# datawhalechina/Agent-Learning-Hub

> A curated AI Agent learning roadmap: an 8-stage todo list with links to official docs, papers, and open-source projects for people who want to build reliable agents instead of collecting random links.

- Magnitude: 1.8 out of 10 — Steady
- Stars: 8,161 total · +0 stars on 2026-09-24 (UTC), ≈ 22 by evening
- Star trust: star growth looks organic
- Category: Learning & lists · Language: HTML · License: MIT · Created: 2026-05-17 · Last push: 2026-07-19
- GitHub: https://github.com/datawhalechina/Agent-Learning-Hub · Homepage: https://datawhalechina.github.io/Agent-Learning-Hub/ · Page: https://gitnova.dev/en/r/datawhalechina/Agent-Learning-Hub

## Useful for

- Complete Stage 1 and write a minimal 50-150 line agent loop with tool calls.
- Build a research assistant from Stage 2: search, filter, summarize, and cite sources.
- Study one agent harness in Stage 3 and add your own tool to it.

## Why it’s here

- 0 stars so far today, about 22 expected by the end of the day.

## 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: 828
- Issues and pull requests: 18
- Watchers: 15
- Average over the last week: 29 per day
- Usual pace: 40 per day

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

2026-09-30 … 2026-10-29: None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None

## Magnitude by day, last 12 days

09-13 2.1, 09-14 2.3, 09-15 2.3, 09-16 2.3, 09-17 2.3, 09-18 2.3, 09-19 1.9, 09-20 2.1, 09-21 2.2, 09-22 2.1, 09-23 2.1, 09-24 1.8

---

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 2026-09-24 00:01 UTC, updated every 30 minutes.