No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by Snailclimb · MCP Server · ★ 511
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is AIGuide safe to install? View the security audit →
AI 应用开发 你好，我是 JavaGuide 的作者。最近这段时间，我一直在补 AI 应用开发、AI 编程实战和 AI 面试这几块内容。 这份开源指南写给所有想系统学习 AI 应用开发与 AI 工程化落地 的同学：后端、前端、测试、架构师、技术管理者、产品技术同学都可以看。你不需要先转算法岗，也不需要一上来就啃训练框架和论文公式；这里重点放在 LLM、Agent、RAG、MCP、Prompt、评测、系统设计、Claude Code、Codex 这些做应用时会真正用到的东西。 如果你本来是 Java / Go 后端，会更容易把高并发、缓存、数据库、消息队列、可观测性这些经验迁移过来；如果你是前端、测试或产品技术方向，也可以从 Prompt、RAG、Agent、AI Coding、评测和系统设计切入，理解一个 AI 功能从 Demo 到上线到底要补哪些环节。 项目地址： 在线阅读： AI 编程专题： 目前每篇文章都会尽量配上真实工程场景、关键参数、踩坑点和图解。内容还在持续更新，有帮助的话欢迎 Star，也欢迎提 Issue 一起补充。 发布之后，收到了不少读者朋友的反馈和推荐。感谢大家，我会继续维护。 怎么读 如果你是第一次系统学 AI 应用开发，建议按这个顺序走： 先看 大模型基础：把 Token、上下文窗口、采样参数、API 调用、结构化输出和评测搞清楚。 再看 RAG：企业知识库问答最常见，坑也最多，文档处理、向量检索、更新链路和评测都得补。 接着看 AI Agent：重点理解 Tool Calling、Memory、MCP、Skills、Workflow / Graph / Loop。 最后看 AI 系统设计：把 Demo 放进生产环境，处理网关、限流、fallback、成本、观测、安全和灰度。 AI Coding 不是另一条完全独立的线。它更像是日常研发方式的升级，写业务代码、改前端页面、补测试、做重构、查线上问题都能用。建议一边学 AI 应用开发，一边用 Claude Code、Codex、Cursor、Trae 这类工具练起来。 面试题 AI 应用开发面试指南：把 LLM、RAG、Agent、系统设计这几条线串起来，适合系统复盘。 [大模型基础面试题总结](https://javaguide.cn/ai/interview-questions/llm-in
| Stars | 511 |
| Forks | 62 |
| Category | MCP Server |
| Quality Score | 50.4377413412312/100 |
| Last Updated | 2026-07-07 |
| Created | 2026-04-15 |
| Platforms | claude-code, codex, mcp |
| Est. Tokens | ~5k |
These tools work well together with AIGuide for enhanced workflows:
Looking for a AIGuide alternative? If you're comparing AIGuide with other mcp server tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
Structural code intelligence for AI agents — semantic search, knowledge graphs, and a built-in MCP server in o
A Go framework for building production agent systems with graph workflows, tools, memory, A2A, AG-UI, MCP, eva
100% Rust implementation of code graphRAG with blazing fast AST+FastML parsing, surrealDB backend and advanced
The missing linter and lsp for AI coding assistants. Validate CLAUDE.md, AGENTS.md, SKILL.md, hooks, MCP. Plug
Context-Engine MCP - Agentic Context Compression Suite
DeepContext is an MCP server that adds symbol-aware semantic search to Claude Code, Codex CLI, and other agent
Explore other popular mcp server tools:
AIGuide is AI 应用开发、AI 编程实战与面试指南，涵盖 LLM、Agent、RAG、MCP、Claude Code、Codex 等核心技术与工程实践。. It is categorized as a MCP Server with 511 GitHub stars.
You can find installation instructions and usage details in the AIGuide GitHub repository at github.com/Snailclimb/AIGuide. The project has 511 stars and 62 forks, indicating an active community.
The top alternatives to AIGuide on Agent Skills Hub include octocode, trpc-agent-go, codegraph-rust. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: