Source: https://seerepo.com/compare/datawhalechina/hello-agents/vs/tobi/qmd
Markdown source: https://seerepo.com/compare/datawhalechina/hello-agents/vs/tobi/qmd.md
Description: hello-agents and qmd share 9 technologies: SQLite, Hugging Face, accelerate, MCP, peft, torch, transformers, datasets, and Pydantic. hello-agents is written in Python and qmd in TypeScript.

# hello-agents vs qmd

hello-agents and qmd share 9 technologies: SQLite, Hugging Face, accelerate, MCP, peft, torch, transformers, datasets, and Pydantic. hello-agents is written in Python and qmd 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
- [tobi/qmd](https://seerepo.com/r/tobi/qmd): mini cli search engine for your docs, knowledge bases, meeting notes, whatever. Tracking current sota approaches while being all local

## What they share and what sets them apart

- In common: SQLite, Hugging Face, accelerate, MCP, peft, torch, transformers, datasets, Pydantic
- Only in hello-agents: FastAPI, uvicorn, aiosqlite, asyncpg, psycopg2-binary, Postgres, chromadb, Redis, oracledb, pymilvus, OpenAI, Qdrant, Flask, fastmcp, starlette, anyio, AIOHTTP, Streamlit, Vite, Vue, vue-router, React, react-router-dom, cycler, fonttools, contourpy, Plotly, Gradio, matplotlib, Rich, alembic, SQLAlchemy, bcrypt, onnxruntime, safetensors, tavily-python, tokenizers, scikit-learn, sentence-transformers, tiktoken, 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, 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 qmd: sqlite-vec, gguf, sentencepiece, trl, node-llama-cpp, trackio, yaml, Zod

## Side by side

| | hello-agents | qmd |
|---|---|---|
| Size | 226,661 lines written, 1,212 code files | 62,234 lines written, 49 code files |
| Who writes it | 2.4% of its commits signed by AI. With Codex, Cursor, and Claude Code | 27.2% of its commits signed by AI. With Claude Code, Codex, Cursor, Warp, and GitHub Copilot |
| Activity | Last push October 13, 2026, 660 commits, 86,039 stars | Last push October 15, 2026, 639 commits, 30,946 stars |
| Tests | 97 test files. 6.9% of its code files have a test that imports them | 69 test files. 42.9% 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, hello-agents or qmd?

hello-agents, with 226,661 lines written; qmd has 62,234.

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 qmd?

hello-agents, with 86,039 stars; qmd has 30,946.

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

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

hello-agents, with 97 test files; qmd has 69.

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 qmd?

qmd: its last push was on October 15, 2026, and hello-agents's on October 13, 2026.

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

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

qmd: an AI signed 27.2% of its commits, with Claude Code, Codex, Cursor, Warp, and GitHub Copilot; in hello-agents, 2.4%.

The proof: [the commits each tool signed in tobi/qmd](https://seerepo.com/r/tobi/qmd/ai)

## Sources

- datawhalechina/hello-agents: Read on November 4, 2026, at commit 36f583c (https://github.com/datawhalechina/hello-agents/tree/36f583c233ea5cee4537ef93455702b55053af18)
- tobi/qmd: Read on November 7, 2026, at commit 86d2365 (https://github.com/tobi/qmd/tree/86d2365d17fc682e491c2c53d1e4a884aee8682a)

## 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.