Source: https://seerepo.com/compare/datawhalechina/hello-agents/vs/OpenSPG/KAG
Markdown source: https://seerepo.com/compare/datawhalechina/hello-agents/vs/OpenSPG/KAG.md
Description: hello-agents and KAG share 11 technologies: FastAPI, OpenAI, matplotlib, MCP, markdown, pdfminer.six, pypdf, python-docx, pypdf2, jinja2, and Pydantic. Both are written in Python.

# hello-agents vs KAG

hello-agents and KAG share 11 technologies: FastAPI, OpenAI, matplotlib, MCP, markdown, pdfminer.six, pypdf, python-docx, pypdf2, jinja2, and Pydantic. 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
- [OpenSPG/KAG](https://seerepo.com/r/OpenSPG/KAG): KAG is a logical form-guided reasoning and retrieval framework based on OpenSPG engine and LLMs.  It is used to build logical reasoning and factual Q&A solutions for professional domain knowledge bases. It can effectively overcome the shortcomings of the traditional RAG vector similarity calculation model.

## What they share and what sets them apart

- In common: FastAPI, OpenAI, matplotlib, MCP, markdown, pdfminer.six, pypdf, python-docx, pypdf2, jinja2, Pydantic
- Only in hello-agents: uvicorn, aiosqlite, asyncpg, psycopg2-binary, Postgres, chromadb, Redis, SQLite, libsql-client, oracledb, pymilvus, Qdrant, Google, Hugging Face, Flask, python, React, react-dom, starlette, fastmcp, anyio, AIOHTTP, Streamlit, Vite, Vue, vue-router, react-router-dom, cycler, fonttools, soupsieve, contourpy, ipywidgets, Plotly, Gradio, Rich, seaborn, alembic, SQLAlchemy, python-jose, passlib, bcrypt, accelerate, bitsandbytes, camel-ai, mermaid, onnxruntime, peft, safetensors, tavily-python, textblob, tokenizers, hello-agents, torch, transformers, agentscope, scikit-learn, sentence-transformers, tiktoken, autogen-agentchat, autogen-ext, datasets, langchain-openai, langdetect, LangGraph, paddlenlp, rank-bm25, spaCy, imaplib2, lxml, openpyxl, reportlab, xlrd, pdfplumber, pillow, feedparser, pymupdf, beautifulsoup4, pymupdf4llm, annotated-types, email-validator, jsonschema, kubernetes, OpenTelemetry, opentelemetry-exporter-otlp-proto-grpc, loguru, ant-design-vue, D3, @ant-design/icons-vue, katex, Tailwind CSS, markdown-it, vue-flow, @monaco-editor/loader, Chart.js, vue-chartjs, highlight.js, dompurify, marked, react-markdown, Element, vue-echarts, echarts, @element-plus/icons-vue, Leaflet, @amap/amap-jsapi-loader, html2canvas, jspdf
- Only in KAG: pyodps, Neo4j, diskcache, pyvis, dashscope, nltk, Ollama, bs4, aliyun-log-python-sdk, psutil

## Side by side

| | hello-agents | KAG |
|---|---|---|
| Size | 251,996 lines written, 1,282 code files | 100,755 lines written, 558 code files |
| Who writes it | 3.6% of its commits signed by AI. With Codex, Claude Code, and Cursor | 0.2% of its commits signed by AI. With Jules |
| Activity | Last push November 13, 2026, 670 commits, 87,189 stars | Last push November 19, 2026, 1,028 commits, 9,180 stars |
| Tests | 103 test files. 6.5% of its code files have a test that imports them | 35 test files. 4.1% 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 KAG?

hello-agents, with 251,996 lines written; KAG has 100,755.

The proof: [datawhalechina/hello-agents's code at commit 2eb1c75](https://github.com/datawhalechina/hello-agents/tree/2eb1c7547018b519b85cb57acf5533f12d65bf8e)

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

hello-agents, with 87,189 stars; KAG has 9,180.

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

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

hello-agents, with 103 test files; KAG has 35.

The proof: [datawhalechina/hello-agents's code at commit 2eb1c75](https://github.com/datawhalechina/hello-agents/tree/2eb1c7547018b519b85cb57acf5533f12d65bf8e)

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

KAG: its last push was on November 19, 2026, and hello-agents's on November 13, 2026.

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

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

hello-agents: an AI signed 3.6% of its commits, with Codex, Claude Code, and Cursor; in KAG, 0.2%.

The proof: [the commits each tool signed in datawhalechina/hello-agents](https://seerepo.com/r/datawhalechina/hello-agents/ai)

## Sources

- datawhalechina/hello-agents: Read on November 17, 2026, at commit 2eb1c75 (https://github.com/datawhalechina/hello-agents/tree/2eb1c7547018b519b85cb57acf5533f12d65bf8e)
- OpenSPG/KAG: Read on November 19, 2026, at commit e162ce1 (https://github.com/OpenSPG/KAG/tree/e162ce1884ae9f5d7357091f18be9d2d722c5834)

## 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.
