GraphCanon updated 1d · GitHub synced 1d
Decision brief
AgentGuide is an AI agent development guide that also focuses on career and interview preparation with resources specific to the field of building agents.
Good fit when
- Use AgentGuide if you need systematic guidance in developing AI agents and are preparing for job interviews in this niche.
- Leverage it for detailed coverage on advanced RAG, reinforcement learning, and data synthesis related to AI agent development.
Avoid when
- Do not use AgentGuide if you prefer tools that focus solely on AI model development without career advice or interview preparation content.
- Avoid this guide if you are looking for resources that are more focused on general machine learning concepts rather than the specific domain of AI agents.
Observed Jul 14, 2026 · Source: enrich:decision_facts
Verify the decision
Maintenance and security
Full trust report- Maintenance
- Active (14d since push)
- As of 1d
- Provenance
- Not a fork · Personal account
- As of 1d
- Security (OSV)
- No lockfile
- As of 1mo
Public GitHub metadata and optional OSV scans. Signals, not a guarantee. Trust methodology.
Install
git clone https://github.com/adongwanai/AgentGuideHow it fits your stack(8)
Typed graph edges - alternatives, integrations, successors, and dependencies. Ranked by relationship type, not raw GitHub stars.
Alternative
Integrates
Relationship graph
Optional deeper exploration of typed edges and category neighbours.
Similar tools
Same-category neighbours not already linked as typed edges.
Evidence and technical details
Sourced facts, taxonomy, compatibility claims, README excerpt, and machine-readable endpoints.
Overview
A comprehensive resource for developing AI agents, including high-level RAG, large model transitions, job interviews, reinforcement learning, and data synthesis.
Capability facts
- Languages
- html
Source: github.language · Aug 18, 2026
Categories
Graph entities
Compatibility
Sourced claims from the README excerpt - not unsourced marketing copy.
Source: README excerpt (regex_v1, Aug 18, 2026)
- ❌ **看了无数篇 LangChain 文档,却依然不知道从哪里开始**Source link
Source: README excerpt (regex_v1, Aug 18, 2026)
- [📖 技术教程](#-第五步系统学习-agent-技术技术准备) - LangGraph、RAG、上下文工程、监督微调、强化学习Source link
Tags
README
AgentGuide
💡 核心理念
📌 本项目定位:资源整合 + 系统化路径 + 实战导向
🎯 我们的原则:
- ✅ 站在巨人的肩膀上 - 互联网已有的优质资源(课程、教程、论文),我们直接引用,不重复造轮子
- ✅ 只分享干货 - (坚持更新中,欢迎催更)
- ✅ 提供系统化路径 - 将碎片化资源串联成完整学习路线,告诉你先学什么、再学什么
- ✅ 求职导向 - 每个知识点都标注"面试怎么考"、"简历怎么写"
💪 AgentGuide 的独特价值:不是简单的资源堆砌,而是系统化 + 求职导向 + 实战验证的完整解决方案!
📑 目录
🎯 核心内容:
- 💡 关于本项目 - Agent开发指南、转行大模型、高级RAG、大模型面试
- 🆕 求职新范式 - 1-2-5框架、个人品牌、投递策略
- 🧭 Agent 求职通关 Todo List - 当前优先级、8阶段学习产出、项目落地5步法
- 🚦 6步学习路径 - 从岗位选择到拿Offer
- 🔬 算法岗 vs 🛠️ 开发岗 - 岗位选择决策树
- 📚 学习路线图 - 算法岗10-15周 | 开发岗8-12周
- 💼 实战项目 - 开源优质项目合集+N X Agent项目
- 📖 技术教程 - LangGraph、RAG、上下文工程、监督微调、强化学习
- 🎯 面试题库 - 1500+题/面经、系统设计、编程题
🛠️ 快速导航:
- ⭐ 阿东作品推荐:learn-workbuddy - 从 0 搭建 WorkBuddy-style Desktop Agent Harness,clean-room 教学复现 Agent Loop、工具调用、上下文工程、长期记忆、Sidecar、权限审计和真实模型评测
- 🚀 10分钟快速开始 | 💬 加入学习社群 | ❓ 常见问题
- 🧭 新手快速开始 | 🧭 2026 Agent 求职路线 | 🛠️ Agent 项目落地方法 | 🧩 Agent Harness Engineering
- 🔬 前沿算法完整路线 | 🤖 具身智能/VLA路线 | 💻 算法+AI手撕题库 | 📋 小红书AI算法岗面经
- 📄 Paper Agent | 🧳 Travel Agent | 🌐 Web Agent | 🖼️ Multimodal RAG
📖 关于本项目
3 分钟了解为什么你需要 AgentGuide
😰 你是否正在经历这些痛点?
- ❌ 学了一堆 LLM API 调用,但不知道 Agent 和普通对话有什么区别
- ❌ 看了无数篇 LangChain 文档,却依然不知道从哪里开始
- ❌ 做了一些 Demo 项目,但简历上写不出亮点,面试讲不清楚
- ❌ 想转 AI Agent 方向,但不知道算法岗和开发岗应该准备什么
- ❌ 网上资料又多又杂,缺少一条清晰的学习路线
AgentGuide 是什么?
AI Agent 开发学习指南 | 转行大模型 | LangGraph 实战 | 高级RAG | 大模型面试
一份系统化、求职导向的 AI Agent 学习与面试指南,涵盖:
- Agent 工程:Agent Loop、LangGraph / OpenAI Agents SDK、MCP、Skills、权限与状态管理
- Context Engineering:上下文分层、Memory、Tool Loadout、长任务压缩、成本与缓存优化
- RAG / Multimodal RAG:文档解析、Embedding、Rerank、GraphRAG、Agentic RAG、视觉文档检索
- Eval / Observability / Safety:Agent 评测集、trace、LLM-as-judge、红队、安全边界与 human-in-the-loop
- Post-training / Agent RL:SFT、偏好优化、GRPO/DPO、工具调用数据合成、轨迹数据训练
- 实战与求职:Paper Agent、Travel Agent、Web Agent、项目复盘、简历表达与面试题库
🗺️ AgentGuide 在 LLM 生态中的定位
我们覆盖 AI Agent 开发的完整技术栈 - 从模型微调到应用部署的全流程:
For agents
This page has a .md twin and JSON over the API.