Source: https://seerepo.com/compare/arc53/DocsGPT/vs/datawhalechina/hello-agents
Markdown source: https://seerepo.com/compare/arc53/DocsGPT/vs/datawhalechina/hello-agents.md
Description: DocsGPT and hello-agents share 52 technologies: Flask, pymilvus, Redis, Postgres, Hugging Face, OpenAI, Qdrant, AIOHTTP, anyio, starlette, fastmcp, uvicorn, React, Vite, react-router-dom, matplotlib, Rich, SQLAlchemy, alembic, accelerate, safetensors, transformers, torch, MCP, onnxruntime, tiktoken, tokenizers, lxml, pdfminer.six, pillow, beautifulsoup4, pypdf, jinja2, openpyxl, pdfplumber, python-docx, reportlab, annotated-types, email-validator, pydantic-core, Pydantic, jsonschema, loguru, opentelemetry-exporter-otlp-proto-grpc, OpenTelemetry, dompurify, markdown-it, Tailwind CSS, Chart.js, Mermaid, D3, and react-markdown. Both are written in Python.

# DocsGPT vs hello-agents

DocsGPT and hello-agents share 52 technologies: Flask, pymilvus, Redis, Postgres, Hugging Face, OpenAI, Qdrant, AIOHTTP, anyio, starlette, fastmcp, uvicorn, React, Vite, react-router-dom, matplotlib, Rich, SQLAlchemy, alembic, accelerate, safetensors, transformers, torch, MCP, onnxruntime, tiktoken, tokenizers, lxml, pdfminer.six, pillow, beautifulsoup4, pypdf, jinja2, openpyxl, pdfplumber, python-docx, reportlab, annotated-types, email-validator, pydantic-core, Pydantic, jsonschema, loguru, opentelemetry-exporter-otlp-proto-grpc, OpenTelemetry, dompurify, markdown-it, Tailwind CSS, Chart.js, Mermaid, D3, and react-markdown. Both are written in Python.

- [arc53/DocsGPT](https://seerepo.com/r/arc53/DocsGPT): Private AI platform for agents, assistants and enterprise search. Built-in Agent Builder, Deep research, Document analysis, Multi-model support, and API connectivity for agents.
- [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: Flask, pymilvus, Redis, Postgres, Hugging Face, OpenAI, Qdrant, AIOHTTP, anyio, starlette, fastmcp, uvicorn, React, Vite, react-router-dom, matplotlib, Rich, SQLAlchemy, alembic, accelerate, safetensors, transformers, torch, MCP, onnxruntime, tiktoken, tokenizers, lxml, pdfminer.six, pillow, beautifulsoup4, pypdf, jinja2, openpyxl, pdfplumber, python-docx, reportlab, annotated-types, email-validator, pydantic-core, Pydantic, jsonschema, loguru, opentelemetry-exporter-otlp-proto-grpc, OpenTelemetry, dompurify, markdown-it, Tailwind CSS, Chart.js, Mermaid, D3, react-markdown
- Only in DocsGPT: flask-restx, amqp, Milvus, obstore, pgvector, psycopg, psycopg-binary, psycopg-pool, pyarrow, s3transfer, Celery, kombu, Google, Anthropic, ElevenLabs, asgiref, werkzeug, a2wsgi, soupsieve, prompt-toolkit, authlib, google-auth, google-auth-httplib2, itsdangerous, joserfc, oauthlib, requests-oauthlib, pyjwt, cryptography, google-auth-oauthlib, msal, faiss-cpu, rapidocr, torchvision, fastembed, gtts, docling-slim, et-xmlfile, filetype, firecrawl-anydoc, latex2mathml, mako, markdown-it-py, markupsafe, mdurl, olefile, pylatexenc, uharfbuzz, xlsxwriter, pypdfium2, markdownify, defusedxml, docling, docx2txt, imageio, pdf2image, pytesseract, python-pptx, beartype, cel-python, docling-core, jsonschema-path, jsonschema-specifications, marshmallow, referencing, colorlog, opentelemetry-api, opentelemetry-instrumentation, opentelemetry-instrumentation-aiohttp-client, opentelemetry-instrumentation-asgi, opentelemetry-instrumentation-celery, opentelemetry-instrumentation-flask, opentelemetry-instrumentation-logging, opentelemetry-instrumentation-psycopg, opentelemetry-instrumentation-redis, opentelemetry-instrumentation-requests, opentelemetry-instrumentation-sqlalchemy, opentelemetry-semantic-conventions, opentelemetry-util-http, psutil, boto3, botocore, Gunicorn, daytona, styled-components, prismjs, class-variance-authority, tailwind-merge, Radix UI, reactflow, react-dropzone, react-chartjs-2, react-syntax-highlighter, @shadcn/react, cmdk, react-day-picker, react-force-graph-2d, Lucide, unified, remark-gfm, micromark-util-character, micromark-util-types, micromark-util-symbol, unist-util-visit, rehype-katex, remark-math, remark-parse, remend
- Only in hello-agents: FastAPI, aiosqlite, asyncpg, psycopg2-binary, chromadb, SQLite, oracledb, Streamlit, Vue, vue-router, cycler, fonttools, contourpy, Plotly, Gradio, bcrypt, peft, tavily-python, scikit-learn, sentence-transformers, datasets, langchain-openai, LangGraph, paddlenlp, rank-bm25, spaCy, markdown, xlrd, feedparser, pymupdf, katex, vue-flow, vue-chartjs, highlight.js, marked, Element, echarts, Leaflet, html2canvas, jspdf

## Side by side

| | DocsGPT | hello-agents |
|---|---|---|
| Size | 812,848 lines written, 1,275 code files | 226,661 lines written, 1,212 code files |
| Who writes it | 0.3% of its commits signed by AI. With Claude Code, GitHub Copilot, Codex, and Cursor | 2.4% of its commits signed by AI. With Codex, Cursor, and Claude Code |
| Activity | Last push November 6, 2026, 5,882 commits, 18,360 stars | Last push October 13, 2026, 660 commits, 86,039 stars |
| Tests | 1,391 test files. 77.3% of its code files have a test that imports them | 97 test files. 6.9% 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, DocsGPT or hello-agents?

DocsGPT, with 812,848 lines written; hello-agents has 226,661.

The proof: [arc53/DocsGPT's code at commit dcf08f1](https://github.com/arc53/DocsGPT/tree/dcf08f1b5a474b00d5981e00d1edb33529559571)

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

hello-agents, with 86,039 stars; DocsGPT has 18,360.

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

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

DocsGPT, with 1,391 test files; hello-agents has 97.

The proof: [arc53/DocsGPT's code at commit dcf08f1](https://github.com/arc53/DocsGPT/tree/dcf08f1b5a474b00d5981e00d1edb33529559571)

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

DocsGPT: its last push was on November 6, 2026, and hello-agents's on October 13, 2026.

The proof: [arc53/DocsGPT's commits on GitHub](https://github.com/arc53/DocsGPT/commits)

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

hello-agents: an AI signed 2.4% of its commits, with Codex, Cursor, and Claude Code; in DocsGPT, 0.3%.

## Sources

- arc53/DocsGPT: Read on November 6, 2026, at commit dcf08f1 (https://github.com/arc53/DocsGPT/tree/dcf08f1b5a474b00d5981e00d1edb33529559571)
- datawhalechina/hello-agents: Read on November 4, 2026, at commit 36f583c (https://github.com/datawhalechina/hello-agents/tree/36f583c233ea5cee4537ef93455702b55053af18)

## 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.