📦 Shubhamsaboo/awesome-llm-apps：100+ 可运行的 AI Agent 与 RAG 应用模板

Deutsch | Español | français | 日本語 | 한국어 | Português | Русский | 中文

---

100+ 个真正可运行的 AI Agent 与 RAG 应用——克隆、定制、交付。
AI 智能体 · 常驻智能体 · 多智能体团队 · MCP 智能体 · RAG · 语音智能体 · 智能体技能 · 微调

免费分步教程，尽在 Unwind AI
可与 Claude · Gemini · OpenAI · xAI · Qwen · Llama 配合使用

🚀 快速开始 📂 浏览模板 📚 分步教程

---

每次启动新的 LLM 项目，你都不必从头开始重建相同的 RAG 管道、Agent 循环或 MCP 集成。

Awesome LLM Apps 是一本可即时运行模板的“食谱”——你可以 Fork、定制并作为生产级 LLM 应用交付的起始代码。这里的每个模板都独立完整，提供全部源代码，并非从别处收集而来。

• 🛠️ 纯手写，非收集——每个模板都是原创作品，发布前经过端到端测试。
• 🧪 三条命令即可运行——没有残缺的 requirements.txt，没有“自己想办法”的脚手架。
• 🧠 覆盖现代 AI 技术栈——AI 智能体、常驻智能体、多智能体团队、MCP 智能体、语音 AI 智能体、RAG、智能体技能、微调。
• 🌐 模型无关——只需更改配置即可在 Claude、Gemini、GPT、Llama、Qwen、xAI 等模型间切换。
• 📚 分步教程——每个精选模板在 Unwind AI 上都有免费演练。
• 💸 Apache-2.0 许可——可 Fork、可交付、可商用。无付费墙、无需注册、无遥测。

⭐ 如果这为你节省了时间，请 star 本仓库——这就是下一位开发者发现它的方式。

只需 30 秒 运行你的第一个 Agent：

git clone https://github.com/Shubhamsaboo/awesome-llm-apps.git
cd awesome-llm-apps/starter_ai_agents/ai_travel_agent
pip install -r requirements.txt
streamlit run travel_agent.py

📬 订阅 Unwind AI，第一时间收到新模板推送与教程。

15 个类别 · 点击展开

单文件 Agent，只需一个 API 密钥即可运行——绝佳的入门选择。

具备工具、记忆与多步推理的生产级 Agent。

按计划或事件运行的后台 Agent，能监测变化的上下文，判断需要关注的事项，并主动推送更新、产出物或行动。

多个 Agent 协作完成复杂、跨领域的任务。

基于实时语音 API 的语音输入、语音输出 Agent。

🖼️ 生成式 UI 与智能化前端

能够渲染交互式 UI 组件——表单、卡片、图表、可编辑计划——而不仅仅是文本的 Agent。

🎮 自主游戏 Agent

端到端玩游戏的 Agent——推理、策略与行动。

通过模型上下文协议（MCP）连接外部工具与数据的 Agent。

📀 RAG（检索增强生成）

检索流水线——从简单链到智能化、多数据源检索。

即插即用的智能体技能文件，可接入任何 AI Agent 或 LLM 工作流。

📋 浏览全部 19 项技能

技能	描述
🎓 Academic Researcher	文献综述、论文分析、引用管理
🔍 Code Reviewer	自动化代码审查，附带最佳实践检查
✍️ Content Creator	博客文章、社交媒体、营销文案
📊 Data Analyst	数据探索、统计分析、洞察
🐛 Debugger	系统化缺陷排查与根因分析
🤔 Decision Helper	结构化决策框架与权衡分析
🔬 Deep Research	多源研究并形成综述
📝 Editor	校对、风格与清晰度提升
📧 Email Drafter	专业电子邮件撰写
✅ Fact Checker	声明验证与来源确认
💻 Fullstack Developer	端到端 Web 应用开发
📋 Meeting Notes	会议摘要、行动项、后续跟进
📅 Project Planner	路线图、里程碑、资源规划
🐍 Python Expert	Pythonic 代码、打包、性能优化
🏃 Sprint Planner	敏捷冲刺规划与待办事项梳理
🧭 Strategy Advisor	商业战略与竞争分析
📖 Technical Writer	文档、API 文档、指南
🎨 UX Designer	UI/UX 设计反馈与线框图
📈 Visualization Expert	图表、仪表盘、数据叙事

💾 带记忆的 LLM 应用教程

能够在各会话间记住对话与用户状态的 Agent 与聊天机器人。

将任何数据源转化为聊天界面。

在不牺牲质量的前提下减少 Token 消耗、上下文大小和 API 成本。

🔧 LLM 微调教程

面向开源模型的端到端微调配方。

🧑‍🏫 AI Agent 框架速成课

深度剖析主流 Agent 框架的教程。

Google ADK 速成课

• 入门 Agent；模型无关（OpenAI、Claude）
• 结构化输出（Pydantic）
• 工具：内置、函数、第三方、MCP 工具
• 记忆；回调；插件
• 简单多 Agent；多 Agent 模式

OpenAI Agents SDK 速成课

• 入门 Agent；函数调用；结构化输出
• 工具：内置、函数、第三方集成
• 记忆；回调；评估
• 多 Agent 模式；Agent 交接
• Swarm 编排；路由逻辑

由 Shubham Saboo 创建并维护，感谢出色的社区成员贡献。

🌟 不要错过后续更新——star 本仓库，新模板发布时你将收到通知。

Apache-2.0 许可。详见 LICENSE。可 Fork、可交付、可商用。

Deutsch | Español | français | 日本語 | 한국어 | Português | Русский | 中文

---

100+ AI Agent & RAG apps you can actually run — clone, customize, ship.
AI Agents · Always-on Agents · Multi-agent Teams · MCP Agents · RAG · Voice Agents · Agent Skills · Fine-tuning

Free step-by-step tutorials onUnwind AI
Works with Claude · Gemini · OpenAI · xAI · Qwen · Llama

🚀 Quick Start 📂 Browse Templates 📚 Step-by-Step Tutorials

---

You shouldn't have to rebuild the same RAG pipeline, agent loop, or MCP integration from scratch every time you start a new LLM project.

Awesome LLM Apps is a cookbook of ready-to-run templates - starter code you can fork, customize, and ship as a production LLM app. Every template here is self-contained with full source code, not collected from elsewhere.

• 🛠️ Hand-built, not curated - every template is original work, tested end-to-end before it ships.
• 🧪 Runs in 3 commands - no broken requirements.txt, no "figure it out yourself" scaffolding.
• 🧠 Covers the modern AI stack - AI Agents, Always-on Agents, Multi-agent Teams, MCP Agents, Voice AI Agents, RAG, Agent Skills, Fine-tuning.
• 🌐 Provider-agnostic - switch between Claude, Gemini, GPT, Llama, Qwen, xAI and others with a config change.
• 📚 Step-by-step tutorials - every featured template has a free walkthrough on Unwind AI.
• 💸 Apache-2.0 - fork it, ship it, sell it. No paywall, no signup, no telemetry.

⭐ If this saves you time,star the repo - that's how the next developer discovers it.

Run your first agent in 30 seconds :

git clone https://github.com/Shubhamsaboo/awesome-llm-apps.git
cd awesome-llm-apps/starter_ai_agents/ai_travel_agent
pip install -r requirements.txt
streamlit run travel_agent.py

📬 Subscribe on Unwind AI to get new template drops + tutorials in your inbox.

15 categories · Click to expand

Single-file agents that run with just an API key - a great place to start.

Production-style agents with tools, memory, and multi-step reasoning.

Background agents that run on schedules or events, monitor changing context, decide what needs attention, and proactively deliver updates, artifacts, or actions.

Multiple agents collaborating to accomplish complex, cross-domain tasks.

Speech-in, speech-out agents using real-time voice APIs.

🖼️ Generative UI and Agentic Frontends

Agents that render interactive UI components — forms, cards, charts, editable plans — not just text.

🎮 Autonomous Game-Playing Agents

Agents that play games end-to-end - reasoning, strategy, and action.

Agents that connect to external tools and data via Model Context Protocol.

📀 RAG (Retrieval Augmented Generation)

Retrieval pipelines - from simple chains to agentic and multi-source.

Ready-to-use agent skill files you can plug into any AI agent or LLM workflow.

📋 Browse all 19 skills Skill	Description
🎓 Academic Researcher	Literature reviews, paper analysis, citation management
🔍 Code Reviewer	Automated code review with best-practice checks
✍️ Content Creator	Blog posts, social media, marketing copy
📊 Data Analyst	Data exploration, statistical analysis, insights
🐛 Debugger	Systematic bug hunting and root-cause analysis
🤔 Decision Helper	Structured decision frameworks and trade-off analysis
🔬 Deep Research	Multi-source research with synthesis
📝 Editor	Proofreading, style, and clarity improvements
📧 Email Drafter	Professional email composition
✅ Fact Checker	Claim verification and source validation
💻 Fullstack Developer	End-to-end web app development
📋 Meeting Notes	Meeting summaries, action items, follow-ups
📅 Project Planner	Roadmaps, milestones, resource planning
🐍 Python Expert	Pythonic code, packaging, performance
🏃 Sprint Planner	Agile sprint planning and backlog grooming
🧭 Strategy Advisor	Business strategy and competitive analysis
📖 Technical Writer	Documentation, API docs, guides
🎨 UX Designer	UI/UX design feedback and wireframes
📈 Visualization Expert	Charts, dashboards, data storytelling

💾 LLM Apps with Memory Tutorials

Agents and chatbots that remember conversations and user state across sessions.

Turn any data source into a chat interface.

Reduce token usage, context size, and API cost without losing quality.

🔧 LLM Fine-tuning Tutorials

End-to-end fine-tuning recipes for open-source models.

🧑‍🏫 AI Agent Framework Crash Course

Deep-dive tutorials on the major agent frameworks.

Google ADK Crash Course

• Starter agent; model‑agnostic (OpenAI, Claude)
• Structured outputs (Pydantic)
• Tools: built‑in, function, third‑party, MCP tools
• Memory; callbacks; Plugins
• Simple multi‑agent; Multi‑agent patterns

OpenAI Agents SDK Crash Course

• Starter agent; function calling; structured outputs
• Tools: built‑in, function, third‑party integrations
• Memory; callbacks; evaluation
• Multi‑agent patterns; agent handoffs
• Swarm orchestration; routing logic

Created and maintained by Shubham Saboo with contributions from the amazing community members.

🌟 Don't miss future drops -star the repo to get notified when new templates ship.

Apache-2.0. See LICENSE. Fork it, ship it, sell it.