Source: https://seerepo.com/compare/datawhalechina/hello-agents/vs/microsoft/RD-Agent
Markdown source: https://seerepo.com/compare/datawhalechina/hello-agents/vs/microsoft/RD-Agent.md
Description: hello-agents and RD-Agent share 30 technologies: OpenAI, Hugging Face, Flask, Streamlit, Vite, Vue, vue-router, Plotly, matplotlib, Rich, accelerate, peft, torch, transformers, scikit-learn, tiktoken, datasets, rank-bm25, spaCy, pypdf, pymupdf, beautifulsoup4, Pydantic, loguru, katex, markdown-it, highlight.js, marked, Element, and echarts. Both are written in Python.

# hello-agents vs RD-Agent

hello-agents and RD-Agent share 30 technologies: OpenAI, Hugging Face, Flask, Streamlit, Vite, Vue, vue-router, Plotly, matplotlib, Rich, accelerate, peft, torch, transformers, scikit-learn, tiktoken, datasets, rank-bm25, spaCy, pypdf, pymupdf, beautifulsoup4, Pydantic, loguru, katex, markdown-it, highlight.js, marked, Element, and echarts. 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/RD-Agent](https://seerepo.com/r/microsoft/RD-Agent): Research and development (R&D) is crucial for the enhancement of industrial productivity, especially in the AI era, where the core aspects of R&D are mainly focused on data and models. We are committed to automating these high-value generic R&D processes through R&D-Agent, which lets AI drive data-driven AI. 🔗https://aka.ms/RD-Agent-Tech-Report

## What they share and what sets them apart

- In common: OpenAI, Hugging Face, Flask, Streamlit, Vite, Vue, vue-router, Plotly, matplotlib, Rich, accelerate, peft, torch, transformers, scikit-learn, tiktoken, datasets, rank-bm25, spaCy, pypdf, pymupdf, beautifulsoup4, Pydantic, loguru, katex, markdown-it, highlight.js, marked, Element, echarts
- Only in hello-agents: FastAPI, uvicorn, aiosqlite, asyncpg, psycopg2-binary, Postgres, chromadb, Redis, SQLite, oracledb, pymilvus, Qdrant, fastmcp, starlette, anyio, AIOHTTP, React, react-router-dom, cycler, fonttools, contourpy, Gradio, alembic, SQLAlchemy, bcrypt, MCP, onnxruntime, safetensors, tavily-python, tokenizers, sentence-transformers, langchain-openai, LangGraph, paddlenlp, lxml, markdown, openpyxl, pdfminer.six, python-docx, reportlab, xlrd, pdfplumber, pillow, feedparser, jinja2, annotated-types, email-validator, pydantic-core, jsonschema, OpenTelemetry, opentelemetry-exporter-otlp-proto-grpc, D3, Tailwind CSS, vue-flow, Chart.js, vue-chartjs, dompurify, react-markdown, Leaflet, Mermaid, html2canvas, jspdf
- Only in RD-Agent: werkzeug, pyarrow, tables, Kaggle, flask-cors, furo, sphinx-rtd-theme, seaborn, gym, pydantic-ai-slim, pyserini, trl, vLLM, litellm, MLflow, LangChain, myst-parser, nbformat, genson, docker, Prefect, github-markdown-css, markdown-it-texmath, prismjs

## Side by side

| | hello-agents | RD-Agent |
|---|---|---|
| Size | 226,661 lines written, 1,212 code files | 83,518 lines written, 505 code files |
| Who writes it | 2.4% of its commits signed by AI. With Codex, Cursor, and Claude Code | 0.7% of its commits signed by AI. With GitHub Copilot and Claude Code |
| Activity | Last push October 13, 2026, 660 commits, 86,039 stars | Last push October 21, 2026, 1,013 commits, 15,282 stars |
| Tests | 97 test files. 6.9% of its code files have a test that imports them | 41 test files. 9.5% 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 RD-Agent?

hello-agents, with 226,661 lines written; RD-Agent has 83,518.

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 RD-Agent?

hello-agents, with 86,039 stars; RD-Agent has 15,282.

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

### Which has more tests, hello-agents or RD-Agent?

hello-agents, with 97 test files; RD-Agent has 41.

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 RD-Agent?

RD-Agent: its last push was on October 21, 2026, and hello-agents's on October 13, 2026.

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

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

hello-agents: an AI signed 2.4% of its commits, with Codex, Cursor, and Claude Code; in RD-Agent, 0.7%.

## Sources

- datawhalechina/hello-agents: Read on November 4, 2026, at commit 36f583c (https://github.com/datawhalechina/hello-agents/tree/36f583c233ea5cee4537ef93455702b55053af18)
- microsoft/RD-Agent: Read on November 8, 2026, at commit 484776c (https://github.com/microsoft/RD-Agent/tree/484776c211e4fbbeef03e0ec00d6bbee7362a4f4)

## 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.