Source: https://seerepo.com/compare/datawhalechina/hello-agents/vs/HKUDS/DeepCode
Markdown source: https://seerepo.com/compare/datawhalechina/hello-agents/vs/HKUDS/DeepCode.md
Description: hello-agents and DeepCode share 10 technologies: OpenAI, AIOHTTP, Vite, React, Rich, MCP, pypdf, reportlab, loguru, and react-markdown. Both are written in Python.

# hello-agents vs DeepCode

hello-agents and DeepCode share 10 technologies: OpenAI, AIOHTTP, Vite, React, Rich, MCP, pypdf, reportlab, loguru, and react-markdown. 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
- [HKUDS/DeepCode](https://seerepo.com/r/HKUDS/DeepCode): "DeepCode: Open Agentic Coding (Agent Harness & Loop Engineering & Multi-Agent Orchestration)"

## What they share and what sets them apart

- In common: OpenAI, AIOHTTP, Vite, React, Rich, MCP, pypdf, reportlab, loguru, react-markdown
- Only in hello-agents: FastAPI, uvicorn, aiosqlite, asyncpg, psycopg2-binary, Postgres, chromadb, Redis, SQLite, oracledb, pymilvus, Qdrant, Hugging Face, Flask, fastmcp, starlette, anyio, Streamlit, Vue, vue-router, react-router-dom, cycler, fonttools, contourpy, Plotly, Gradio, matplotlib, alembic, SQLAlchemy, bcrypt, accelerate, 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, python-docx, xlrd, pdfplumber, pillow, feedparser, pymupdf, beautifulsoup4, 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, Element, echarts, Leaflet, Mermaid, html2canvas, jspdf
- Only in DeepCode: Anthropic, Google, Tauri, @tauri-apps/api, prompt-toolkit, tauri-plugin-dialog, monaco-editor, prism-react-renderer, xterm, Lucide, remark-gfm, tauri-apps

## Side by side

| | hello-agents | DeepCode |
|---|---|---|
| Size | 226,661 lines written, 1,212 code files | 252,336 lines written, 487 code files |
| Who writes it | 2.4% of its commits signed by AI. With Codex, Cursor, and Claude Code | 14.5% of its commits signed by AI. With Claude Code, Cursor, and Codex |
| Activity | Last push October 13, 2026, 660 commits, 86,039 stars | Last push November 2, 2026, 759 commits, 16,814 stars |
| Tests | 97 test files. 6.9% of its code files have a test that imports them | 346 test files. 70.8% 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 DeepCode?

DeepCode, with 252,336 lines written; hello-agents has 226,661.

The proof: [HKUDS/DeepCode's code at commit aa6ed16](https://github.com/HKUDS/DeepCode/tree/aa6ed16148719101b994882c94608ae12e88f870)

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

hello-agents, with 86,039 stars; DeepCode has 16,814.

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

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

DeepCode, with 346 test files; hello-agents has 97.

The proof: [HKUDS/DeepCode's code at commit aa6ed16](https://github.com/HKUDS/DeepCode/tree/aa6ed16148719101b994882c94608ae12e88f870)

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

DeepCode: its last push was on November 2, 2026, and hello-agents's on October 13, 2026.

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

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

DeepCode: an AI signed 14.5% of its commits, with Claude Code, Cursor, and Codex; in hello-agents, 2.4%.

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

## Sources

- datawhalechina/hello-agents: Read on November 4, 2026, at commit 36f583c (https://github.com/datawhalechina/hello-agents/tree/36f583c233ea5cee4537ef93455702b55053af18)
- HKUDS/DeepCode: Read on November 7, 2026, at commit aa6ed16 (https://github.com/HKUDS/DeepCode/tree/aa6ed16148719101b994882c94608ae12e88f870)

## 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.