# datawhalechina/hello-agents

> Datawhale's open tutorial on building AI agents from scratch: from theory (ReAct, Plan-and-Solve, Reflection) to a custom HelloAgents framework, memory, RAG, MCP and Agentic RL. Aimed at developers and students with basic Python who want to move from using LLMs to building agent systems.

- Magnitude: 3.4 out of 10 — Steady
- Stars: 82,217 total · +19 stars measured 2026-10-09, 11:35–13:11 UTC, ≈ 63 by evening
- Star trust: star growth looks organic
- Category: AI agents · Language: Python · Created: 2025-09-07 · Last push: 2026-10-08
- GitHub: https://github.com/datawhalechina/hello-agents · Homepage: https://hello-agents.datawhale.cc · Page: https://gitnova.dev/en/r/datawhalechina/hello-agents

## Useful for

- Follow the course and implement classic agent patterns ReAct, Plan-and-Solve and Reflection
- Build your own HelloAgents agent framework on top of the OpenAI API
- Study MCP, memory, RAG and Agentic RL to design multi-agent applications

## Why it’s here

- Star-counter measurements on 2026-10-09 (UTC), 11:35–13:11: 82198 → 82217 stars (+19). This is the change over that interval.
- Estimated end-of-day forecast: about +63 stars, using observed gains and the previous day.
- GitHub Trending Python today: #9, +193 stars.
- About 33 forks a day — people are taking the code.

## Star trust

Star growth looks organic.

Star-trust labels are heuristics based on the repository’s behavior, not a check of every stargazer.

## Numbers

- Forks: 10,198
- Issues and pull requests: 783
- Watchers: 232
- Average over the last week: 95 per day
- Usual pace: 145 per day
- Stars in the last hour (measured): 13
- Latest release: V1.0.3 (2026-07-17)

## Stars per day, last 30 days (oldest → newest, today is partial)

2026-09-10 … 2026-10-09: 227, 151, 139, 214, 211, 225, 240, 234, 133, 154, 193, 209, 186, 159, 94, 74, 83, 111, 184, 144, 90, 62, 74, 58, 86, 67, 81, 129, 181, 19

## Spotted in now

- GitHub Trending Python today: #9, +193 stars

## More in this category

1. **morluto/rea** — 9.3 · Breakout · AI agents · TypeScript · +10,030 stars measured 2026-10-09, 00:04–13:08 UTC, ≈ 17,097 by evening
   A reverse-engineering tool that lets AI agents inspect apps and native binaries: it connects agents to Hopper or Ghidra via MCP and CLI, helping explain how a feature works and rebuild it in your own project.
   Full card: https://gitnova.dev/en/r/morluto/rea.md
2. **zhongerxin/iPhone-use** — 8.2 · Early signal · AI agents · Python · +1,012 stars measured 2026-10-09, 00:05–13:08 UTC, ≈ 1,630 by evening
   Lets Codex control a real iPhone over USB via WebDriverAgent: it installs and signs WDA, exposes MCP tools for app navigation, taps, typing and list collection, and shows a live screen widget.
   Full card: https://gitnova.dev/en/r/zhongerxin/iPhone-use.md
3. **docker/docker-agent** — 7.3 · Breakout · AI agents · Go · +55 stars measured 2026-10-09, 00:04–13:08 UTC, ≈ 150 by evening
   Docker CLI plugin for building and running AI agents from a declarative YAML config with tools, MCP servers, and multi-agent orchestration. Lets you assemble agent teams without writing code and share them via OCI registry.
   Full card: https://gitnova.dev/en/r/docker/docker-agent.md
4. **thedotmack/claude-mem** — 7.2 · Breakout · AI agents · TypeScript · +423 stars measured 2026-10-09, 00:05–13:08 UTC, ≈ 768 by evening
   Persistent memory system for Claude Code and other agents: it captures agent actions via lifecycle hooks, compresses them into semantic summaries, and injects relevant context into future sessions.
   Full card: https://gitnova.dev/en/r/thedotmack/claude-mem.md
5. **Ebony-Vinyl/dsh-our-free-model** — 6.5 · Breakout · AI agents · JavaScript · +685 stars measured 2026-10-09, 00:05–13:09 UTC, ≈ 1,198 by evening · unusual star pattern (heuristic)
   A dsh plugin that adds free access to Muse Spark 1.3, MiMo V2.6 and other models without sign-up or API key, plus a local OpenAI-compatible proxy and usage dashboard.
   Full card: https://gitnova.dev/en/r/Ebony-Vinyl/dsh-our-free-model.md

---

Magnitude (0–10) measures how fast and how unusually interest in a repository is growing right now. It is not a quality score.
Days are UTC. “So far today” is a fact; “expected by the end of the day” is a forecast.
Summaries and use cases are written by an LLM (DeepSeek V4.1 Flash) from the README and may be inaccurate: verify specific claims (benchmarks, speed, hardware) in the repository itself.
Data as of 2026-10-09 13:25 UTC, updated every 30 minutes.