Source: https://seerepo.com/compare/datawhalechina/hello-agents/vs/walkinglabs/learn-harness-engineering
Markdown source: https://seerepo.com/compare/datawhalechina/hello-agents/vs/walkinglabs/learn-harness-engineering.md
Description: hello-agents and learn-harness-engineering share 3 technologies: Vite, React, and fonttools. hello-agents is written in Python and learn-harness-engineering in TypeScript.

# hello-agents vs learn-harness-engineering

hello-agents and learn-harness-engineering share 3 technologies: Vite, React, and fonttools. hello-agents is written in Python and learn-harness-engineering in TypeScript.

- [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
- [walkinglabs/learn-harness-engineering](https://seerepo.com/r/walkinglabs/learn-harness-engineering): Harness engineering beginner tutorial, from 0 to 1

## What they share and what sets them apart

- In common: Vite, React, fonttools
- 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, Vue, vue-router, react-router-dom, cycler, contourpy, Plotly, Gradio, matplotlib, Rich, alembic, SQLAlchemy, bcrypt, accelerate, MCP, onnxruntime, peft, safetensors, tavily-python, tokenizers, torch, transformers, scikit-learn, sentence-transformers, tiktoken, datasets, langchain-openai, LangGraph, paddlenlp, rank-bm25, spaCy, lxml, markdown, openpyxl, pdfminer.six, pypdf, python-docx, reportlab, xlrd, pdfplumber, pillow, feedparser, pymupdf, beautifulsoup4, jinja2, annotated-types, email-validator, pydantic-core, Pydantic, jsonschema, OpenTelemetry, opentelemetry-exporter-otlp-proto-grpc, loguru, 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 learn-harness-engineering: Electron, cairosvg

## Side by side

| | hello-agents | learn-harness-engineering |
|---|---|---|
| Size | 226,661 lines written, 1,212 code files | 70,426 lines written, 205 code files |
| Who writes it | 2.4% of its commits signed by AI. With Codex, Cursor, and Claude Code | 22% of its commits signed by AI. With Claude Code, GitHub Copilot, and Cursor |
| Activity | Last push October 13, 2026, 660 commits, 86,039 stars | Last push October 22, 2026, 223 commits, 23,149 stars |
| Tests | 97 test files. 6.9% of its code files have a test that imports them | 1 test files |

- 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 learn-harness-engineering?

hello-agents, with 226,661 lines written; learn-harness-engineering has 70,426.

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 learn-harness-engineering?

hello-agents, with 86,039 stars; learn-harness-engineering has 23,149.

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

### Which has more tests, hello-agents or learn-harness-engineering?

hello-agents, with 97 test files; learn-harness-engineering has 1.

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 learn-harness-engineering?

learn-harness-engineering: its last push was on October 22, 2026, and hello-agents's on October 13, 2026.

The proof: [walkinglabs/learn-harness-engineering's commits on GitHub](https://github.com/walkinglabs/learn-harness-engineering/commits)

### Which has more commits signed by AI, hello-agents or learn-harness-engineering?

learn-harness-engineering: an AI signed 22% of its commits, with Claude Code, GitHub Copilot, and Cursor; in hello-agents, 2.4%.

The proof: [the commits each tool signed in walkinglabs/learn-harness-engineering](https://seerepo.com/r/walkinglabs/learn-harness-engineering/ai)

## Sources

- datawhalechina/hello-agents: Read on November 4, 2026, at commit 36f583c (https://github.com/datawhalechina/hello-agents/tree/36f583c233ea5cee4537ef93455702b55053af18)
- walkinglabs/learn-harness-engineering: Read on November 4, 2026, at commit a9342ff (https://github.com/walkinglabs/learn-harness-engineering/tree/a9342ff471f2c0e60be0c08b9f4a7c502df4e442)

## 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.