tingaicompass/AI-Compass

“AI-Compass”将为社区指引在 AI 技术海洋中航行的方向，无论你是初学者还是进阶开发者，都能在这里找到通往 AI 各大方向的路径。旨在帮助开发者系统性地了解 AI 的核心概念、主流技术、前沿趋势，并通过实践掌握从理论到落地的全过程。

What it solves

AI-Compass is a comprehensive, systematically organized AI learning ecosystem designed to guide users from beginner to advanced levels. It solves the problem of fragmented AI information by integrating a full knowledge system—from basic theory to frontier applications—into a single, structured repository that serves as both a curated resource library and a local knowledge base for AI coding assistants.

How it works

The project is organized into nine core modules that cover the entire AI technology stack:

  • Blog Module: Technical articles on Python, algorithms, and LLM guides/interview prep.
  • Code Module: Runnable AI engineering examples, such as a complete RAG system based on Milvus.
  • Basic Knowledge: Entry points for tool discovery, prompt engineering, model benchmarks, and LLM collections (text and multimodal).
  • Technical Frameworks: Resources on embedding models, training frameworks, inference deployment, and RLHF.
  • Application Practice: Focuses on frontier architectures like RAG+workflow, Agents, GraphRAG, and MCP+A2A.
  • Product & Tools: AI applications, products, and competition resources.
  • Learning Resources: Academic tools, selected articles, and software for systematic growth.
  • Enterprise Open Source: Resources from major companies like Huawei, Tencent, Alibaba, and Baidu.
  • Community & Platforms: Forums and technical article platforms.

Additionally, the repository includes a weeklyHighlights directory that tracks incremental updates and new AI tools/models, allowing users to maintain a current view of the fast-moving AI landscape.

Who it’s for

  • AI Beginners: Those needing a structured learning path to build a foundational understanding of AI.
  • Technical Developers: Developers seeking deep technical resources and engineering guides to improve AI project deployment.
  • Product Managers: Those looking for AI product design methodologies and market case studies.
  • Researchers: Individuals tracking frontier technology trends and academic resources.
  • Enterprise Teams: Teams needing AI technology selection and implementation plans for digital transformation.
  • Job Seekers: Those preparing for AI-related interviews with project experience and study materials.

Highlights

  • AI Assistant Ready: Specifically structured to be used as a local knowledge base for tools like Claude Code and Codex for intelligent Q&A and project decomposition.
  • Comprehensive Scope: Covers everything from basic Python and LeetCode to advanced RAG, Agents, and multimodal models.
  • Systematic Organization: Moves beyond a simple list of links by providing a curated, multi-layered architecture of knowledge.
  • Weekly Incremental Updates: A dedicated system for tracking the latest AI breakthroughs and tool releases via weekly reports.