Source: https://seerepo.com/compare/datawhalechina/hello-agents/vs/opensandbox-group/OpenSandbox
Markdown source: https://seerepo.com/compare/datawhalechina/hello-agents/vs/opensandbox-group/OpenSandbox.md
Description: hello-agents and OpenSandbox share 12 technologies: FastAPI, uvicorn, Postgres, Redis, starlette, Vite, React, react-router-dom, Rich, MCP, Pydantic, and OpenTelemetry. hello-agents is written in Python and OpenSandbox in Go.

# hello-agents vs OpenSandbox

hello-agents and OpenSandbox share 12 technologies: FastAPI, uvicorn, Postgres, Redis, starlette, Vite, React, react-router-dom, Rich, MCP, Pydantic, and OpenTelemetry. hello-agents is written in Python and OpenSandbox in Go.

- [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
- [opensandbox-group/OpenSandbox](https://seerepo.com/r/opensandbox-group/OpenSandbox): Secure, Fast, and Extensible Sandbox runtime for AI agents.

## What they share and what sets them apart

- In common: FastAPI, uvicorn, Postgres, Redis, starlette, Vite, React, react-router-dom, Rich, MCP, Pydantic, OpenTelemetry
- Only in hello-agents: aiosqlite, asyncpg, psycopg2-binary, chromadb, SQLite, oracledb, pymilvus, OpenAI, Qdrant, Hugging Face, Flask, fastmcp, anyio, AIOHTTP, Streamlit, Vue, vue-router, 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, pypdf, python-docx, reportlab, xlrd, pdfplumber, pillow, feedparser, pymupdf, beautifulsoup4, jinja2, annotated-types, email-validator, pydantic-core, jsonschema, 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 OpenSandbox: net/http, Gin, go-redis, psycopg, etcd, github.com/aliyun/aliyun-oss-go-sdk, MySQL, oss2, sigs.k8s.io/controller-runtime, jedis, JetBrains, cryptography, itsdangerous, github.com/go-playground/validator/v10, opentelemetry-api, kubernetes, go.opentelemetry.io/otel/metric, docker, k8s.io/klog/v2, github.com/go-logr/logr, gopkg.in/natefinch/lumberjack.v2, containerd, org.slf4j:slf4j-api, go.opentelemetry.io/otel/exporters/otlp/otlpmetric/otlpmetrichttp, go.opentelemetry.io/otel/sdk, go.opentelemetry.io/otel/sdk/metric, go.uber.org/zap, go.opentelemetry.io/otel/trace, io.opentelemetry:opentelemetry-api, Knative, opentelemetry-exporter-otlp-proto-http, opentelemetry-sdk, Prometheus, antd, xterm, Ant Design, pyjwt, Microsoft.Extensions.Logging.Abstractions, ch.qos.logback:logback-classic

## Side by side

| | hello-agents | OpenSandbox |
|---|---|---|
| Size | 226,661 lines written, 1,212 code files | 650,138 lines written, 1,423 code files |
| Who writes it | 2.4% of its commits signed by AI. With Codex, Cursor, and Claude Code | 12.8% of its commits signed by AI. With Claude Code, Codex, Cursor, GitHub Copilot, Devin, and Gemini CLI |
| Activity | Last push October 13, 2026, 660 commits, 86,039 stars | Last push November 7, 2026, 3,370 commits, 16,493 stars |
| Tests | 97 test files. 6.9% of its code files have a test that imports them | 952 test files. 50.2% 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 OpenSandbox?

OpenSandbox, with 650,138 lines written; hello-agents has 226,661.

The proof: [opensandbox-group/OpenSandbox's code at commit a0e6e93](https://github.com/opensandbox-group/OpenSandbox/tree/a0e6e93e40c2a7aa8be4ffef7243e534338615e1)

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

hello-agents, with 86,039 stars; OpenSandbox has 16,493.

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

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

OpenSandbox, with 952 test files; hello-agents has 97.

The proof: [opensandbox-group/OpenSandbox's code at commit a0e6e93](https://github.com/opensandbox-group/OpenSandbox/tree/a0e6e93e40c2a7aa8be4ffef7243e534338615e1)

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

OpenSandbox: its last push was on November 7, 2026, and hello-agents's on October 13, 2026.

The proof: [opensandbox-group/OpenSandbox's commits on GitHub](https://github.com/opensandbox-group/OpenSandbox/commits)

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

OpenSandbox: an AI signed 12.8% of its commits, with Claude Code, Codex, Cursor, GitHub Copilot, Devin, and Gemini CLI; in hello-agents, 2.4%.

The proof: [the commits each tool signed in opensandbox-group/OpenSandbox](https://seerepo.com/r/opensandbox-group/OpenSandbox/ai)

## Sources

- datawhalechina/hello-agents: Read on November 4, 2026, at commit 36f583c (https://github.com/datawhalechina/hello-agents/tree/36f583c233ea5cee4537ef93455702b55053af18)
- opensandbox-group/OpenSandbox: Read on November 7, 2026, at commit a0e6e93 (https://github.com/opensandbox-group/OpenSandbox/tree/a0e6e93e40c2a7aa8be4ffef7243e534338615e1)

## 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.