[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"similar-Arindam200--awesome-ai-apps":3,"tool-Arindam200--awesome-ai-apps":61},[4,18,26,36,44,53],{"id":5,"name":6,"github_repo":7,"description_zh":8,"stars":9,"difficulty_score":10,"last_commit_at":11,"category_tags":12,"status":17},4358,"openclaw","openclaw\u002Fopenclaw","OpenClaw 是一款专为个人打造的本地化 AI 助手，旨在让你在自己的设备上拥有完全可控的智能伙伴。它打破了传统 AI 助手局限于特定网页或应用的束缚，能够直接接入你日常使用的各类通讯渠道，包括微信、WhatsApp、Telegram、Discord、iMessage 等数十种平台。无论你在哪个聊天软件中发送消息，OpenClaw 都能即时响应，甚至支持在 macOS、iOS 和 Android 设备上进行语音交互，并提供实时的画布渲染功能供你操控。\n\n这款工具主要解决了用户对数据隐私、响应速度以及“始终在线”体验的需求。通过将 AI 部署在本地，用户无需依赖云端服务即可享受快速、私密的智能辅助，真正实现了“你的数据，你做主”。其独特的技术亮点在于强大的网关架构，将控制平面与核心助手分离，确保跨平台通信的流畅性与扩展性。\n\nOpenClaw 非常适合希望构建个性化工作流的技术爱好者、开发者，以及注重隐私保护且不愿被单一生态绑定的普通用户。只要具备基础的终端操作能力（支持 macOS、Linux 及 Windows WSL2），即可通过简单的命令行引导完成部署。如果你渴望拥有一个懂你",349277,3,"2026-04-06T06:32:30",[13,14,15,16],"Agent","开发框架","图像","数据工具","ready",{"id":19,"name":20,"github_repo":21,"description_zh":22,"stars":23,"difficulty_score":10,"last_commit_at":24,"category_tags":25,"status":17},3808,"stable-diffusion-webui","AUTOMATIC1111\u002Fstable-diffusion-webui","stable-diffusion-webui 是一个基于 Gradio 构建的网页版操作界面，旨在让用户能够轻松地在本地运行和使用强大的 Stable Diffusion 图像生成模型。它解决了原始模型依赖命令行、操作门槛高且功能分散的痛点，将复杂的 AI 绘图流程整合进一个直观易用的图形化平台。\n\n无论是希望快速上手的普通创作者、需要精细控制画面细节的设计师，还是想要深入探索模型潜力的开发者与研究人员，都能从中获益。其核心亮点在于极高的功能丰富度：不仅支持文生图、图生图、局部重绘（Inpainting）和外绘（Outpainting）等基础模式，还独创了注意力机制调整、提示词矩阵、负向提示词以及“高清修复”等高级功能。此外，它内置了 GFPGAN 和 CodeFormer 等人脸修复工具，支持多种神经网络放大算法，并允许用户通过插件系统无限扩展能力。即使是显存有限的设备，stable-diffusion-webui 也提供了相应的优化选项，让高质量的 AI 艺术创作变得触手可及。",162132,"2026-04-05T11:01:52",[14,15,13],{"id":27,"name":28,"github_repo":29,"description_zh":30,"stars":31,"difficulty_score":32,"last_commit_at":33,"category_tags":34,"status":17},1381,"everything-claude-code","affaan-m\u002Feverything-claude-code","everything-claude-code 是一套专为 AI 编程助手（如 Claude Code、Codex、Cursor 等）打造的高性能优化系统。它不仅仅是一组配置文件，而是一个经过长期实战打磨的完整框架，旨在解决 AI 代理在实际开发中面临的效率低下、记忆丢失、安全隐患及缺乏持续学习能力等核心痛点。\n\n通过引入技能模块化、直觉增强、记忆持久化机制以及内置的安全扫描功能，everything-claude-code 能显著提升 AI 在复杂任务中的表现，帮助开发者构建更稳定、更智能的生产级 AI 代理。其独特的“研究优先”开发理念和针对 Token 消耗的优化策略，使得模型响应更快、成本更低，同时有效防御潜在的攻击向量。\n\n这套工具特别适合软件开发者、AI 研究人员以及希望深度定制 AI 工作流的技术团队使用。无论您是在构建大型代码库，还是需要 AI 协助进行安全审计与自动化测试，everything-claude-code 都能提供强大的底层支持。作为一个曾荣获 Anthropic 黑客大奖的开源项目，它融合了多语言支持与丰富的实战钩子（hooks），让 AI 真正成长为懂上",157379,2,"2026-04-15T23:32:42",[14,13,35],"语言模型",{"id":37,"name":38,"github_repo":39,"description_zh":40,"stars":41,"difficulty_score":32,"last_commit_at":42,"category_tags":43,"status":17},2271,"ComfyUI","Comfy-Org\u002FComfyUI","ComfyUI 是一款功能强大且高度模块化的视觉 AI 引擎，专为设计和执行复杂的 Stable Diffusion 图像生成流程而打造。它摒弃了传统的代码编写模式，采用直观的节点式流程图界面，让用户通过连接不同的功能模块即可构建个性化的生成管线。\n\n这一设计巧妙解决了高级 AI 绘图工作流配置复杂、灵活性不足的痛点。用户无需具备编程背景，也能自由组合模型、调整参数并实时预览效果，轻松实现从基础文生图到多步骤高清修复等各类复杂任务。ComfyUI 拥有极佳的兼容性，不仅支持 Windows、macOS 和 Linux 全平台，还广泛适配 NVIDIA、AMD、Intel 及苹果 Silicon 等多种硬件架构，并率先支持 SDXL、Flux、SD3 等前沿模型。\n\n无论是希望深入探索算法潜力的研究人员和开发者，还是追求极致创作自由度的设计师与资深 AI 绘画爱好者，ComfyUI 都能提供强大的支持。其独特的模块化架构允许社区不断扩展新功能，使其成为当前最灵活、生态最丰富的开源扩散模型工具之一，帮助用户将创意高效转化为现实。",108322,"2026-04-10T11:39:34",[14,15,13],{"id":45,"name":46,"github_repo":47,"description_zh":48,"stars":49,"difficulty_score":32,"last_commit_at":50,"category_tags":51,"status":17},6121,"gemini-cli","google-gemini\u002Fgemini-cli","gemini-cli 是一款由谷歌推出的开源 AI 命令行工具，它将强大的 Gemini 大模型能力直接集成到用户的终端环境中。对于习惯在命令行工作的开发者而言，它提供了一条从输入提示词到获取模型响应的最短路径，无需切换窗口即可享受智能辅助。\n\n这款工具主要解决了开发过程中频繁上下文切换的痛点，让用户能在熟悉的终端界面内直接完成代码理解、生成、调试以及自动化运维任务。无论是查询大型代码库、根据草图生成应用，还是执行复杂的 Git 操作，gemini-cli 都能通过自然语言指令高效处理。\n\n它特别适合广大软件工程师、DevOps 人员及技术研究人员使用。其核心亮点包括支持高达 100 万 token 的超长上下文窗口，具备出色的逻辑推理能力；内置 Google 搜索、文件操作及 Shell 命令执行等实用工具；更独特的是，它支持 MCP（模型上下文协议），允许用户灵活扩展自定义集成，连接如图像生成等外部能力。此外，个人谷歌账号即可享受免费的额度支持，且项目基于 Apache 2.0 协议完全开源，是提升终端工作效率的理想助手。",100752,"2026-04-10T01:20:03",[52,13,15,14],"插件",{"id":54,"name":55,"github_repo":56,"description_zh":57,"stars":58,"difficulty_score":32,"last_commit_at":59,"category_tags":60,"status":17},4721,"markitdown","microsoft\u002Fmarkitdown","MarkItDown 是一款由微软 AutoGen 团队打造的轻量级 Python 工具，专为将各类文件高效转换为 Markdown 格式而设计。它支持 PDF、Word、Excel、PPT、图片（含 OCR）、音频（含语音转录）、HTML 乃至 YouTube 链接等多种格式的解析，能够精准提取文档中的标题、列表、表格和链接等关键结构信息。\n\n在人工智能应用日益普及的今天，大语言模型（LLM）虽擅长处理文本，却难以直接读取复杂的二进制办公文档。MarkItDown 恰好解决了这一痛点，它将非结构化或半结构化的文件转化为模型“原生理解”且 Token 效率极高的 Markdown 格式，成为连接本地文件与 AI 分析 pipeline 的理想桥梁。此外，它还提供了 MCP（模型上下文协议）服务器，可无缝集成到 Claude Desktop 等 LLM 应用中。\n\n这款工具特别适合开发者、数据科学家及 AI 研究人员使用，尤其是那些需要构建文档检索增强生成（RAG）系统、进行批量文本分析或希望让 AI 助手直接“阅读”本地文件的用户。虽然生成的内容也具备一定可读性，但其核心优势在于为机器",93400,"2026-04-06T19:52:38",[52,14],{"id":62,"github_repo":63,"name":64,"description_en":65,"description_zh":66,"ai_summary_zh":66,"readme_en":67,"readme_zh":68,"quickstart_zh":69,"use_case_zh":70,"hero_image_url":71,"owner_login":72,"owner_name":73,"owner_avatar_url":74,"owner_bio":75,"owner_company":76,"owner_location":77,"owner_email":78,"owner_twitter":79,"owner_website":80,"owner_url":81,"languages":82,"stars":113,"forks":114,"last_commit_at":115,"license":116,"difficulty_score":32,"env_os":117,"env_gpu":117,"env_ram":117,"env_deps":118,"category_tags":121,"github_topics":122,"view_count":32,"oss_zip_url":78,"oss_zip_packed_at":78,"status":17,"created_at":128,"updated_at":129,"faqs":130,"releases":131},8054,"Arindam200\u002Fawesome-ai-apps","awesome-ai-apps","A collection of projects showcasing RAG, agents, workflows, and other AI use cases","awesome-ai-apps 是一个专为开发者打造的实用资源库，汇集了 80 多个基于大语言模型（LLM）构建应用的项目实例、教程与代码食谱。它旨在解决开发者在从理论走向实践过程中遇到的“起步难”问题，提供了涵盖文本智能体、语音助手、RAG（检索增强生成）应用以及 MCP 支持工具等多样化的落地方案。\n\n无论是刚接触 AI 开发的新手，还是希望快速验证想法的资深工程师，都能在这里找到适合的参考项目。资源库内容结构清晰，从基础的入门智能体到具备记忆功能的高级代理，再到复杂的 RAG 系统，循序渐进地展示了如何利用主流 AI 框架搭建强大应用。其独特亮点在于不仅提供代码，更强调“实战性”，通过具体的场景化案例帮助开发者理解智能体的工作流设计与集成技巧。如果你正在寻找灵感，或需要一套完整的代码模板来加速你的 AI 产品开发进程，awesome-ai-apps 将是一份极具价值的指南。","![Banner](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FArindam200_awesome-ai-apps_readme_09f7c23d7766.png)\n\n\u003Cdiv align=\"center\">\n\n# Awesome AI Apps [![Awesome](https:\u002F\u002Fawesome.re\u002Fbadge.svg)](https:\u002F\u002Fawesome.re)\n\n\u003Ca href=\"https:\u002F\u002Ftrendshift.io\u002Frepositories\u002F14662\" target=\"_blank\">\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FArindam200_awesome-ai-apps_readme_bbada6ddd5d3.png\" alt=\"Arindam200%2Fawesome-ai-apps | Trendshift\" style=\"width: 250px; height: 55px;\" width=\"250\" height=\"55\"\u002F>\u003C\u002Fa>\n\n\u003C\u002Fdiv>\n\nThis repository is a comprehensive collection of **80+ practical examples, tutorials, and recipes** for building powerful LLM-powered applications — including text agents, voice assistants, RAG apps, and MCP-backed tools. These projects serve as a guide for developers working with various AI frameworks and stacks.\n\n## 📋 Table of Contents\n\n- [🎓 Courses](#-courses)\n- [🚀 Featured AI Apps](#-featured-ai-apps)\n  - [🧩 Starter Agents](#-starter-agents)\n  - [🪶 Simple Agents](#-simple-agents)\n  - [🎙️ Voice Agents](#-voice-agents)\n  - [🗂️ MCP Agents](#️-mcp-agents)\n  - [🧠 Memory Agents](#-memory-agents)\n  - [📚 RAG Applications](#-rag-applications)\n  - [🔬 Advanced Agents](#-advanced-agents)\n- [📺 Tutorials & Videos](#-tutorials--videos)\n- [🚀 Getting Started](#getting-started)\n- [🤝 Contributing](#-contributing)\n\n---\n\n\u003Cdiv align=\"center\">\n\n## 💎 Sponsors\n\n\u003Cp align=\"center\">\n  A huge thank you to our sponsors for their generous support!\n\u003C\u002Fp>\n\n\u003Ctable align=\"center\" cellpadding=\"10\" style=\"width:100%; border-collapse:collapse;\">\n  \u003Ctr align=\"center\">\n    \u003Ctd width=\"300\" valign=\"middle\" align=\"center\">\n      \u003Ca href=\"https:\u002F\u002Fdub.sh\u002Fbrightdata\" target=\"_blank\" title=\"Visit Bright Data\">\n        \u003Cimg src=\"https:\u002F\u002Fmintlify.s3.us-west-1.amazonaws.com\u002Fbrightdata\u002Flogo\u002Flight.svg\" height=\"35\" style=\"max-width:180px;\" alt=\"Bright Data - Web Data Platform\">\n      \u003C\u002Fa>\n      \u003Cbr>\n      \u003Csub>\n        \u003Cspan style=\"white-space:nowrap;\">Web Data Platform\u003C\u002Fspan>\n        \u003Cbr>\n        \u003Ca href=\"https:\u002F\u002Fdub.sh\u002Fbrightdata\" target=\"_blank\">\n          \u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FVisit%20Site-blue?style=flat-square\" alt=\"Visit Bright Data website\">\n        \u003C\u002Fa>\n      \u003C\u002Fsub>\n    \u003C\u002Ftd>\n    \u003Ctd width=\"300\" valign=\"middle\" align=\"center\">\n      \u003Ca href=\"https:\u002F\u002Fdub.sh\u002Fnebius\" target=\"_blank\" title=\"Visit Nebius Token Factory\">\n        \u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FArindam200_awesome-ai-apps_readme_1cf213308fe6.png\" height=\"36\" style=\"max-width:180px;\" alt=\"Nebius Token Factory\">\n      \u003C\u002Fa>\n      \u003Cbr>\n      \u003Csub>\n        \u003Cspan style=\"white-space:nowrap;\">AI Inference Provider\u003C\u002Fspan>\n        \u003Cbr>\n        \u003Ca href=\"https:\u002F\u002Fdub.sh\u002Fnebius\" target=\"_blank\">\n          \u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FVisit%20Site-blue?style=flat-square\" alt=\"Visit Nebius Token Factory\">\n        \u003C\u002Fa>\n      \u003C\u002Fsub>\n    \u003C\u002Ftd>\n    \u003Ctd width=\"300\" valign=\"middle\" align=\"center\">\n      \u003Ca href=\"https:\u002F\u002Fdub.sh\u002Fscrapegraphai\" target=\"_blank\" title=\"Visit ScrapeGraphAI on GitHub\">\n        \u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FArindam200_awesome-ai-apps_readme_904b7cdfd793.png\" height=\"44\" style=\"max-width:180px;\" alt=\"ScrapeGraphAI - Web Scraping Library\">\n      \u003C\u002Fa>\n      \u003Cbr>\n      \u003Csub>\n        \u003Cspan style=\"white-space:nowrap;\">AI Web Scraping framework\u003C\u002Fspan>\n        \u003Cbr>\n        \u003Ca href=\"https:\u002F\u002Fdub.sh\u002Fscrapegraphai\" target=\"_blank\">\n          \u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FVisit%20Site-blue?style=flat-square\" alt=\"View ScrapeGraphAI on GitHub\">\n        \u003C\u002Fa>\n      \u003C\u002Fsub>\n    \u003C\u002Ftd>\n  \u003C\u002Ftr>\n  \u003Ctr align=\"center\">\n    \u003Ctd width=\"300\" valign=\"middle\" align=\"center\">\n      \u003Ca href=\"https:\u002F\u002Fdub.sh\u002Fmemorilabs\" target=\"_blank\" title=\"Visit Memorilabs\">\n        \u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FArindam200_awesome-ai-apps_readme_9ee3ad72e9b7.png\" height=\"36\" style=\"max-width:180px;\" alt=\"Memori - SQL Native Memory for AI\">\n      \u003C\u002Fa>\n      \u003Cbr>\n      \u003Csub>\n        \u003Cspan style=\"white-space:nowrap;\">SQL Native Memory for AI\u003C\u002Fspan>\n        \u003Cbr>\n        \u003Ca href=\"https:\u002F\u002Fdub.sh\u002Fmemorilabs\" target=\"_blank\">\n          \u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FVisit%20Site-blue?style=flat-square\" alt=\"Visit Memorilabs website\">\n        \u003C\u002Fa>\n      \u003C\u002Fsub>\n    \u003C\u002Ftd>\n    \u003Ctd width=\"300\" valign=\"middle\" align=\"center\">\n      \u003Ca href=\"https:\u002F\u002Fdub.sh\u002Fcopilotkit\" target=\"_blank\" title=\"Visit CopilotKit\">\n        \u003Cimg src=\"assets\u002Fcopilot-kit-logo.svg\" height=\"36\" style=\"max-width:180px;\" alt=\"CopilotKit - Agentic Application Platform\">\n      \u003C\u002Fa>\n      \u003Cbr>\n      \u003Csub>\n        \u003Cspan style=\"white-space:nowrap;\">Agentic Application Platform\u003C\u002Fspan>\n        \u003Cbr>\n        \u003Ca href=\"https:\u002F\u002Fdub.sh\u002Fcopilotkit\" target=\"_blank\">\n          \u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FVisit%20Site-blue?style=flat-square\" alt=\"Visit CopilotKit website\">\n        \u003C\u002Fa>\n      \u003C\u002Fsub>\n    \u003C\u002Ftd>\n    \u003Ctd width=\"300\" valign=\"middle\" align=\"center\">\n      \u003Ca href=\"https:\u002F\u002Fdub.sh\u002Fscalekitt\" target=\"_blank\" title=\"Visit ScaleKit\">\n        \u003Cimg src=\"assets\u002Fscalekit.svg\" height=\"36\" style=\"max-width:180px;\" alt=\"ScaleKit - Auth Stack for AI\">\n      \u003C\u002Fa>\n      \u003Cbr>\n      \u003Csub>\n        \u003Cspan style=\"white-space:nowrap;\">Auth Stack for AI\u003C\u002Fspan>\n        \u003Cbr>\n        \u003Ca href=\"https:\u002F\u002Fdub.sh\u002Fscalekitt\" target=\"_blank\">\n          \u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FVisit%20Site-blue?style=flat-square\" alt=\"Visit ScaleKit website\">\n        \u003C\u002Fa>\n      \u003C\u002Fsub>\n    \u003C\u002Ftd>\n  \u003C\u002Ftr>\n  \u003Ctr align=\"center\">\n    \u003Ctd width=\"200\" valign=\"middle\" align=\"center\">\n      \u003Ca href=\"https:\u002F\u002Fokahu.ai\" target=\"_blank\" title=\"Visit Okahu\">\n        \u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FArindam200_awesome-ai-apps_readme_6825a905f76f.png\" height=\"36\" style=\"max-width:180px;\" alt=\"Okahu - AI Platform\">\n      \u003C\u002Fa>\n      \u003Cbr>\n      \u003Csub>\n        \u003Cspan style=\"white-space:nowrap;\">AI Observability Platform\u003C\u002Fspan>\n        \u003Cbr>\n        \u003Ca href=\"https:\u002F\u002Fokahu.ai\" target=\"_blank\">\n          \u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FVisit%20Site-blue?style=flat-square\" alt=\"Visit Okahu website\">\n        \u003C\u002Fa>\n      \u003C\u002Fsub>\n    \u003C\u002Ftd>\n    \u003Ctd width=\"200\" valign=\"middle\" align=\"center\">\n      \u003Ca href=\"https:\u002F\u002Fdub.sh\u002FserpApi\" target=\"_blank\" title=\"Visit SerpApi\">\n        \u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FArindam200_awesome-ai-apps_readme_1205205dbbaf.png\" height=\"36\" style=\"max-width:180px;\" alt=\"SerpApi - Google Search API\">\n      \u003C\u002Fa>\n      \u003Cbr>\n      \u003Csub>\n        \u003Cspan style=\"white-space:nowrap;\">Google Search API\u003C\u002Fspan>\n        \u003Cbr>\n        \u003Ca href=\"https:\u002F\u002Fdub.sh\u002FserpApi\" target=\"_blank\">\n          \u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FVisit%20Site-blue?style=flat-square\" alt=\"Visit SerpApi website\">\n        \u003C\u002Fa>\n      \u003C\u002Fsub>\n    \u003C\u002Ftd>\n    \u003Ctd width=\"200\" valign=\"middle\" align=\"center\">\n      \u003Ca href=\"https:\u002F\u002Fdub.sh\u002Fagentfield\" target=\"_blank\" title=\"Visit AgentField\">\n        \u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FArindam200_awesome-ai-apps_readme_2697f66b2124.png\" height=\"40\" style=\"max-width:180px;\" alt=\"AgentField - Kubernetes for AI Agents\">\n      \u003C\u002Fa>\n      \u003Cbr>\n      \u003Csub>\n        \u003Cspan style=\"white-space:nowrap;\">Kubernetes for AI Agents\u003C\u002Fspan>\n        \u003Cbr>\n        \u003Ca href=\"https:\u002F\u002Fdub.sh\u002Fagentfield\" target=\"_blank\">\n          \u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FVisit%20Site-blue?style=flat-square\" alt=\"Visit AgentField website\">\n        \u003C\u002Fa>\n      \u003C\u002Fsub>\n    \u003C\u002Ftd>\n  \u003C\u002Ftr>\n\n   \n\n\u003C\u002Ftable>\n\n### 💎 Become a Sponsor\n\n\u003Cp align=\"center\">\nInterested in sponsoring this project? Feel free to reach out!\n\u003Cbr\u002F>\n\u003Ca href=\"https:\u002F\u002Fdub.sh\u002Farindam-linkedin\" target=\"_blank\">\n    \u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FLinkedIn-0077B5?style=for-the-badge&logo=linkedin&logoColor=white\" alt=\"LinkedIn\">\n\u003C\u002Fa>\n\u003Ca href=\"mailto:arindammajumder2020@gmail.com\">\n    \u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FEmail-D14836?style=for-the-badge&logo=gmail&logoColor=white\" alt=\"Email\">\n\u003C\u002Fa>\n\u003C\u002Fp>\n\n\u003C\u002Fdiv>\n\n---\n\n## 🎓 Courses\n\n### AWS Strands Course for Beginners\n\n**Comprehensive hands-on course on building AI agents with AWS Strands SDK:**\n\n- [**AWS Strands Course**](course\u002Faws_strands) - Complete 8-lesson course covering agent fundamentals to production patterns\n  - **Foundation**: Basic agents, session management, structured output\n  - **Integration**: MCP agents, human-in-the-loop patterns\n  - **Multi-Agent**: Orchestrator agents, swarm intelligence, graph workflows\n  - **Production**: Observability, safety guardrails, and best practices\n\n## 🚀 Featured AI Apps\n\n### 🧩 Starter Agents\n\n**Quick-start agents for learning and extending different AI frameworks.** _13 projects_\n\n- [Agno HackerNews Analysis](starter_ai_agents\u002Fagno_starter) - Agno-based agent for trend analysis on HackerNews\n- [OpenAI SDK Starter](starter_ai_agents\u002Fopenai_agents_sdk) - OpenAI Agents SDK with email helper & haiku writer examples\n- [LlamaIndex Task Manager](starter_ai_agents\u002Fllamaindex_starter) - LlamaIndex-powered task assistant\n- [CrewAI Research Crew](starter_ai_agents\u002Fcrewai_starter) - Multi-agent research team example\n- [PydanticAI Weather Bot](starter_ai_agents\u002Fpydantic_starter) - Real-time weather information agent\n- [LangChain-LangGraph Starter](starter_ai_agents\u002Flangchain_langgraph_starter) - LangChain + LangGraph workflow starter\n- [AWS Strands Agent Starter](starter_ai_agents\u002Faws_strands_starter) - Weather report agent using AWS Strands SDK\n- [Camel AI Starter](starter_ai_agents\u002Fcamel_ai_starter) - Performance benchmarking tool comparing various AI models\n- [DSPy Starter](starter_ai_agents\u002Fdspy_starter) - DSPy framework for building and optimizing AI systems\n- [Google ADK Starter](starter_ai_agents\u002Fgoogle_adk_starter) - Google Agent Development Kit starter template\n- [cagent Starter](starter_ai_agents\u002Fcagent_starter) - Open-source customizable multi-agent runtime by Docker\n- [Sayna Voice Agent](starter_ai_agents\u002Fsayna_starter) - Real-time voice infrastructure with multi-provider STT\u002FTTS (Deepgram, ElevenLabs, Azure, Google) and WebSocket streaming\n- [KAOS Starter](starter_ai_agents\u002Fkaos_starter) - Kubernetes-native multi-agent system with MCP tools and in-cluster LLM\n\n### 🪶 Simple Agents\n\n**Straightforward, practical use-cases for everyday AI applications.** _14 projects_\n\n- [Agno AI Examples](simple_ai_agents\u002Fagno_ai_examples) - Simple to multi-agent examples with web search & knowledge base\n- [Finance Agent](simple_ai_agents\u002Ffinance_agent) - Real-time stock & market data tracking agent\n- [Human-in-the-Loop Agent](simple_ai_agents\u002Fhuman_in_the_loop_agent) - HITL actions for safe AI task execution\n- [Newsletter Generator](simple_ai_agents\u002Fnewsletter_agent) - AI-powered newsletter builder with Firecrawl integration\n- [Reasoning Agent](simple_ai_agents\u002Freasoning_agent) - Step-by-step financial reasoning demonstration\n- [Agno UI Example](simple_ai_agents\u002Fagno_ui_agent) - Interactive UI for web & finance agents\n- [Mastra Weather Bot](simple_ai_agents\u002Fmastra_ai_weather_agent) - Weather updates using Mastra AI framework\n- [Calendar Assistant](simple_ai_agents\u002Fcal_scheduling_agent) - Calendar scheduling integration with Cal.com\n- [Smart Scheduler Assistant](simple_ai_agents\u002Femail_to_calendar_scheduler) - AI-powered Gmail reader and Google Calendar manager\n- [Web Automation Agent](simple_ai_agents\u002Fbrowser_agent) - Browser automation agent using Nebius & browser-use\n- [Nebius Chat](simple_ai_agents\u002Fnebius_chat) - Chat interface for Nebius Token Factory\n- [RouteLLM Chat](simple_ai_agents\u002Fllm_router) - Intelligent model routing with RouteLLM (GPT-4o-mini vs Nebius Llama) for cost optimization\n- [Talk to Your DB](simple_ai_agents\u002Ftalk_to_db) - Natural language database queries with GibsonAI & LangChain\n- [Agent Discovery Agent](simple_ai_agents\u002Fagent_discovery_agent) - Find and compare AI agents across NANDA, MCP, Virtuals, A2A, and ERC-8004 registries\n\n### 🎙️ Voice Agents\n\n**Real-time voice assistants and streaming speech pipelines.** _2 projects_\n\n- [LiveKit + Gemini Realtime](voice_agents\u002Flivekit_gemini_agents) - LiveKit Agents with Google Gemini Live (`gemini` multimodal realtime) for low-latency voice conversations in a LiveKit room\n- [Pipecat + Sarvam](voice_agents\u002Fpipecat_agent) - Pipecat voice pipeline with Sarvam STT\u002FTTS and OpenAI for chat; WebRTC (browser) or Daily transport via the Pipecat runner\n\n### 🗂️ MCP Agents\n\n**Examples using Model Context Protocol for external tool integration.** _13 projects_\n\n- [Doc-MCP](mcp_ai_agents\u002Fdoc_mcp) - Semantic RAG documentation & Q&A system\n- [LangGraph MCP Agent](mcp_ai_agents\u002Flangchain_langgraph_mcp_agent) - LangChain ReAct agent with Couchbase integration\n- [GitHub MCP Agent](mcp_ai_agents\u002Fgithub_mcp_agent) - Repository insights and analysis via MCP\n- [MCP Starter](mcp_ai_agents\u002Fmcp_starter) - GitHub repository analyzer starter template\n- [Talk to your Docs](mcp_ai_agents\u002Fdocs_qna_agent) - Documentation Q&A agent with MCP\n- [Database MCP Agent](mcp_ai_agents\u002Fdatabase_mcp_agent) - Conversational AI agent for managing GibsonAI database projects and schemas\n- [Hotel Finder Agent](mcp_ai_agents\u002Fhotel_finder_agent) - Hotel search and booking using MCP integration\n- [Custom MCP Server](mcp_ai_agents\u002Fcustom_mcp_server) - Custom MCP server implementation example\n- [Couchbase MCP Server](mcp_ai_agents\u002Fcouchbase_mcp_server) - Couchbase database integration with MCP protocol\n- [ScaleKit Exa MCP Security](mcp_ai_agents\u002Fscalekit-exa-mcp-security) - Security-focused MCP integration with Exa search\n- [Docker E2B MCP Agent](mcp_ai_agents\u002Fe2b_docker_mcp_agent) - Secure AI agent for running agents in sandboxed Docker environments via MCP Gateway\n- [Taskade MCP Agent](mcp_ai_agents\u002Ftaskade_mcp_agent) - AI-powered workspace agent for managing projects, tasks, and workflows via Taskade MCP\n- [Telemetry MCP Okahu](mcp_ai_agents\u002Ftelemetry-mcp-okahu) - Self-healing Text-to-SQL demo using Okahu Cloud traces via hosted MCP\n\n### 🧠 Memory Agents\n\n**Agents with advanced memory capabilities for context retention and personalization.** _12 projects_\n\n- [Agno Memory Agent](memory_agents\u002Fagno_memory_agent) - Agno-based agent with persistent memory capabilities\n- [arXiv Researcher Agent with Memori](memory_agents\u002Farxiv_researcher_agent_with_memori) - Research assistant using OpenAI Agents and GibsonAI Memori\n- [AWS Strands Agent with Memori](memory_agents\u002Faws_strands_agent_with_memori) - AWS Strands agent enhanced with Memori memory system\n- [Blog Writing Agent](memory_agents\u002Fblog_writing_agent) - Personalized blog writing agent with memory for style consistency\n- [Social Media Agent](memory_agents\u002Fsocial_media_agent) - Social media automation agent with memory for brand voice\n- [Job Search Agent](memory_agents\u002Fjob_search_agent) - Job search agent with memory for preference tracking\n- [Brand Reputation Monitor](memory_agents\u002Fbrand_reputation_monitor) - AI-powered brand reputation monitoring with news analysis and sentiment tracking\n- [Product Launch Agent](memory_agents\u002Fproduct_launch_agent) - Competitive intelligence tool for analyzing competitor product launches\n- [AI Consultant Agent](memory_agents\u002Fai_consultant_agent\u002F) - AI-powered consulting agent using **Memori v3** as long-term memory fabric and **ExaAI** for research\n- [Customer Support Voice Agent](memory_agents\u002Fcustomer_support_voice_agent) - Voice-enabled customer support assistant with Memori v3 and Firecrawl for knowledge base management\n- [YouTube Trend Agent](memory_agents\u002Fyoutube_trend_agent) - YouTube channel analysis agent with Memori, Agno, and Exa for trend analysis and video ideas\n- [Study Coach Agent](memory_agents\u002Fstudy_coach_agent) - AI-powered study coach with Memori v3 and LangGraph for multi-step verification of understanding\n\n### 📚 RAG Applications\n\n**Retrieve-augmented generation examples for document understanding and knowledge bases.** _12 projects_\n\n- [Agentic RAG](rag_apps\u002Fagentic_rag) - Agentic RAG implementation with Agno & GPT-5\n- [Agentic RAG with Web Search](rag_apps\u002Fagentic_rag_with_web_search) - Advanced RAG with CrewAI, Qdrant, and Exa for hybrid search capabilities\n- [Resume Optimizer](rag_apps\u002Fresume_optimizer) - AI-powered resume optimization and enhancement tool\n- [LlamaIndex RAG Starter](rag_apps\u002FllamaIndex_starter) - LlamaIndex + Nebius RAG starter template\n- [PDF RAG Analyzer](rag_apps\u002Fpdf_rag_analyser) - Multi-PDF chat and analysis system\n- [Qwen3 RAG Chat](rag_apps\u002Fqwen3_rag) - PDF chatbot interface built with Streamlit\n- [Chat with Code](rag_apps\u002Fchat_with_code) - Conversational code explorer and documentation assistant\n- [Gemma3 OCR](rag_apps\u002Fgemma_ocr\u002F) - OCR-based document and image processor using Gemma3 model\n- [Nvidia Nemotron OCR](rag_apps\u002Fnvidia_ocr\u002F) - OCR-based document and image parsing using Nvidia Nemotron-Nano-V2-12b\n- [Contextual AI RAG](rag_apps\u002Fcontextual_ai_rag) - Enterprise-level RAG with managed datastores and quality evaluation\n- [Simple RAG](rag_apps\u002Fsimple_rag) - Basic RAG implementation with Nebius for quick starts\n- [WFGY 16 Problem Map LLM Debugger](rag_apps\u002Fwfgy_llm_debugger) - 16-mode map based debugger for LLM and RAG bugs\n\n### 🔬 Advanced Agents\n\n**Complex multi-agent pipelines for production-ready end-to-end workflows.** _18 projects_\n\n- [Nebius AutoResearch](advance_ai_agents\u002Fnebius-autoresearch-autoresearch-mar30) - NYC taxi analytics pipeline optimizer; iterative code search with Nebius Token Factory (real-time or batch inference)\n- [AgentField Financial Research Agent](advance_ai_agents\u002Fagentfield_finance_research_agent) - Financial Research Agent with AgentField\n- [Due Diligence Agent](advance_ai_agents\u002Fdue_diligence_agent) - Multi-agent company due diligence pipeline with AG2 and TinyFish deep web scraping\n- [Deep Researcher](advance_ai_agents\u002Fdeep_researcher_agent) - Multi-stage research agent with Agno & ScrapeGraph AI\n- [Candilyzer](advance_ai_agents\u002Fcandidate_analyser) - Candidate analysis tool for GitHub\u002FLinkedIn profiles\n- [Job Finder](advance_ai_agents\u002Fjob_finder_agent) - LinkedIn job search automation with Bright Data integration\n- [AI Trend Analyzer](advance_ai_agents\u002Ftrend_analyzer_agent) - AI trend mining and analysis with Google ADK\n- [Conference Talk Generator](advance_ai_agents\u002Fconference_talk_abstract_generator) - Automated talk abstract generation with Google ADK & Couchbase\n- [Finance Service Agent](advance_ai_agents\u002Ffinance_service_agent) - FastAPI server for stock data and predictions with Agno\n- [Price Monitoring Agent](advance_ai_agents\u002Fprice_monitoring_agent) - Price monitoring and alerting agent powered by CrewAI, Twilio & Nebius\n- [Startup Idea Validator Agent](advance_ai_agents\u002Fstartup_idea_validator_agent) - Agentic workflow to validate and analyze startup ideas\n- [Meeting Assistant Agent](advance_ai_agents\u002Fmeeting_assistant_agent) - Automated meeting notes and task creation from conversations\n- [AI Hedgefund](advance_ai_agents\u002Fai-hedgefund) - Agentic workflow for comprehensive financial analysis\n- [Smart GTM Agent](advance_ai_agents\u002Fsmart_gtm_agent) - Go-to-market strategy and competitive analysis agent\n- [Conference Agnostic CFP Generator](advance_ai_agents\u002Fconference_agnositc_cfp_generator) - Automated conference proposal generation system\n- [Car Finder Agent](advance_ai_agents\u002Fcar_finder_agent) - AI-powered used car recommendation system with CrewAI and MongoDB\n- [Content Team Agent](advance_ai_agents\u002Fcontent_team_agent) - SEO content optimization workflow with Agno & SerpAPI for Google AI Search ranking\n- [Temporal Agents](advance_ai_agents\u002Ftemporal_agents\u002F) - Examples of Temporal based AI Agents\n\n## 📺 Tutorials & Videos\n\n### 🎓 Course Playlists\n\n- [**AWS Strands Course**](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PLMZM1DAlf0Lrc43ZtUXAwYu9DhnqxzRKZ) - Complete 8-lesson course on building AI agents with AWS Strands SDK\n\n### 🔧 Framework Tutorials\n\n- [**Build with MCP**](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PLMZM1DAlf0Lolxax4L2HS54Me8gn1gkz4) - Model Context Protocol tutorials and examples\n- [**Build AI Agents**](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PLMZM1DAlf0LqixhAG9BDk4O_FjqnaogK8) - General AI agent development tutorials\n- [**AI Agents, MCP and more...**](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PL2ambAOfYA6-LDz0KpVKu9vJKAqhv0KKI) - Mixed tutorials and project demos\n\n---\n\n\u003Cdiv align=\"center\">\n\n## 📥 Stay Updated with Daily AI Insight!\n\nGet easy-to-follow weekly tutorials and deep dives on AI, LLMs, and agent frameworks. Perfect for developers who want to learn, build, and stay ahead with new tech. Subscribe our Newsletter!\n\n[![Subscribe to our Newsletter](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FArindam200_awesome-ai-apps_readme_b94c361c9a8e.png)](https:\u002F\u002Fmranand.substack.com\u002Fsubscribe)\n\n\u003C\u002Fdiv>\n\n---\n\n## Getting Started\n\n### Prerequisites\n\n- **Python 3.10+** (Python 3.11+ recommended for newer projects)\n- **Git** for cloning the repository\n- **Package Manager**: `pip` or `uv` (recommended for faster installs)\n- **API Keys**: Most projects require API keys (see individual project READMEs)\n\n### Quick Start\n\n1. **Clone the repository**\n\n   ```bash\n   git clone https:\u002F\u002Fgithub.com\u002FArindam200\u002Fawesome-ai-apps.git\n   cd awesome-ai-apps\n   ```\n\n2. **Choose a project** and navigate to its directory\n\n   ```bash\n   cd starter_ai_agents\u002Fagno_starter  # Example: Start with Agno starter\n   ```\n\n3. **Set up environment variables**\n\n   ```bash\n   cp .env.example .env  # Copy example environment file\n   # Edit .env with your API keys\n   ```\n\n4. **Install dependencies**\n\n   ```bash\n   # Using pip\n   pip install -r requirements.txt\n\n   # OR using uv (recommended - faster)\n   uv sync\n   # or\n   uv pip install -e .\n   ```\n\n5. **Run the project**\n\n   ```bash\n   python main.py\n   # or for Streamlit apps\n   streamlit run app.py\n   ```\n\n## 🤝 Contributing\n\nWe welcome contributions from the community! Here's how you can help:\n\n- 🐛 **Report bugs** or suggest improvements via [GitHub Issues](https:\u002F\u002Fgithub.com\u002FArindam200\u002Fawesome-ai-apps\u002Fissues)\n- 💡 **Add new projects** - Submit your own AI agent examples\n- 📝 **Improve documentation** - Help make projects more accessible\n- 🔧 **Fix issues** - Contribute code improvements and bug fixes\n\n**Before contributing:**\n\n- Read our [Contributing Guidelines](CONTRIBUTING.md) for detailed information\n- Check existing issues to avoid duplicates\n- Follow the project structure and naming conventions\n- Ensure your project includes a comprehensive README.md\n\n**Important:** This project follows a [Contributor Code of Conduct](CODE_OF_CONDUCT.md). By participating, you agree to abide by its terms.\n\n## 📜 License\n\nThis repository is licensed under the [MIT License](.\u002FLICENSE). Feel free to use and modify the examples for your projects.\n\n## 👥 Core Maintainers\n\nThis project is actively maintained by:\n\n\u003Cp align=\"center\">\n  \u003Ca href=\"https:\u002F\u002Fgithub.com\u002FArindam200\" title=\"Arindam Majumder\">\n    \u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FArindam200_awesome-ai-apps_readme_f96dc1126ab7.png\" width=\"72\" height=\"72\" alt=\"Arindam Majumder\" style=\"border-radius: 50%;\" \u002F>\n  \u003C\u002Fa>\n     \n  \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fshivaylamba\" title=\"Shivay Lamba\">\n    \u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FArindam200_awesome-ai-apps_readme_e2e3779147e7.png\" width=\"72\" height=\"72\" alt=\"Shivay Lamba\" style=\"border-radius: 50%;\" \u002F>\n  \u003C\u002Fa>\n     \n  \u003Ca href=\"https:\u002F\u002Fgithub.com\u002FAstrodevil\" title=\"Astrodevil\">\n    \u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FArindam200_awesome-ai-apps_readme_64f3007189a7.png\" width=\"72\" height=\"72\" alt=\"Astrodevil\" style=\"border-radius: 50%;\" \u002F>\n  \u003C\u002Fa>\n\u003C\u002Fp>\n\n\u003Cp align=\"center\">\n  \u003Csub>\n    \u003Ca href=\"https:\u002F\u002Fgithub.com\u002FArindam200\">Arindam Majumder\u003C\u002Fa>\n     · \n    \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fshivaylamba\">Shivay Lamba\u003C\u002Fa>\n     · \n    \u003Ca href=\"https:\u002F\u002Fgithub.com\u002FAstrodevil\">Astrodevil\u003C\u002Fa>\n  \u003C\u002Fsub>\n\u003C\u002Fp>\n\nFor any questions, suggestions, or contributions, feel free to reach out to the maintainers.\n\n## Thank You for the Support! 🙏\n\n[![Star History Chart](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FArindam200_awesome-ai-apps_readme_4a77588ed71f.png)](https:\u002F\u002Fwww.star-history.com\u002F#Arindam200\u002Fawesome-ai-apps&Date)\n","![Banner](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FArindam200_awesome-ai-apps_readme_09f7c23d7766.png)\n\n\u003Cdiv align=\"center\">\n\n# 令人惊叹的 AI 应用 [![Awesome](https:\u002F\u002Fawesome.re\u002Fbadge.svg)](https:\u002F\u002Fawesome.re)\n\n\u003Ca href=\"https:\u002F\u002Ftrendshift.io\u002Frepositories\u002F14662\" target=\"_blank\">\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FArindam200_awesome-ai-apps_readme_bbada6ddd5d3.png\" alt=\"Arindam200%2Fawesome-ai-apps | Trendshift\" style=\"width: 250px; height: 55px;\" width=\"250\" height=\"55\"\u002F>\u003C\u002Fa>\n\n\u003C\u002Fdiv>\n\n本仓库是一个全面的集合，包含**80多个实用示例、教程和配方**，用于构建强大的基于 LLM 的应用——包括文本代理、语音助手、RAG 应用以及由 MCP 支持的工具。这些项目为使用各种 AI 框架和技术栈的开发者提供了指导。\n\n## 📋 目录\n\n- [🎓 课程](#-courses)\n- [🚀 精选 AI 应用](#-featured-ai-apps)\n  - [🧩 入门级代理](#-starter-agents)\n  - [🪶 简单代理](#-simple-agents)\n  - [🎙️ 语音代理](#-voice-agents)\n  - [🗂️ MCP 代理](#️-mcp-agents)\n  - [🧠 记忆代理](#-memory-agents)\n  - [📚 RAG 应用](#-rag-applications)\n  - [🔬 高级代理](#-advanced-agents)\n- [📺 教程与视频](#-tutorials--videos)\n- [🚀 入门指南](#getting-started)\n- [🤝 贡献](#-contributing)\n\n---\n\n\u003Cdiv align=\"center\">\n\n## 💎 赞助商\n\n\u003Cp align=\"center\">\n  衷心感谢各位赞助商的慷慨支持！\n\u003C\u002Fp>\n\n\u003Ctable align=\"center\" cellpadding=\"10\" style=\"width:100%; border-collapse:collapse;\">\n  \u003Ctr align=\"center\">\n    \u003Ctd width=\"300\" valign=\"middle\" align=\"center\">\n      \u003Ca href=\"https:\u002F\u002Fdub.sh\u002Fbrightdata\" target=\"_blank\" title=\"访问 Bright Data\">\n        \u003Cimg src=\"https:\u002F\u002Fmintlify.s3.us-west-1.amazonaws.com\u002Fbrightdata\u002Flogo\u002Flight.svg\" height=\"35\" style=\"max-width:180px;\" alt=\"Bright Data - 网络数据平台\">\n      \u003C\u002Fa>\n      \u003Cbr>\n      \u003Csub>\n        \u003Cspan style=\"white-space:nowrap;\">网络数据平台\u003C\u002Fspan>\n        \u003Cbr>\n        \u003Ca href=\"https:\u002F\u002Fdub.sh\u002Fbrightdata\" target=\"_blank\">\n          \u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FVisit%20Site-blue?style=flat-square\" alt=\"访问 Bright Data 官网\">\n        \u003C\u002Fa>\n      \u003C\u002Fsub>\n    \u003C\u002Ftd>\n    \u003Ctd width=\"300\" valign=\"middle\" align=\"center\">\n      \u003Ca href=\"https:\u002F\u002Fdub.sh\u002Fnebius\" target=\"_blank\" title=\"访问 Nebius Token Factory\">\n        \u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FArindam200_awesome-ai-apps_readme_1cf213308fe6.png\" height=\"36\" style=\"max-width:180px;\" alt=\"Nebius Token Factory\">\n      \u003C\u002Fa>\n      \u003Cbr>\n      \u003Csub>\n        \u003Cspan style=\"white-space:nowrap;\">AI 推理服务提供商\u003C\u002Fspan>\n        \u003Cbr>\n        \u003Ca href=\"https:\u002F\u002Fdub.sh\u002Fnebius\" target=\"_blank\">\n          \u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FVisit%20Site-blue?style=flat-square\" alt=\"访问 Nebius Token Factory 官网\">\n        \u003C\u002Fa>\n      \u003C\u002Fsub>\n    \u003C\u002Ftd>\n    \u003Ctd width=\"300\" valign=\"middle\" align=\"center\">\n      \u003Ca href=\"https:\u002F\u002Fdub.sh\u002Fscrapegraphai\" target=\"_blank\" title=\"访问 ScrapeGraphAI 在 GitHub 上\">\n        \u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FArindam200_awesome-ai-apps_readme_904b7cdfd793.png\" height=\"44\" style=\"max-width:180px;\" alt=\"ScrapeGraphAI - 网页抓取库\">\n      \u003C\u002Fa>\n      \u003Cbr>\n      \u003Csub>\n        \u003Cspan style=\"white-space:nowrap;\">AI 网页抓取框架\u003C\u002Fspan>\n        \u003Cbr>\n        \u003Ca href=\"https:\u002F\u002Fdub.sh\u002Fscrapegraphai\" target=\"_blank\">\n          \u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FVisit%20Site-blue?style=flat-square\" alt=\"查看 ScrapeGraphAI 在 GitHub 上\">\n        \u003C\u002Fa>\n      \u003C\u002Fsub>\n    \u003C\u002Ftd>\n  \u003C\u002Ftr>\n  \u003Ctr align=\"center\">\n    \u003Ctd width=\"300\" valign=\"middle\" align=\"center\">\n      \u003Ca href=\"https:\u002F\u002Fdub.sh\u002Fmemorilabs\" target=\"_blank\" title=\"访问 Memorilabs\">\n        \u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FArindam200_awesome-ai-apps_readme_9ee3ad72e9b7.png\" height=\"36\" style=\"max-width:180px;\" alt=\"Memori - 面向 AI 的 SQL 原生内存\">\n      \u003C\u002Fa>\n      \u003Cbr>\n      \u003Csub>\n        \u003Cspan style=\"white-space:nowrap;\">面向 AI 的 SQL 原生内存\u003C\u002Fspan>\n        \u003Cbr>\n        \u003Ca href=\"https:\u002F\u002Fdub.sh\u002Fmemorilabs\" target=\"_blank\">\n          \u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FVisit%20Site-blue?style=flat-square\" alt=\"访问 Memorilabs 官网\">\n        \u003C\u002Fa>\n      \u003C\u002Fsub>\n    \u003C\u002Ftd>\n    \u003Ctd width=\"300\" valign=\"middle\" align=\"center\">\n      \u003Ca href=\"https:\u002F\u002Fdub.sh\u002Fcopilotkit\" target=\"_blank\" title=\"访问 CopilotKit\">\n        \u003Cimg src=\"assets\u002Fcopilot-kit-logo.svg\" height=\"36\" style=\"max-width:180px;\" alt=\"CopilotKit - 代理式应用平台\">\n      \u003C\u002Fa>\n      \u003Cbr>\n      \u003Csub>\n        \u003Cspan style=\"white-space:nowrap;\">代理式应用平台\u003C\u002Fspan>\n        \u003Cbr>\n        \u003Ca href=\"https:\u002F\u002Fdub.sh\u002Fcopilotkit\" target=\"_blank\">\n          \u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FVisit%20Site-blue?style=flat-square\" alt=\"访问 CopilotKit 官网\">\n        \u003C\u002Fa>\n      \u003C\u002Fsub>\n    \u003C\u002Ftd>\n    \u003Ctd width=\"300\" valign=\"middle\" align=\"center\">\n      \u003Ca href=\"https:\u002F\u002Fdub.sh\u002Fscalekitt\" target=\"_blank\" title=\"访问 ScaleKit\">\n        \u003Cimg src=\"assets\u002Fscalekit.svg\" height=\"36\" style=\"max-width:180px;\" alt=\"ScaleKit - 面向 AI 的认证栈\">\n      \u003C\u002Fa>\n      \u003Cbr>\n      \u003Csub>\n        \u003Cspan style=\"white-space:nowrap;\">面向 AI 的认证栈\u003C\u002Fspan>\n        \u003Cbr>\n        \u003Ca href=\"https:\u002F\u002Fdub.sh\u002Fscalekitt\" target=\"_blank\">\n          \u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FVisit%20Site-blue?style=flat-square\" alt=\"访问 ScaleKit 官网\">\n        \u003C\u002Fa>\n      \u003C\u002Fsub>\n    \u003C\u002Ftd>\n  \u003C\u002Ftr>\n  \u003Ctr align=\"center\">\n    \u003Ctd width=\"200\" valign=\"middle\" align=\"center\">\n      \u003Ca href=\"https:\u002F\u002Fokahu.ai\" target=\"_blank\" title=\"访问 Okahu\">\n        \u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FArindam200_awesome-ai-apps_readme_6825a905f76f.png\" height=\"36\" style=\"max-width:180px;\" alt=\"Okahu - AI 平台\">\n      \u003C\u002Fa>\n      \u003Cbr>\n      \u003Csub>\n        \u003Cspan style=\"white-space:nowrap;\">AI 可观测性平台\u003C\u002Fspan>\n        \u003Cbr>\n        \u003Ca href=\"https:\u002F\u002Fokahu.ai\" target=\"_blank\">\n          \u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FVisit%20Site-blue?style=flat-square\" alt=\"访问 Okahu 官网\">\n        \u003C\u002Fa>\n      \u003C\u002Fsub>\n    \u003C\u002Ftd>\n    \u003Ctd width=\"200\" valign=\"middle\" align=\"center\">\n      \u003Ca href=\"https:\u002F\u002Fdub.sh\u002FserpApi\" target=\"_blank\" title=\"访问 SerpApi\">\n        \u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FArindam200_awesome-ai-apps_readme_1205205dbbaf.png\" height=\"36\" style=\"max-width:180px;\" alt=\"SerpApi - Google 搜索 API\">\n      \u003C\u002Fa>\n      \u003Cbr>\n      \u003Csub>\n        \u003Cspan style=\"white-space:nowrap;\">Google 搜索 API\u003C\u002Fspan>\n        \u003Cbr>\n        \u003Ca href=\"https:\u002F\u002Fdub.sh\u002FserpApi\" target=\"_blank\">\n          \u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FVisit%20Site-blue?style=flat-square\" alt=\"访问 SerpApi 官网\">\n        \u003C\u002Fa>\n      \u003C\u002Fsub>\n    \u003C\u002Ftd>\n    \u003Ctd width=\"200\" valign=\"middle\" align=\"center\">\n      \u003Ca href=\"https:\u002F\u002Fdub.sh\u002Fagentfield\" target=\"_blank\" title=\"访问 AgentField\">\n        \u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FArindam200_awesome-ai-apps_readme_2697f66b2124.png\" height=\"40\" style=\"max-width:180px;\" alt=\"AgentField - 面向 AI 代理的 Kubernetes\">\n      \u003C\u002Fa>\n      \u003Cbr>\n      \u003Csub>\n        \u003Cspan style=\"white-space:nowrap;\">面向 AI 代理的 Kubernetes\u003C\u002Fspan>\n        \u003Cbr>\n        \u003Ca href=\"https:\u002F\u002Fdub.sh\u002Fagentfield\" target=\"_blank\">\n          \u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FVisit%20Site-blue?style=flat-square\" alt=\"访问 AgentField 官网\">\n        \u003C\u002Fa>\n      \u003C\u002Fsub>\n    \u003C\u002Ftd>\n  \u003C\u002Ftr>\n\n   \n\n\u003C\u002Ftable>\n\n### 💎 成为赞助商\n\n\u003Cp align=\"center\">\n如果您有兴趣赞助本项目，请随时联系我们！\n\u003Cbr\u002F>\n\u003Ca href=\"https:\u002F\u002Fdub.sh\u002Farindam-linkedin\" target=\"_blank\">\n    \u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FLinkedIn-0077B5?style=for-the-badge&logo=linkedin&logoColor=white\" alt=\"LinkedIn\">\n\u003C\u002Fa>\n\u003Ca href=\"mailto:arindammajumder2020@gmail.com\">\n    \u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FEmail-D14836?style=for-the-badge&logo=gmail&logoColor=white\" alt=\"Email\">\n\u003C\u002Fa>\n\u003C\u002Fp>\n\n\u003C\u002Fdiv>\n\n---\n\n## 🎓 课程\n\n### AWS Strands 初学者课程\n\n**使用 AWS Strands SDK 构建 AI 代理的全面实践课程：**\n\n- [**AWS Strands 课程**](course\u002Faws_strands) - 完整的 8 节课，涵盖从代理基础到生产级模式的内容\n  - **基础**：基本代理、会话管理、结构化输出\n  - **集成**：MCP 代理、人机协作模式\n  - **多智能体**：编排型代理、群体智能、图工作流\n  - **生产**：可观测性、安全防护机制及最佳实践\n\n## 🚀 精选 AI 应用\n\n### 🧩 入门级代理\n\n**用于学习和扩展不同 AI 框架的快速入门代理。** _13 个项目_\n\n- [Agno HackerNews 分析](starter_ai_agents\u002Fagno_starter) - 基于 Agno 的代理，用于分析 HackerNews 上的趋势\n- [OpenAI SDK 入门](starter_ai_agents\u002Fopenai_agents_sdk) - OpenAI Agents SDK，包含邮件助手和俳句生成器示例\n- [LlamaIndex 任务管理器](starter_ai_agents\u002Fllamaindex_starter) - 基于 LlamaIndex 的任务助手\n- [CrewAI 研究团队](starter_ai_agents\u002Fcrewai_starter) - 多智能体研究团队示例\n- [PydanticAI 天气机器人](starter_ai_agents\u002Fpydantic_starter) - 实时天气信息代理\n- [LangChain-LangGraph 入门](starter_ai_agents\u002Flangchain_langgraph_starter) - LangChain + LangGraph 工作流入门\n- [AWS Strands 代理入门](starter_ai_agents\u002Faws_strands_starter) - 使用 AWS Strands SDK 的天气预报代理\n- [Camel AI 入门](starter_ai_agents\u002Fcamel_ai_starter) - 性能基准测试工具，用于比较各种 AI 模型\n- [DSPy 入门](starter_ai_agents\u002Fdspy_starter) - DSPy 框架，用于构建和优化 AI 系统\n- [Google ADK 入门](starter_ai_agents\u002Fgoogle_adk_starter) - Google Agent Development Kit 入门模板\n- [cagent 入门](starter_ai_agents\u002Fcagent_starter) - Docker 开源的可定制多智能体运行时\n- [Sayna 语音代理](starter_ai_agents\u002Fsayna_starter) - 实时语音基础设施，支持多提供商 STT\u002FTTS（Deepgram、ElevenLabs、Azure、Google）以及 WebSocket 流媒体传输\n- [KAOS 入门](starter_ai_agents\u002Fkaos_starter) - 基于 Kubernetes 的多智能体系统，配备 MCP 工具和集群内 LLM\n\n### 🪶 简单代理\n\n**面向日常 AI 应用的直接且实用的案例。** _14 个项目_\n\n- [Agno AI 示例](simple_ai_agents\u002Fagno_ai_examples) - 从简单到多智能体的示例，结合网页搜索和知识库\n- [金融代理](simple_ai_agents\u002Ffinance_agent) - 实时股票与市场数据跟踪代理\n- [人机协作代理](simple_ai_agents\u002Fhuman_in_the_loop_agent) - 用于安全执行 AI 任务的 HITL 操作\n- [新闻通讯生成器](simple_ai_agents\u002Fnewsletter_agent) - 结合 Firecrawl 的 AI 驱动新闻通讯生成器\n- [推理代理](simple_ai_agents\u002Freasoning_agent) - 分步展示财务推理过程\n- [Agno UI 示例](simple_ai_agents\u002Fagno_ui_agent) - 适用于网络和金融代理的交互式界面\n- [Mastra 天气机器人](simple_ai_agents\u002Fmastra_ai_weather_agent) - 使用 Mastra AI 框架的天气更新\n- [日历助理](simple_ai_agents\u002Fcal_scheduling_agent) - 与 Cal.com 集成的日历安排代理\n- [智能日程安排助手](simple_ai_agents\u002Femail_to_calendar_scheduler) - 基于 AI 的 Gmail 阅读器和 Google 日历管理器\n- [网页自动化代理](simple_ai_agents\u002Fbrowser_agent) - 使用 Nebius 和 browser-use 的浏览器自动化代理\n- [Nebius 聊天](simple_ai_agents\u002Fnebius_chat) - Nebius Token Factory 的聊天界面\n- [RouteLLM 聊天](simple_ai_agents\u002Fllm_router) - 智能模型路由，通过 RouteLLM（GPT-4o-mini 与 Nebius Llama）实现成本优化\n- [与数据库对话](simple_ai_agents\u002Ftalk_to_db) - 使用 GibsonAI 和 LangChain 进行自然语言数据库查询\n- [代理发现代理](simple_ai_agents\u002Fagent_discovery_agent) - 在 NANDA、MCP、Virtuals、A2A 和 ERC-8004 注册表中查找并比较 AI 代理\n\n### 🎙️ 语音代理\n\n**实时语音助手和流式语音管道。** _2 个项目_\n\n- [LiveKit + Gemini 实时](voice_agents\u002Flivekit_gemini_agents) - LiveKit 代理结合 Google Gemini Live（`gemini` 多模态实时功能），在 LiveKit 房间中实现低延迟语音对话\n- [Pipecat + Sarvam](voice_agents\u002Fpipecat_agent) - Pipecat 语音管道，结合 Sarvam STT\u002FTTS 和 OpenAI 进行聊天；可通过 WebRTC（浏览器）或 Daily 传输，借助 Pipecat 运行器实现\n\n### 🗂️ MCP 代理\n\n**使用 Model Context Protocol 进行外部工具集成的示例。** _13 个项目_\n\n- [Doc-MCP](mcp_ai_agents\u002Fdoc_mcp) - 语义 RAG 文档与问答系统\n- [LangGraph MCP 代理](mcp_ai_agents\u002Flangchain_langgraph_mcp_agent) - LangChain ReAct 代理，集成 Couchbase 数据库\n- [GitHub MCP 代理](mcp_ai_agents\u002Fgithub_mcp_agent) - 通过 MCP 提供仓库洞察与分析\n- [MCP 入门](mcp_ai_agents\u002Fmcp_starter) - GitHub 仓库分析器入门模板\n- [与文档对话](mcp_ai_agents\u002Fdocs_qna_agent) - 基于 MCP 的文档问答代理\n- [数据库 MCP 代理](mcp_ai_agents\u002Fdatabase_mcp_agent) - 用于管理 GibsonAI 数据库项目和架构的对话式 AI 代理\n- [酒店查找代理](mcp_ai_agents\u002Fhotel_finder_agent) - 使用 MCP 集成进行酒店搜索和预订\n- [自定义 MCP 服务器](mcp_ai_agents\u002Fcustom_mcp_server) - 自定义 MCP 服务器实现示例\n- [Couchbase MCP 服务器](mcp_ai_agents\u002Fcouchbase_mcp_server) - 通过 MCP 协议集成 Couchbase 数据库\n- [ScaleKit Exa MCP 安全](mcp_ai_agents\u002Fscalekit-exa-mcp-security) - 以安全为重点的 MCP 集成，结合 Exa 搜索\n- [Docker E2B MCP 代理](mcp_ai_agents\u002Fe2b_docker_mcp_agent) - 通过 MCP 网关，在沙盒化的 Docker 环境中运行代理的安全 AI 代理\n- [Taskade MCP 代理](mcp_ai_agents\u002Ftaskade_mcp_agent) - 基于 Taskade MCP 的 AI 驱动工作空间代理，用于管理项目、任务和工作流\n- [Telemetry MCP Okahu](mcp_ai_agents\u002Ftelemetry-mcp-okahu) - 使用 Okahu Cloud 跟踪数据，通过托管 MCP 实现自我修复的文本转 SQL 演示\n\n### 🧠 记忆智能体\n\n**具备高级记忆能力的智能体，用于保持上下文和个性化。** _12个项目_\n\n- [Agno记忆智能体](memory_agents\u002Fagno_memory_agent) - 基于Agno的具有持久记忆能力的智能体\n- [带有Memori的arXiv研究员智能体](memory_agents\u002Farxiv_researcher_agent_with_memori) - 使用OpenAI Agents和GibsonAI Memori的研究助理\n- [带有Memori的AWS Strands智能体](memory_agents\u002Faws_strands_agent_with_memori) - 由Memori记忆系统增强的AWS Strands智能体\n- [博客写作智能体](memory_agents\u002Fblog_writing_agent) - 具有记忆功能以保持写作风格一致性的个性化博客写作智能体\n- [社交媒体智能体](memory_agents\u002Fsocial_media_agent) - 具有品牌声音记忆功能的社交媒体自动化智能体\n- [求职智能体](memory_agents\u002Fjob_search_agent) - 具有偏好跟踪记忆功能的求职智能体\n- [品牌声誉监控器](memory_agents\u002Fbrand_reputation_monitor) - 基于AI的品牌声誉监控工具，具备新闻分析和情感追踪功能\n- [产品发布智能体](memory_agents\u002Fproduct_launch_agent) - 用于分析竞争对手产品发布的竞争情报工具\n- [AI顾问智能体](memory_agents\u002Fai_consultant_agent\u002F) - 使用**Memori v3**作为长期记忆框架、并借助**ExaAI**进行研究的AI驱动顾问智能体\n- [客户支持语音智能体](memory_agents\u002Fcustomer_support_voice_agent) - 配备Memori v3和Firecrawl用于知识库管理的语音客户支持助手\n- [YouTube趋势智能体](memory_agents\u002Fyoutube_trend_agent) - 结合Memori、Agno和Exa进行趋势分析与视频创意生成的YouTube频道分析智能体\n- [学习教练智能体](memory_agents\u002Fstudy_coach_agent) - 使用Memori v3和LangGraph进行多步骤理解验证的AI驱动学习教练智能体\n\n### 📚 RAG应用\n\n**用于文档理解和知识库的检索增强生成示例。** _12个项目_\n\n- [代理式RAG](rag_apps\u002Fagentic_rag) - 结合Agno与GPT-5的代理式RAG实现\n- [带网络搜索的代理式RAG](rag_apps\u002Fagentic_rag_with_web_search) - 利用CrewAI、Qdrant和Exa实现混合搜索功能的高级RAG\n- [简历优化器](rag_apps\u002Fresume_optimizer) - 基于AI的简历优化与提升工具\n- [LlamaIndex RAG入门](rag_apps\u002FllamaIndex_starter) - LlamaIndex + Nebius RAG入门模板\n- [PDF RAG分析器](rag_apps\u002Fpdf_rag_analyser) - 多PDF聊天与分析系统\n- [Qwen3 RAG聊天](rag_apps\u002Fqwen3_rag) - 使用Streamlit构建的PDF聊天机器人界面\n- [代码聊天](rag_apps\u002Fchat_with_code) - 对话式代码探索与文档辅助工具\n- [Gemma3 OCR](rag_apps\u002Fgemma_ocr\u002F) - 基于Gemma3模型的OCR文档与图像处理工具\n- [Nvidia Nemotron OCR](rag_apps\u002Fnvidia_ocr\u002F) - 使用Nvidia Nemotron-Nano-V2-12b进行文档与图像解析的OCR工具\n- [情境AI RAG](rag_apps\u002Fcontextual_ai_rag) - 具有托管数据存储和质量评估的企业级RAG\n- [简单RAG](rag_apps\u002Fsimple_rag) - 使用Nebius实现的快速启动基础RAG\n- [WFGY 16问题地图LLM调试器](rag_apps\u002Fwfgy_llm_debugger) - 基于16种模式的地图型LLM和RAG错误调试工具\n\n### 🔬 高级智能体\n\n**面向生产环境的复杂多智能体流程。** _18个项目_\n\n- [Nebius AutoResearch](advance_ai_agents\u002Fnebius-autoresearch-autoresearch-mar30) - 纽约市出租车数据分析流程优化器；结合Nebius Token Factory进行迭代式代码搜索（实时或批量推理）\n- [AgentField金融研究智能体](advance_ai_agents\u002Fagentfield_finance_research_agent) - 使用AgentField的金融研究智能体\n- [尽职调查智能体](advance_ai_agents\u002Fdue_diligence_agent) - 结合AG2和TinyFish深度网络爬虫的多智能体公司尽职调查流程\n- [深度研究员](advance_ai_agents\u002Fdeep_researcher_agent) - 结合Agno与ScrapeGraph AI的多阶段研究智能体\n- [候选人分析器](advance_ai_agents\u002Fcandidate_analyser) - 用于GitHub\u002FLinkedIn个人资料分析的工具\n- [求职智能体](advance_ai_agents\u002Fjob_finder_agent) - 集成Bright Data的LinkedIn职位搜索自动化工具\n- [AI趋势分析器](advance_ai_agents\u002Ftrend_analyzer_agent) - 结合Google ADK进行AI趋势挖掘与分析的智能体\n- [会议演讲生成器](advance_ai_agents\u002Fconference_talk_abstract_generator) - 结合Google ADK与Couchbase实现的自动演讲摘要生成工具\n- [金融服务智能体](advance_ai_agents\u002Ffinance_service_agent) - 使用Agno构建的用于股票数据与预测的FastAPI服务器\n- [价格监控智能体](advance_ai_agents\u002Fprice_monitoring_agent) - 基于CrewAI、Twilio与Nebius的价格监控与提醒智能体\n- [创业想法验证智能体](advance_ai_agents\u002Fstartup_idea_validator_agent) - 用于验证和分析创业想法的代理式工作流\n- [会议助手智能体](advance_ai_agents\u002Fmeeting_assistant_agent) - 根据对话自动生成会议记录与任务的智能体\n- [AI对冲基金](advance_ai_agents\u002Fai-hedgefund) - 用于全面财务分析的代理式工作流\n- [智能GTM智能体](advance_ai_agents\u002Fsmart_gtm_agent) - 用于进入市场策略与竞争分析的智能体\n- [会议无关CFP生成器](advance_ai_agents\u002Fconference_agnositc_cfp_generator) - 自动化会议提案生成系统\n- [汽车寻找智能体](advance_ai_agents\u002Fcar_finder_agent) - 结合CrewAI和MongoDB的二手车推荐AI系统\n- [内容团队智能体](advance_ai_agents\u002Fcontent_team_agent) - 使用Agno与SerpAPI提升Google AI搜索排名的SEO内容优化工作流\n- [时序智能体](advance_ai_agents\u002Ftemporal_agents\u002F) - 基于Temporal的AI智能体示例\n\n## 📺 教程与视频\n\n### 🎓 课程播放列表\n\n- [**AWS Strands课程**](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PLMZM1DAlf0Lrc43ZtUXAwYu9DhnqxzRKZ) - 完整的8课时课程，讲解如何使用AWS Strands SDK构建AI智能体\n\n### 🔧 框架教程\n\n- [**使用MCP构建**](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PLMZM1DAlf0Lolxax4L2HS54Me8gn1gkz4) - Model Context Protocol教程与示例\n- [**构建AI智能体**](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PLMZM1DAlf0LqixhAG9BDk4O_FjqnaogK8) - 通用AI智能体开发教程\n- [**AI智能体、MCP及其他...**](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PL2ambAOfYA6-LDz0KpVKu9vJKAqhv0KKI) - 混合教程与项目演示\n\n---\n\n\u003Cdiv align=\"center\">\n\n## 📥 每日AI洞察，助您保持前沿！\n\n每周提供易于跟随的教程与深入解读，涵盖AI、LLM及智能体框架。非常适合希望学习、构建并紧跟新技术的开发者。立即订阅我们的通讯吧！\n\n[![订阅我们的通讯](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FArindam200_awesome-ai-apps_readme_b94c361c9a8e.png)](https:\u002F\u002Fmranand.substack.com\u002Fsubscribe)\n\n\u003C\u002Fdiv>\n\n---\n\n## 开始使用\n\n### 前置条件\n\n- **Python 3.10+**（对于新项目，建议使用 Python 3.11+）\n- **Git** 用于克隆仓库\n- **包管理器**：`pip` 或 `uv`（推荐使用 `uv` 以获得更快的安装速度）\n- **API 密钥**：大多数项目需要 API 密钥（请参阅各个项目的 README 文件）\n\n### 快速开始\n\n1. **克隆仓库**\n\n   ```bash\n   git clone https:\u002F\u002Fgithub.com\u002FArindam200\u002Fawesome-ai-apps.git\n   cd awesome-ai-apps\n   ```\n\n2. **选择一个项目**并进入其目录\n\n   ```bash\n   cd starter_ai_agents\u002Fagno_starter  # 示例：从 Agno 入门项目开始\n   ```\n\n3. **设置环境变量**\n\n   ```bash\n   cp .env.example .env  # 复制示例环境文件\n   # 编辑 .env 文件，填入您的 API 密钥\n   ```\n\n4. **安装依赖**\n\n   ```bash\n   # 使用 pip 安装\n   pip install -r requirements.txt\n\n   # 或者使用 uv（推荐，速度更快）\n   uv sync\n   # 或\n   uv pip install -e .\n   ```\n\n5. **运行项目**\n\n   ```bash\n   python main.py\n   # 或对于 Streamlit 应用\n   streamlit run app.py\n   ```\n\n## 🤝 贡献\n\n我们欢迎社区的贡献！以下是您可以帮助的方式：\n\n- 🐛 **报告 bug** 或通过 [GitHub Issues](https:\u002F\u002Fgithub.com\u002FArindam200\u002Fawesome-ai-apps\u002Fissues) 提出改进建议\n- 💡 **添加新项目** - 提交您自己的 AI 代理示例\n- 📝 **改进文档** - 帮助使项目更加易于理解\n- 🔧 **修复问题** - 贡献代码改进和 bug 修复\n\n**在贡献之前：**\n\n- 请阅读我们的 [贡献指南](CONTRIBUTING.md)，以获取详细信息\n- 检查现有问题，避免重复提交\n- 遵循项目结构和命名规范\n- 确保您的项目包含一份完整的 README.md 文件\n\n**重要提示：** 本项目遵循 [贡献者行为准则](CODE_OF_CONDUCT.md)。参与即表示您同意遵守其中的条款。\n\n## 📜 许可证\n\n本仓库采用 [MIT 许可证](.\u002FLICENSE) 许可。您可以自由地使用和修改这些示例，以用于您的项目中。\n\n## 👥 核心维护者\n\n该项目由以下人员积极维护：\n\n\u003Cp align=\"center\">\n  \u003Ca href=\"https:\u002F\u002Fgithub.com\u002FArindam200\" title=\"Arindam Majumder\">\n    \u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FArindam200_awesome-ai-apps_readme_f96dc1126ab7.png\" width=\"72\" height=\"72\" alt=\"Arindam Majumder\" style=\"border-radius: 50%;\" \u002F>\n  \u003C\u002Fa>\n     \n  \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fshivaylamba\" title=\"Shivay Lamba\">\n    \u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FArindam200_awesome-ai-apps_readme_e2e3779147e7.png\" width=\"72\" height=\"72\" alt=\"Shivay Lamba\" style=\"border-radius: 50%;\" \u002F>\n  \u003C\u002Fa>\n     \n  \u003Ca href=\"https:\u002F\u002Fgithub.com\u002FAstrodevil\" title=\"Astrodevil\">\n    \u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FArindam200_awesome-ai-apps_readme_64f3007189a7.png\" width=\"72\" height=\"72\" alt=\"Astrodevil\" style=\"border-radius: 50%;\" \u002F>\n  \u003C\u002Fa>\n\u003C\u002Fp>\n\n\u003Cp align=\"center\">\n  \u003Csub>\n    \u003Ca href=\"https:\u002F\u002Fgithub.com\u002FArindam200\">Arindam Majumder\u003C\u002Fa>\n     · \n    \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fshivaylamba\">Shivay Lamba\u003C\u002Fa>\n     · \n    \u003Ca href=\"https:\u002F\u002Fgithub.com\u002FAstrodevil\">Astrodevil\u003C\u002Fa>\n  \u003C\u002Fsub>\n\u003C\u002Fp>\n\n如有任何问题、建议或贡献，请随时联系维护者。\n\n## 感谢您的支持！ 🙏\n\n[![星标历史图](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FArindam200_awesome-ai-apps_readme_4a77588ed71f.png)](https:\u002F\u002Fwww.star-history.com\u002F#Arindam200\u002Fawesome-ai-apps&Date)","# awesome-ai-apps 快速上手指南\n\n`awesome-ai-apps` 是一个汇集了 80+ 个实用 LLM 应用示例、教程和代码食谱的开源仓库。它涵盖了文本代理、语音助手、RAG 应用、MCP 工具等多种场景，旨在帮助开发者快速掌握主流 AI 框架（如 LangChain, CrewAI, Agno, LlamaIndex 等）的开发模式。\n\n## 🛠️ 环境准备\n\n在开始之前，请确保您的开发环境满足以下要求：\n\n*   **操作系统**: Windows, macOS 或 Linux\n*   **Python 版本**: 推荐 Python 3.10 或更高版本\n*   **包管理器**: pip 或 uv (推荐)\n*   **API Keys**: 根据您选择的具体示例，可能需要准备相应的 API Key（如 OpenAI, Anthropic, Google Gemini, AWS 等）。\n\n**前置依赖安装：**\n建议为每个示例项目创建独立的虚拟环境，以避免依赖冲突。\n\n```bash\n# 使用 venv 创建虚拟环境\npython -m venv venv\n\n# 激活虚拟环境\n# Windows:\nvenv\\Scripts\\activate\n# macOS\u002FLinux:\nsource venv\u002Fbin\u002Factivate\n```\n\n## 📦 安装步骤\n\n由于该仓库包含多个独立的项目示例，没有统一的“一键安装”命令。请按照以下步骤获取并安装特定示例的依赖：\n\n1.  **克隆仓库**\n    ```bash\n    git clone https:\u002F\u002Fgithub.com\u002FArindam200\u002Fawesome-ai-apps.git\n    cd awesome-ai-apps\n    ```\n\n2.  **选择并进入目标示例目录**\n    浏览 `starter_ai_agents`, `simple_ai_agents`, `voice_agents` 等文件夹，选择您感兴趣的项目。例如，选择一个基于 Agno 的入门代理：\n    ```bash\n    cd starter_ai_agents\u002Fagno_starter\n    ```\n\n3.  **安装项目依赖**\n    进入具体项目目录后，安装其所需的 Python 包。如果项目根目录提供了 `requirements.txt`：\n    ```bash\n    pip install -r requirements.txt\n    ```\n    *注：部分现代项目可能使用 `pyproject.toml`，可使用 `pip install .` 或 `uv sync` 进行安装。*\n\n4.  **配置环境变量**\n    大多数示例需要 API Key。请在项目目录下创建 `.env` 文件（如果不存在），并填入您的密钥：\n    ```bash\n    # 示例 .env 文件内容\n    OPENAI_API_KEY=sk-your-key-here\n    ANTHROPIC_API_KEY=sk-ant-your-key-here\n    ```\n\n## 🚀 基本使用\n\n以下以 `starter_ai_agents` 中的 **Agno HackerNews Analysis** 为例，展示如何运行一个简单的 AI 代理。\n\n1.  **确认环境**：确保已激活虚拟环境并安装了 `agno` 及相关依赖。\n2.  **配置密钥**：在 `.env` 文件中配置好 `OPENAI_API_KEY`。\n3.  **运行脚本**：\n    在项目目录下执行主程序文件（通常为 `main.py`, `app.py` 或 `run.py`，具体文件名请参考该项目目录下的说明）：\n\n    ```bash\n    python main.py\n    ```\n\n4.  **交互体验**：\n    程序启动后，终端将提示您输入问题。例如，您可以输入：\n    ```text\n    What are the top trending topics on HackerNews today?\n    ```\n    代理将调用大模型进行分析并返回结果。\n\n**探索更多示例：**\n*   **语音代理**: 进入 `voice_agents\u002Flivekit_gemini_agents` 运行实时语音对话示例。\n*   **RAG 应用**: 进入 `mcp_ai_agents\u002Fdoc_mcp` 体验基于文档的问答系统。\n*   **复杂工作流**: 查看 `simple_ai_agents` 中的多代理协作案例。\n\n> **提示**：每个子目录通常包含独立的 `README.md`，其中详细说明了该特定示例的运行参数和特殊要求，建议在运行前查阅。","某初创团队的技术负责人正带领三名开发者，试图在两周内构建一个能结合内部文档检索与外部工具调用的智能客服原型。\n\n### 没有 awesome-ai-apps 时\n- **架构选型迷茫**：面对 RAG、Agent、MCP 等多种技术路线，团队花费数天查阅零散文档仍无法确定最佳实践方案。\n- **重复造轮子**：开发者需从零编写语音交互逻辑和记忆模块代码，导致核心业务逻辑开发时间被严重压缩。\n- **集成陷阱频发**：在尝试连接不同 AI 框架时，因缺乏标准参考示例，频繁遭遇接口不兼容和环境配置错误。\n- **学习曲线陡峭**：新入职成员难以快速理解复杂的 Agent 工作流，项目进度因人员磨合而大幅滞后。\n\n### 使用 awesome-ai-apps 后\n- **方案一键落地**：直接复用仓库中成熟的\"RAG 应用”和\"MCP Agent\"模板，半天内即可搭建出可运行的基础架构。\n- **模块即插即用**：调用现成的语音助手和记忆代理代码片段，将原本需要一周的功能开发缩短至两天。\n- **避坑指南明确**：参照 80+ 个经过验证的实战案例（Recipes），轻松解决框架集成难题，显著降低调试成本。\n- **团队协作高效**：统一的代码风格和清晰的教程视频让新人能迅速上手，全员聚焦于业务逻辑优化而非底层基建。\n\nawesome-ai-apps 通过将分散的顶尖 AI 工程实践转化为标准化的“乐高积木”，帮助团队将原型研发周期从两周缩减至三天，实现了从“摸索试错”到“快速交付”的质变。","https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FArindam200_awesome-ai-apps_904b7cdf.png","Arindam200","Arindam Majumder ","https:\u002F\u002Foss.gittoolsai.com\u002Favatars\u002FArindam200_7769edbb.png","Building @Studio1HQ ","Studio1HQ.com","India",null,"Arindam_1729","https:\u002F\u002Fwww.arindammajumder.com\u002F","https:\u002F\u002Fgithub.com\u002FArindam200",[83,87,91,95,99,103,107,110],{"name":84,"color":85,"percentage":86},"Python","#3572A5",72,{"name":88,"color":89,"percentage":90},"Jupyter Notebook","#DA5B0B",18.5,{"name":92,"color":93,"percentage":94},"TypeScript","#3178c6",4.5,{"name":96,"color":97,"percentage":98},"HTML","#e34c26",4.2,{"name":100,"color":101,"percentage":102},"Shell","#89e051",0.7,{"name":104,"color":105,"percentage":106},"Makefile","#427819",0,{"name":108,"color":109,"percentage":106},"Dockerfile","#384d54",{"name":111,"color":112,"percentage":106},"JavaScript","#f1e05a",10105,1342,"2026-04-16T00:19:31","MIT","未说明",{"notes":119,"python":117,"dependencies":120},"该仓库是一个包含 80+ 个 LLM 应用示例、教程和食谱的集合（如文本代理、语音助手、RAG 应用、MCP 工具等），而非单一的可执行软件。具体的运行环境需求（操作系统、GPU、内存、Python 版本及依赖库）取决于用户选择运行的特定子项目（例如 Agno, LangChain, CrewAI, LlamaIndex 等不同框架的示例）。建议查看各子项目目录下的独立 README 文件以获取详细的环境配置指南。",[117],[15,14,35,13],[123,124,125,126,127],"agents","ai","llm","mcp","hacktoberfest","2026-03-27T02:49:30.150509","2026-04-16T16:12:29.143404",[],[]]