agent-interview-hub

by Zchary1106Verified

AI Agent 工程师面试资料库 - 国内大厂面经、岗位要求、高频面试题

222
Stars
29
Forks
HTML
Language
8/23/2026
Added
View on GitHubDownload ZIP

⚠️ Third-Party Software Notice

This skill is third-party open-source software developed and hosted independently on GitHub. SkillTip is an informational directory and does not control or maintain the underlying repository. Any security checks displayed are automated and limited in scope. Review the source code before installing.

Read the Terms of Service

Installation

Add to your Claude Code skills directory:

# Add to your Claude Code skills
git clone https://github.com/Zchary1106/agent-interview-hub

Getting Started

Guides for using skills like agent-interview-hub.

Security Report

Verified

Last scanned: —

{
  "status": "PASSED",
  "issues": []
}

README.md

🤖 Agent Interview Hub

国内最全的 AI Agent 工程师面试知识库

Stars Forks License Last Commit

300+ 面试题(全部带答案)· 14 家公司岗位要求与面经(含 Anthropic 等海外顶级 AI 公司)· 6 道实操考题 · 16 周完整学习路线图

📖 经典版 · ✨ 新版 · ⭐ Star 支持 · 🐛 提交面经


📌 这是什么?

专为国内大厂 AI Agent 工程师跳槽/求职打造的一站式面试知识库。

  • 🎯 面向谁 — 准备跳槽阿里、字节、腾讯、百度等大厂 Agent 岗位的工程师
  • 📚 包含什么 — 300+ 高频面试题(全部附答案)、9 家大厂岗位要求与真实面经、6 道限时实操考题、20 篇深度技术文档
  • 🗺️ 学习路线 — 从零到 Offer 的 16 周完整学习计划
  • 特色亮点 — 题目全带答案、面经来自牛客真实分享、支持 GitHub Pages 在线浏览

🧭 知识体系

AI Agent 工程师知识体系
│
├── 🧱 基础层
│   ├── Transformer 架构与注意力机制
│   ├── LLM 原理 / Tokenization / Embedding
│   └── Prompt Engineering 基础
│
├── 🔧 核心层
│   ├── Agent 设计模式(ReAct / Plan-and-Execute / Multi-Agent)
│   ├── RAG 全链路(检索 / 分块 / 重排 / 生成)
│   ├── Function Calling / Tool Use 🆕
│   ├── MCP(Model Context Protocol)🆕
│   ├── 主流框架(LangChain / LangGraph / AutoGen)
│   └── Context Engineering 上下文工程
│
├── 🚀 进阶层
│   ├── Agentic RAG / GraphRAG
│   ├── Agentic Coding 与 AI 编程工具 🆕
│   ├── 模型微调 / 推理优化 / 量化部署
│   └── Agent 安全、评估与对齐
│
└── 💼 实战层
    ├── 系统设计与项目经验
    ├── 大厂岗位要求解读
    └── 面试技巧与真实面经

🗺️ 学习路线图

16 周从基础到 Offer,每周有明确目标和推荐资料

➡️ Agent工程师学习路线图.md


📚 通用知识

🔧 核心技术

#文档简介
112 周 Agent 工程师进阶路线以周为单位交付 RAG、Agent、MCP、生产化作品集
2Agent 核心概念与设计模式ReAct、Plan-and-Execute、Multi-Agent 等核心范式
3Agent 框架全景LangChain、AutoGen、CrewAI 等主流框架横评
4LangChain 与 LangGraph 深度解析链式调用到图编排的演进与实战
5RAG 核心知识与面试题检索增强生成全链路:分块、检索、重排、生成
6Agentic RAG 与 GraphRAG 深度解析从朴素 RAG 到 Agent 驱动的智能检索
7Context Engineering 上下文工程上下文窗口管理、压缩与优化策略(含 Anthropic 最新实践)🔄
8Agent 安全与评估体系Prompt 注入防御、幻觉检测、评估框架
9大模型推理优化与部署量化、蒸馏、KV Cache、vLLM 等推理加速
10Function Calling 与 Tool Use 专题三大厂商实现对比、调用模式、安全防御 🆕
11MCP 与工具生态Model Context Protocol 架构、开发实战、企业应用 🆕
12Agentic Coding 与 AI 编程工具Claude Code / Cursor / Copilot 对比、Hooks、人机协作 🆕
13Agent Harness 与编码代理测评Codex CLI / Claude Code / OpenHands 等 Harness 深度测评与源码入口 🆕

📝 面试题库

#文档简介
14最新 AI Agent 面经索引(2026)牛客、小红书、知乎、CSDN、GitHub 等公开来源的最新面经入口
15核心概念详解与参考答案高频概念题精讲与标准答案
16八股文完整答案集69 道八股题,全部附详细解答
17八股文题库 - DataWhale 开源DataWhale 社区精选题库
18高频拷打题 - 牛客热帖牛客论坛高赞面试拷打合集
19技术知识点汇总速查手册:关键知识点一网打尽
20其他公司面经 - 快手携程等快手、携程等公司面经补充

🌐 进阶面试题

#文档简介
21Agent 核心概念面试题 - 进阶篇核心概念高频问答进阶版
22系统设计面试题 - 进阶篇系统设计题与参考答案进阶版
23AI 协作与工程化面试题 - 进阶篇AI 协作工程化问答进阶版
24交互式面试算法题图谱近期公开 Agent / 大模型面经算法题,附可折叠 Java 解法

🎯 实操考题(限时挑战)

来自 agent-interview-prep 项目,模拟真实面试场景的限时编程题

🗺️ 使用 Obsidian 的同学可以打开 Agent 工程师知识地图,从长期路线、核心知识、项目实战和公司面经四条线复习。

#题目难度限时
1智能文档问答 Agent⭐⭐4-6h
2多 Agent 团队协作⭐⭐4-6h
3ReAct 模式 Agent⭐⭐3-5h
4AI 限时全栈开发⭐⭐2-3h
5AI 调试挑战⭐⭐⭐1-2h
6AI Code Review Agent⭐⭐⭐4-6h

🏢 国内大厂面经

公司岗位要求面试题真实面经
阿里巴巴
字节跳动
小红书
百度
腾讯
美团
蚂蚁集团
华为
快手

🌍 海外顶级 AI 公司面经

公司岗位要求面试题真实面经
OpenAI
Anthropic 🆕
谷歌 (Google DeepMind)
微软 (Microsoft)
初创公司

📖 海外公司综合攻略:海外顶级AI公司面试攻略-2026 🆕


🚀 使用指南

在线阅读(推荐)

访问 GitHub Pages 站点,移动端友好:

经典版保持原有内容和默认地址,并在页面顶部提示切换新版;新版使用新的求职准备布局。

本地阅读

git clone https://github.com/Zchary1106/agent-interview-hub.git
cd agent-interview-hub
# 用任意 Markdown 编辑器打开即可

本地构建静态站

python3 -m pip install -r requirements.txt
python3 scripts/build_site.py
python3 -m http.server 8000 -d dist

生成结果会输出到 dist/。GitHub Pages 通过 .github/workflows/pages.ymlmain 分支 push 后自动构建并发布。

安装面经采集 Agent

本仓库内置 Interview Collector Agent,用于从牛客、小红书、知乎、CSDN、博客园、掘金、GitHub 等公开来源搜索面经,整理成结构化候选,再同步到索引和公司文档。

bash agents/interview-collector/install.sh --targets copilot,claude,cursor,generic

支持安装到:

平台写入位置
GitHub Copilot CLI~/.copilot/instructions/interview-collector.instructions.md
Claude Code~/.claude/skills/interview-collector/SKILL.md
Cursor.cursor/rules/interview-collector.mdc
通用/国内 Agent~/.agent-interview-hub/interview-collector/AGENT.md

详见 Interview Collector Agent 说明

完整采集流程也可以用脚本跑:

# 1. 检查本机搜索/读取工具
python3 scripts/collect_interviews.py doctor

# 2. 搜索公开来源,生成候选 JSON 和 Markdown 报告
python3 scripts/collect_interviews.py search \
  --platform nowcoder \
  --platform zhihu \
  --platform blogs \
  --platform github \
  --query "AI Agent 大模型 面经 2026" \
  --output data/interview_candidates.json \
  --report data/interview_candidates.md

# 3. 人工或 Agent 审核候选后,再整理进 data/interviews.json
python3 -m json.tool data/interviews.json
python3 scripts/build_site.py

如果本机已配置 OpenCLI,也可以追加小红书搜索:

python3 scripts/collect_interviews.py search \
  --platform xiaohongshu \
  --query "AI Agent 面经" \
  --append

推荐阅读顺序

  1. 📖 先看 学习路线图,了解全局
  2. 🧱 通读 Agent 核心概念与设计模式
  3. 🔧 深入 RAGLangChain/LangGraph
  4. 🆕 掌握 Function CallingMCP(2025 高频新考点)
  5. 📝 刷 八股文完整答案集(69 题)
  6. 🏢 针对目标公司看对应面经
  7. 🔥 最后用 高频拷打题 查漏补缺

🤝 贡献指南

欢迎一切形式的贡献!

  • 📝 提交面经 — 通过 Issue 分享你的面试经历
  • 🔧 提交 PR — 补充题目、修正答案、新增公司面经
  • ⭐ Star — 最简单的支持方式,让更多人看到

贡献步骤

# 1. Fork 本仓库
# 2. 创建分支
git checkout -b feat/add-xxx-interview
# 3. 提交更改
git commit -m "feat: 新增 xxx 面经"
# 4. 推送并创建 PR
git push origin feat/add-xxx-interview

Star History

Star History Chart

📄 License

本项目采用 MIT License 开源。


如果这个项目对你有帮助,请给一个 ⭐ Star 支持!

Made with ❤️ for AI Agent Engineers

Frequently Asked Questions

What is agent-interview-hub?

agent-interview-hub is an open-source ai agents skill for AI coding assistants such as Claude Code, Codex CLI, and ChatGPT, built by Zchary1106. AI Agent 工程师面试资料库 - 国内大厂面经、岗位要求、高频面试题. It has 222 GitHub stars.

Is agent-interview-hub safe to use?

Yes. agent-interview-hub passed SkillsLLM's automated security scan — a dependency vulnerability audit plus prompt-injection heuristics — with no high-severity issues. You can read the full report in the Security Report section on this page.

How do I install agent-interview-hub?

Clone the repository with "git clone https://github.com/Zchary1106/agent-interview-hub" and add it to your Claude Code skills directory (see the Installation section above).

What programming language is agent-interview-hub written in?

agent-interview-hub is primarily written in HTML. It is open-source under Zchary1106 on GitHub, so you can review or fork the full source.

Are there alternatives to agent-interview-hub?

Yes. SkillsLLM lists many other AI Agents skills you can browse and compare side by side. Open the AI Agents category from the badge at the top of this page, or use the Related Skills and comparison links further down to weigh agent-interview-hub against similar tools.

Comments (0)

No comments yet. Be the first to share your thoughts!

ECC

by affaan-m

10

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

242,21936,702JavaScript
AI Agentsai-agentsanthropicclaude-code
View details
15

An agentic skills framework & software development methodology that works.

234,96620,863Shell
AI Agentsai-agentsbrainstorming
View details

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

185,94028,768JavaScript
AI Agentsai-agentsanthropicclaude-code
View details

cc-switch

by farion1231

3

A cross-platform desktop All-in-One assistant for Claude Code, Codex, OpenCode, OpenClaw, Grok Build & Hermes Agent. Only official website: ccswitch.io

128,8688,826Rust
AI Agentsclaude-codeai-tools
View details

claude-code

by anthropics

Claude Code is an agentic coding tool that lives in your terminal, understands your codebase, and helps you code faster by executing routine tasks, explaining complex code, and handling git workflows - all through natural language commands.

120,03119,897Shell
AI Agents
View details

Developers Also Liked

Based on votes and bookmarks from developers who liked this skill

ECC

by affaan-m

10

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

242,21936,702JavaScript
AI Agentsai-agentsanthropicclaude-code
View details
15

An agentic skills framework & software development methodology that works.

234,96620,863Shell
AI Agentsai-agentsbrainstorming
View details

n8n

by n8n-io

12

Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations.

201,88160,308TypeScript
MCP Serversapisai-tools
View details

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

185,94028,768JavaScript
AI Agentsai-agentsanthropicclaude-code
View details

cc-switch

by farion1231

3

A cross-platform desktop All-in-One assistant for Claude Code, Codex, OpenCode, OpenClaw, Grok Build & Hermes Agent. Only official website: ccswitch.io

128,8688,826Rust
AI Agentsclaude-codeai-tools
View details