechina/hello-agents/vs/microsoft/qlib
Markdown source: https://seerepo.com/compare/datawhalechina/hello-agents/vs/microsoft/qlib.md
Description: hello-agents and qlib share 5 technologies: torch, lxml, openpyxl, beautifulsoup4, and loguru. Both are written in Python.

# hello-agents vs qlib

hello-agents and qlib share 5 technologies: torch, lxml, openpyxl, beautifulsoup4, and loguru. Both are written in Python.

- [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
- [microsoft/qlib](https://seerepo.com/r/microsoft/qlib): Qlib is an AI-oriented Quant investment platform that aims to use AI tech to empower Quant Research, from exploring ideas to implementing productions. Qlib supports diverse ML modeling paradigms, including supervised learning, market dynamics modeling, and RL, and is now equipped with https://github.com/microsoft/RD-Agent to automate R&D process.

## What they share and what sets them apart

- In common: torch, lxml, openpyxl, beautifulsoup4, loguru
- Only in hello-agents: FastAPI, uvicorn, aiosqlite, asyncpg, psycopg2-binary, Postgres, chromadb, Redis, SQLite, oracledb, pymilvus, OpenAI, Qdrant, Hugging Face, Flask, fastmcp, starlette, anyio, AIOHTTP, Streamlit, Vite, Vue, vue-router, React, react-router-dom, cycler, fonttools, contourpy, Plotly, Gradio, matplotlib, Rich, alembic, SQLAlchemy, bcrypt, accelerate, MCP, onnxruntime, peft, safetensors, tavily-python, tokenizers, transformers, scikit-learn, sentence-transformers, tiktoken, datasets, langchain-openai, LangGraph, paddlenlp, rank-bm25, spaCy, markdown, pdfminer.six, pypdf, python-docx, reportlab, xlrd, pdfplumber, pillow, feedparser, pymupdf, jinja2, annotated-types, email-validator, pydantic-core, Pydantic, jsonschema, OpenTelemetry, opentelemetry-exporter-otlp-proto-grpc, D3, katex, Tailwind CSS, markdown-it, vue-flow, Chart.js, vue-chartjs, highlight.js, dompurify, marked, react-markdown, Element, echarts, Leaflet, Mermaid, html2canvas, jspdf
- Only in qlib: soupsieve, cryptography, bs4

## Side by side

| | hello-agents | qlib |
|---|---|---|
| Size | 226,661 lines written, 1,212 code files | 78,929 lines written, 219 code files |
| Who writes it | 2.4% of its commits signed by AI. With Codex, Cursor, and Claude Code | 0.2% of its commits signed by AI. With GitHub Copilot |
| Activity | Last push October 13, 2026, 660 commits, 86,039 stars | Last push November 4, 2026, 1,852 commits, 50,029 stars |
| Tests | 97 test files. 6.9% of its code files have a test that imports them | 56 test files. 36.5% 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, hello-agents or qlib?

hello-agents, with 226,661 lines written; qlib has 78,929.

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

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

hello-agents, with 86,039 stars; qlib has 50,029.

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

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

hello-agents, with 97 test files; qlib has 56.

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

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

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

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

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

hello-agents: an AI signed 2.4% of its commits, with Codex, Cursor, and Claude Code; in qlib, 0.2%.

## Sources

- datawhalechina/hello-agents: Read on November 4, 2026, at commit 36f583c (https://github.com/datawhalechina/hello-agents/tree/36f583c233ea5cee4537ef93455702b55053af18)
- microsoft/qlib: Read on November 5, 2026, at commit 5435523 (https://github.com/microsoft/qlib/tree/54355232463878d2eebb91fe0ee5fa7fa1f5976c)

## 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.