Source: https://seerepo.com/compare/datawhalechina/hello-agents/vs/MemTensor/MemOS
Markdown source: https://seerepo.com/compare/datawhalechina/hello-agents/vs/MemTensor/MemOS.md
Description: hello-agents and MemOS share 41 technologies: FastAPI, uvicorn, psycopg2-binary, Postgres, Redis, SQLite, pymilvus, OpenAI, Qdrant, Hugging Face, React, fastmcp, starlette, anyio, Vite, react-router-dom, soupsieve, Rich, SQLAlchemy, MCP, onnxruntime, safetensors, tavily-python, tokenizers, torch, transformers, scikit-learn, sentence-transformers, rank-bm25, lxml, openpyxl, xlrd, pillow, beautifulsoup4, jinja2, annotated-types, email-validator, Pydantic, jsonschema, Tailwind CSS, and react-markdown. hello-agents is written in Python and MemOS in TypeScript.

# hello-agents vs MemOS

hello-agents and MemOS share 41 technologies: FastAPI, uvicorn, psycopg2-binary, Postgres, Redis, SQLite, pymilvus, OpenAI, Qdrant, Hugging Face, React, fastmcp, starlette, anyio, Vite, react-router-dom, soupsieve, Rich, SQLAlchemy, MCP, onnxruntime, safetensors, tavily-python, tokenizers, torch, transformers, scikit-learn, sentence-transformers, rank-bm25, lxml, openpyxl, xlrd, pillow, beautifulsoup4, jinja2, annotated-types, email-validator, Pydantic, jsonschema, Tailwind CSS, and react-markdown. hello-agents is written in Python and MemOS in TypeScript.

- [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
- [MemTensor/MemOS](https://seerepo.com/r/MemTensor/MemOS): Self-evolving memory OS for LLM & AI Agents: ultra-persistent memory, hybrid-retrieval, and cross-task skill reuse, with 35.24% token savings and DeepSeek Harness support.

## What they share and what sets them apart

- In common: FastAPI, uvicorn, psycopg2-binary, Postgres, Redis, SQLite, pymilvus, OpenAI, Qdrant, Hugging Face, React, fastmcp, starlette, anyio, Vite, react-router-dom, soupsieve, Rich, SQLAlchemy, MCP, onnxruntime, safetensors, tavily-python, tokenizers, torch, transformers, scikit-learn, sentence-transformers, rank-bm25, lxml, openpyxl, xlrd, pillow, beautifulsoup4, jinja2, annotated-types, email-validator, Pydantic, jsonschema, Tailwind CSS, react-markdown
- Only in hello-agents: aiosqlite, asyncpg, chromadb, libsql-client, oracledb, Flask, python, react-dom, AIOHTTP, Streamlit, Vue, vue-router, cycler, fonttools, contourpy, ipywidgets, Plotly, Gradio, matplotlib, seaborn, alembic, python-jose, passlib, bcrypt, accelerate, bitsandbytes, camel-ai, mermaid, peft, textblob, hello-agents, agentscope, tiktoken, autogen-agentchat, autogen-ext, datasets, langchain-openai, langdetect, LangGraph, paddlenlp, spaCy, imaplib2, markdown, pdfminer.six, pypdf, python-docx, reportlab, pdfplumber, feedparser, pymupdf, pypdf2, pymupdf4llm, pydantic-core, kubernetes, OpenTelemetry, opentelemetry-exporter-otlp-proto-grpc, loguru, ant-design-vue, D3, @ant-design/icons-vue, katex, markdown-it, vue-flow, @monaco-editor/loader, Chart.js, vue-chartjs, highlight.js, dompurify, marked, Element, vue-echarts, echarts, @element-plus/icons-vue, Leaflet, @amap/amap-jsapi-loader, html2canvas, jspdf
- Only in MemOS: diskcache, py-key-value-aio, pymysql, Neo4j, pika, Alibaba Cloud, Preact, @deepseek-ai/dsh-session, @deepseek-ai/cordis, electron-store, Electron, Express, Hono, rich-toolkit, authlib, cryptography, itsdangerous, keyring, pyjwt, langsmith, nltk, NVIDIA, nvidia-cudnn-cu12, triton, LangChain, Ollama, chonkie, defusedxml, docutils, et-xmlfile, magika, mammoth, markdown-it-py, markdownify, markupsafe, mdurl, pdfminer-six, python-pptx, rich-rst, xlsxwriter, markitdown, beartype, jsonschema-path, jsonschema-specifications, openapi-pydantic, pathvalidate, referencing, coloredlogs, concurrent-log-handler, fastapi-cloud-cli, volcengine-python-sdk, prometheus-client, @sinclair/typebox, deepseek-ai, yaml, @deepseek-ai/schemastery, class-variance-authority, Radix UI, Framer, Lucide, @aws-sdk/credential-providers, @aws-sdk/client-bedrock, Zod, @hono/node-server

## Side by side

| | hello-agents | MemOS |
|---|---|---|
| Size | 226,661 lines written, 1,210 code files | 447,484 lines written, 898 code files |
| Who writes it | 2.4% of its commits signed by AI. With Codex, Cursor, and Claude Code | 10.8% of its commits signed by AI. With Cursor, Claude Code, and GitHub Copilot |
| Activity | Last push October 13, 2026, 660 commits, 86,519 stars | Last push November 11, 2026, 1,631 commits, 12,352 stars |
| Tests | 99 test files. 6.9% of its code files have a test that imports them | 480 test files. 46.1% 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 MemOS?

MemOS, with 447,484 lines written; hello-agents has 226,661.

The proof: [MemTensor/MemOS's code at commit 3a16e5f](https://github.com/MemTensor/MemOS/tree/3a16e5fe3048a209f722806f4123fa2e533588fd)

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

hello-agents, with 86,519 stars; MemOS has 12,352.

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

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

MemOS, with 480 test files; hello-agents has 99.

The proof: [MemTensor/MemOS's code at commit 3a16e5f](https://github.com/MemTensor/MemOS/tree/3a16e5fe3048a209f722806f4123fa2e533588fd)

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

MemOS: its last push was on November 11, 2026, and hello-agents's on October 13, 2026.

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

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

MemOS: an AI signed 10.8% of its commits, with Cursor, Claude Code, and GitHub Copilot; in hello-agents, 2.4%.

The proof: [the commits each tool signed in MemTensor/MemOS](https://seerepo.com/r/MemTensor/MemOS/ai)

## Sources

- datawhalechina/hello-agents: Read on November 9, 2026, at commit 36f583c (https://github.com/datawhalechina/hello-agents/tree/36f583c233ea5cee4537ef93455702b55053af18)
- MemTensor/MemOS: Read on November 11, 2026, at commit 3a16e5f (https://github.com/MemTensor/MemOS/tree/3a16e5fe3048a209f722806f4123fa2e533588fd)

## 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.