Source: https://seerepo.com/compare/apple-aiml-research/ml-ferret/vs/datawhalechina/hello-agents
Markdown source: https://seerepo.com/compare/apple-aiml-research/ml-ferret/vs/datawhalechina/hello-agents.md
Description: ml-ferret and hello-agents share 14 technologies: FastAPI, uvicorn, Gradio, accelerate, OpenAI, scikit-learn, spaCy, torch, transformers, peft, bitsandbytes, tokenizers, openpyxl, and Pydantic. Both are written in Python.

# ml-ferret vs hello-agents

ml-ferret and hello-agents share 14 technologies: FastAPI, uvicorn, Gradio, accelerate, OpenAI, scikit-learn, spaCy, torch, transformers, peft, bitsandbytes, tokenizers, openpyxl, and Pydantic. Both are written in Python.

- [apple-aiml-research/ml-ferret](https://seerepo.com/r/apple-aiml-research/ml-ferret)
- [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

## What they share and what sets them apart

- In common: FastAPI, uvicorn, Gradio, accelerate, OpenAI, scikit-learn, spaCy, torch, transformers, peft, bitsandbytes, tokenizers, openpyxl, Pydantic
- Only in ml-ferret: gradio-client, nltk, open-clip-torch, sentencepiece, timm, torchvision, deepspeed, pycocotools, einops, jsonlines, markdown2
- Only in hello-agents: aiosqlite, asyncpg, psycopg2-binary, Postgres, chromadb, Redis, SQLite, libsql-client, oracledb, pymilvus, Qdrant, Hugging Face, Flask, python, React, react-dom, fastmcp, starlette, anyio, AIOHTTP, Streamlit, Vite, Vue, vue-router, react-router-dom, cycler, fonttools, soupsieve, contourpy, ipywidgets, Plotly, matplotlib, Rich, seaborn, alembic, SQLAlchemy, python-jose, passlib, bcrypt, camel-ai, MCP, mermaid, onnxruntime, safetensors, tavily-python, textblob, hello-agents, agentscope, sentence-transformers, tiktoken, autogen-agentchat, autogen-ext, datasets, langchain-openai, langdetect, LangGraph, paddlenlp, rank-bm25, imaplib2, lxml, markdown, pdfminer.six, pypdf, python-docx, reportlab, xlrd, pdfplumber, pillow, feedparser, pymupdf, pypdf2, beautifulsoup4, jinja2, 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

## Side by side

| | ml-ferret | hello-agents |
|---|---|---|
| Size | 15,385 lines written, 54 code files | 227,369 lines written, 1,215 code files |
| Who writes it | 0% of its commits signed by AI | 3.3% of its commits signed by AI. With Codex, Claude Code, and Cursor |
| Activity | Last push September 11, 2026, 5 commits, 8,646 stars | Last push November 11, 2026, 667 commits, 86,829 stars |
| Tests | 1 test files. 1.9% of its code files have a test that imports them | 103 test files. 6.8% 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, ml-ferret or hello-agents?

hello-agents, with 227,369 lines written; ml-ferret has 15,385.

The proof: [datawhalechina/hello-agents's code at commit 2a506bc](https://github.com/datawhalechina/hello-agents/tree/2a506bc7e0e3e2235435559b7f2825057ce9a09c)

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

hello-agents, with 86,829 stars; ml-ferret has 8,646.

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

### Which has more tests, ml-ferret or hello-agents?

hello-agents, with 103 test files; ml-ferret has 1.

The proof: [datawhalechina/hello-agents's code at commit 2a506bc](https://github.com/datawhalechina/hello-agents/tree/2a506bc7e0e3e2235435559b7f2825057ce9a09c)

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

hello-agents: its last push was on November 11, 2026, and ml-ferret's on September 11, 2026.

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

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

hello-agents: an AI signed 3.3% of its commits, with Codex, Claude Code, and Cursor.

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

## Sources

- apple-aiml-research/ml-ferret: Read on November 16, 2026, at commit 25985c2 (https://github.com/apple-aiml-research/ml-ferret/tree/25985c2c4f24b12bc917bd94ec8c879a89176644)
- datawhalechina/hello-agents: Read on November 12, 2026, at commit 2a506bc (https://github.com/datawhalechina/hello-agents/tree/2a506bc7e0e3e2235435559b7f2825057ce9a09c)

## 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.
