adongwanai/AgentGuide

https://adongwanai.github.io/AgentGuide | AI Agent开发指南 | LangGraph实战 | 高级RAG | 转行大模型 | 大模型面试 | 算法工程师 | 面试题库 | 强化学习｜数据合成

What it solves

AgentGuide provides a systematic, career-oriented knowledge base for individuals looking to enter the AI Agent field. It addresses the fragmentation of learning resources by organizing them into structured paths for both algorithm engineers (focused on research and innovation) and development engineers (focused on system implementation and business deployment), while specifically guiding users on how to build "resume-grade" projects and pass technical interviews.

How it works

The project organizes content around the principle of "making it, running it stably, measuring it accurately, and explaining it clearly." It provides:

  • Structured Roadmaps: Tailored learning paths (8-15 weeks) for different roles, moving from basic concepts to advanced implementation.
  • Technical Stack Coverage: Comprehensive guides on Agent Loops, Context Engineering, Memory, Tool protocols (MCP, Skills), RAG (GraphRAG, Agentic RAG), and Post-training (SFT, DPO/GRPO).
  • Job-Hunting Framework: A "1-2-5 framework" that shifts focus from "what I've learned" to "what I've built," including advice on personal branding and AI-driven application strategies.
  • Interview Preparation: A library of 1,500+ interview questions and guides on how to describe projects using architecture, business, and result-based dimensions.

Who it’s for

  • Aspiring AI Agent Algorithm Engineers, AI Agent Development Engineers, and RAG System Engineers.
  • LLM Application Engineers and Multimodal Algorithm Engineers.
  • Developers and researchers wanting to transition into the LLM/Agent space.

Highlights

  • Career-Centric Approach: Every knowledge point is mapped to how it is tested in interviews and how to write it on a resume.
  • Dual-Track Path: Separate but complementary paths for algorithm-focused (research/innovation) and development-focused (engineering/stability) roles.
  • Comprehensive Tech Stack: Covers the full lifecycle from model fine-tuning and RAG to Agent harness engineering and observability.
  • Practical Project Guidance: Includes a 5-step method for landing projects that are verifiable and a "Todo List" for tangible learning outputs.

Related

  • Project
    chujianyun/skills

    A library of reusable Agent Skills and workflows for AI agents, covering everything from prompt optimization and document interpretation to system operations and career coaching.

  • Project
    bytedance/agentkit-samples

    A collection of tutorials and reference implementations for AgentKit, an enterprise AI Agent platform, covering everything from basic dialogue to complex multi-agent systems and RAG.

  • Project
    agentscope-ai/agentscope

    A production-ready agent framework that provides an SDK and a FastAPI-based service to build, deploy and scale multi-agent applications with built-in RAG and tool management.

  • Project
    oxbshw/LLM-Agents-Ecosystem-Handbook

    A production-oriented handbook and toolkit for building LLM agent systems, featuring a multi-provider router, design templates, and comprehensive guides on memory, skills, and safety.