Source: https://seerepo.com/compare/datawhalechina/hello-agents/vs/microsoft/unilm
Markdown source: https://seerepo.com/compare/datawhalechina/hello-agents/vs/microsoft/unilm.md
Description: hello-agents and unilm share 14 technologies: FastAPI, OpenAI, Flask, Gradio, accelerate, peft, tokenizers, torch, transformers, scikit-learn, tiktoken, datasets, lxml, and pillow. Both are written in Python.

# hello-agents vs unilm

hello-agents and unilm share 14 technologies: FastAPI, OpenAI, Flask, Gradio, accelerate, peft, tokenizers, torch, transformers, scikit-learn, tiktoken, datasets, lxml, and pillow. 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/unilm](https://seerepo.com/r/microsoft/unilm): Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities

## What they share and what sets them apart

- In common: FastAPI, OpenAI, Flask, Gradio, accelerate, peft, tokenizers, torch, transformers, scikit-learn, tiktoken, datasets, lxml, pillow
- Only in hello-agents: uvicorn, aiosqlite, asyncpg, psycopg2-binary, Postgres, chromadb, Redis, SQLite, oracledb, pymilvus, Qdrant, Hugging Face, fastmcp, starlette, anyio, AIOHTTP, Streamlit, Vite, Vue, vue-router, React, react-router-dom, cycler, fonttools, contourpy, Plotly, matplotlib, Rich, alembic, SQLAlchemy, bcrypt, MCP, onnxruntime, safetensors, tavily-python, sentence-transformers, langchain-openai, LangGraph, paddlenlp, rank-bm25, spaCy, markdown, openpyxl, pdfminer.six, pypdf, python-docx, reportlab, xlrd, pdfplumber, feedparser, pymupdf, beautifulsoup4, jinja2, annotated-types, email-validator, pydantic-core, Pydantic, 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 unilm: pyarrow, webdataset, timm, torchvision, opencv-python, sacrebleu, sentencepiece, diffusers, deepspeed, torchaudio, bitsandbytes, einops, nltk, triton, vLLM, torchmetrics, pycocotools, boto3

## Side by side

| | hello-agents | unilm |
|---|---|---|
| Size | 226,661 lines written, 1,212 code files | 769,203 lines written, 2,555 code files |
| Who writes it | 2.4% of its commits signed by AI. With Codex, Cursor, and Claude Code | 0% of its commits signed by AI |
| Activity | Last push October 13, 2026, 660 commits, 86,039 stars | Last push September 21, 2026, 1,092 commits, 22,240 stars |
| Tests | 97 test files. 6.9% of its code files have a test that imports them | 163 test files. 5.1% 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 unilm?

unilm, with 769,203 lines written; hello-agents has 226,661.

The proof: [microsoft/unilm's code at commit 31c5b90](https://github.com/microsoft/unilm/tree/31c5b904ca1bf2afb4c234a6675c683a4e5fc7cd)

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

hello-agents, with 86,039 stars; unilm has 22,240.

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

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

unilm, with 163 test files; hello-agents has 97.

The proof: [microsoft/unilm's code at commit 31c5b90](https://github.com/microsoft/unilm/tree/31c5b904ca1bf2afb4c234a6675c683a4e5fc7cd)

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

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

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

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

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

## Sources

- datawhalechina/hello-agents: Read on November 4, 2026, at commit 36f583c (https://github.com/datawhalechina/hello-agents/tree/36f583c233ea5cee4537ef93455702b55053af18)
- microsoft/unilm: Read on November 5, 2026, at commit 31c5b90 (https://github.com/microsoft/unilm/tree/31c5b904ca1bf2afb4c234a6675c683a4e5fc7cd)

## 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.