$ show datawhalechina/Agent-Learning-Hub
This repository is a curated, interactive learning roadmap for building AI agents. It is not a software library or framework, but a single-page web application (index.html) that renders a comprehensive todo list, project ladder, and curated resource collection. The application allows users to track progress via checkboxes stored in localStorage, take Markdown notes per stage, search content, toggle dark mode, and navigate via a sidebar. The underlying data is a static JSON structure embedded in the JavaScript. The repo's primary value is its meticulously organized learning path covering agent loops, tool use, RAG, multi-agent coordination, skills/protocols, browser agents, evaluation, and production deployment. It references dozens of high-quality external resources (official docs, papers, open-source projects) and provides clear learning principles. While the repo contains no runnable agent code, the interactive frontend is a well-crafted tool for self-paced learning. The codebase is a hybrid: it is an application (web UI) but its content is a curated research/learning resource.
The LLM identified 1 files worth highlighting for reuse:
The entire application is contained in a single HTML file. It implements a self-contained interactive learning tracker with features: progress checkboxes with localStorage persistence, a Markdown note editor with live preview, full-text search with highlighting, dark mode toggle, responsive sidebar navigation, and scroll-spy. The architecture is a clean separation of data (JavaScript objects for stages, ladder, resources) and rendering logic. This pattern is directly reusable as a template for any structured learning roadmap or checklist-based tutorial site. The note editor component, in particular, demonstrates good UX with inline editing, Markdown rendering via the 'marked' library, and debounced preview updates.