[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"similar-awslabs--amazon-bedrock-agent-samples":3,"tool-awslabs--amazon-bedrock-agent-samples":64},[4,17,27,35,48,56],{"id":5,"name":6,"github_repo":7,"description_zh":8,"stars":9,"difficulty_score":10,"last_commit_at":11,"category_tags":12,"status":16},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。",162132,3,"2026-04-05T11:01:52",[13,14,15],"开发框架","图像","Agent","ready",{"id":18,"name":19,"github_repo":20,"description_zh":21,"stars":22,"difficulty_score":23,"last_commit_at":24,"category_tags":25,"status":16},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",138956,2,"2026-04-05T11:33:21",[13,15,26],"语言模型",{"id":28,"name":29,"github_repo":30,"description_zh":31,"stars":32,"difficulty_score":23,"last_commit_at":33,"category_tags":34,"status":16},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。",107662,"2026-04-03T11:11:01",[13,14,15],{"id":36,"name":37,"github_repo":38,"description_zh":39,"stars":40,"difficulty_score":23,"last_commit_at":41,"category_tags":42,"status":16},2268,"ML-For-Beginners","microsoft\u002FML-For-Beginners","ML-For-Beginners 是由微软推出的一套系统化机器学习入门课程，旨在帮助零基础用户轻松掌握经典机器学习知识。这套课程将学习路径规划为 12 周，包含 26 节精炼课程和 52 道配套测验，内容涵盖从基础概念到实际应用的完整流程，有效解决了初学者面对庞大知识体系时无从下手、缺乏结构化指导的痛点。\n\n无论是希望转型的开发者、需要补充算法背景的研究人员，还是对人工智能充满好奇的普通爱好者，都能从中受益。课程不仅提供了清晰的理论讲解，还强调动手实践，让用户在循序渐进中建立扎实的技能基础。其独特的亮点在于强大的多语言支持，通过自动化机制提供了包括简体中文在内的 50 多种语言版本，极大地降低了全球不同背景用户的学习门槛。此外，项目采用开源协作模式，社区活跃且内容持续更新，确保学习者能获取前沿且准确的技术资讯。如果你正寻找一条清晰、友好且专业的机器学习入门之路，ML-For-Beginners 将是理想的起点。",84991,"2026-04-05T10:45:23",[14,43,44,45,15,46,26,13,47],"数据工具","视频","插件","其他","音频",{"id":49,"name":50,"github_repo":51,"description_zh":52,"stars":53,"difficulty_score":10,"last_commit_at":54,"category_tags":55,"status":16},3128,"ragflow","infiniflow\u002Fragflow","RAGFlow 是一款领先的开源检索增强生成（RAG）引擎，旨在为大语言模型构建更精准、可靠的上下文层。它巧妙地将前沿的 RAG 技术与智能体（Agent）能力相结合，不仅支持从各类文档中高效提取知识，还能让模型基于这些知识进行逻辑推理和任务执行。\n\n在大模型应用中，幻觉问题和知识滞后是常见痛点。RAGFlow 通过深度解析复杂文档结构（如表格、图表及混合排版），显著提升了信息检索的准确度，从而有效减少模型“胡编乱造”的现象，确保回答既有据可依又具备时效性。其内置的智能体机制更进一步，使系统不仅能回答问题，还能自主规划步骤解决复杂问题。\n\n这款工具特别适合开发者、企业技术团队以及 AI 研究人员使用。无论是希望快速搭建私有知识库问答系统，还是致力于探索大模型在垂直领域落地的创新者，都能从中受益。RAGFlow 提供了可视化的工作流编排界面和灵活的 API 接口，既降低了非算法背景用户的上手门槛，也满足了专业开发者对系统深度定制的需求。作为基于 Apache 2.0 协议开源的项目，它正成为连接通用大模型与行业专有知识之间的重要桥梁。",77062,"2026-04-04T04:44:48",[15,14,13,26,46],{"id":57,"name":58,"github_repo":59,"description_zh":60,"stars":61,"difficulty_score":10,"last_commit_at":62,"category_tags":63,"status":16},2181,"OpenHands","OpenHands\u002FOpenHands","OpenHands 是一个专注于 AI 驱动开发的开源平台，旨在让智能体（Agent）像人类开发者一样理解、编写和调试代码。它解决了传统编程中重复性劳动多、环境配置复杂以及人机协作效率低等痛点，通过自动化流程显著提升开发速度。\n\n无论是希望提升编码效率的软件工程师、探索智能体技术的研究人员，还是需要快速原型验证的技术团队，都能从中受益。OpenHands 提供了灵活多样的使用方式：既可以通过命令行（CLI）或本地图形界面在个人电脑上轻松上手，体验类似 Devin 的流畅交互；也能利用其强大的 Python SDK 自定义智能体逻辑，甚至在云端大规模部署上千个智能体并行工作。\n\n其核心技术亮点在于模块化的软件智能体 SDK，这不仅构成了平台的引擎，还支持高度可组合的开发模式。此外，OpenHands 在 SWE-bench 基准测试中取得了 77.6% 的优异成绩，证明了其解决真实世界软件工程问题的能力。平台还具备完善的企业级功能，支持与 Slack、Jira 等工具集成，并提供细粒度的权限管理，适合从个人开发者到大型企业的各类用户场景。",70612,"2026-04-05T11:12:22",[26,15,13,45],{"id":65,"github_repo":66,"name":67,"description_en":68,"description_zh":69,"ai_summary_zh":69,"readme_en":70,"readme_zh":71,"quickstart_zh":72,"use_case_zh":73,"hero_image_url":74,"owner_login":75,"owner_name":76,"owner_avatar_url":77,"owner_bio":78,"owner_company":79,"owner_location":79,"owner_email":79,"owner_twitter":79,"owner_website":80,"owner_url":81,"languages":82,"stars":95,"forks":96,"last_commit_at":97,"license":98,"difficulty_score":10,"env_os":99,"env_gpu":99,"env_ram":99,"env_deps":100,"category_tags":104,"github_topics":105,"view_count":10,"oss_zip_url":79,"oss_zip_packed_at":79,"status":16,"created_at":112,"updated_at":113,"faqs":114,"releases":145},649,"awslabs\u002Famazon-bedrock-agent-samples","amazon-bedrock-agent-samples","Example Jupyter notebooks 📓 and code scripts 💻 for using Amazon Bedrock Agents 🤖 and its functionalities","amazon-bedrock-agent-samples 是一个开源示例仓库，汇集了用于构建 Amazon Bedrock Agents 的 Jupyter Notebook 和代码脚本。它致力于帮助技术团队快速掌握智能体开发的核心概念，解决复杂工作流自动化及多智能体协作中的落地难题。\n\n这个仓库特别适合开发者、AI 研究人员及技术架构师。通过实战案例，用户可以学习如何利用主管模式进行任务规划，或通过路由模式实现跨智能体的统一对话体验。仓库还重点展示了多智能体协作流程中的行为追踪与安全机制，特别是如何配置 Guardrails 来防御提示注入风险。\n\n值得注意的是，这里的示例主要用于实验和教育目的，并非直接的生产级代码。不过，其涵盖的最佳实践、多语言 SDK 支持以及安全建议，为将 AI 智能体从概念验证推向实际应用提供了坚实的参考基础。借助这些材料，团队能够更轻松地探索 Amazon Bedrock 的多模型能力，构建可扩展且安全的 AI 解决方案。","\u003Ch2 align=\"center\">Amazon Bedrock Agent Samples \u003C\u002Fh2>\n\u003Cp align=\"center\">\n  :wave: :wave: Welcome to the Amazon Bedrock Agent Samples repository :wave: :wave:\n\u003C\u002Fp>\n\n> [!CAUTION]\n> The examples provided in this repository are for experimental and educational purposes only. They demonstrate concepts and techniques but are not intended for direct use in production environments. Make sure to have Amazon Bedrock Guardrails in place to protect against [prompt injection](https:\u002F\u002Fdocs.aws.amazon.com\u002Fbedrock\u002Flatest\u002Fuserguide\u002Fprompt-injection.html). \n\nThis repository provides examples and best practices for working with [Amazon Bedrock Agents](https:\u002F\u002Faws.amazon.com\u002Fbedrock\u002Fagents\u002F).\n\nAmazon Bedrock Agents enables you to automate complex workflows, build robust and scalable end-to-end solutions from experimentation to production and quickly adapt to new models and experiments.\n\nWith [Amazon Bedrock multi-agent collaboration](https:\u002F\u002Fdocs.aws.amazon.com\u002Fbedrock\u002Flatest\u002Fuserguide\u002Fagents-multi-agents-collaboration.html) you can plan and execute complex tasks across agents using supervisor mode. You can also have unified conversations across agents with built-in intent classification using the supervisor with routing mode and fallback to supervisor mode when a single intention cannot be detected. Amazon Bedrock Agents provides you with traces to observe your agents' behavior across multi-agent flows and provides guardrails, security and privacy that are standard across Amazon Bedrock features.\n\n![architecture](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fawslabs_amazon-bedrock-agent-samples_readme_31d8d6298876.gif)\n\n\u003Cp align=\"center\">\n  \u003Ca href=\"\u002Fexamples\u002Fmulti_agent_collaboration\u002Fstartup_advisor_agent\u002F\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FExample-Startup_Advisor_Agent-blue\" \u002F>\u003C\u002Fa>\n\u003C\u002Fp>\n\n\u003Ch3>Demo Video\u003C\u002Fh3>\n\u003Chr \u002F>\nThis one-hour video takes you through a deep dive introduction to Amazon Bedrock multi-agent collaboration, including a pair of demos, and a walkthrough of Unifying customer experiences, and Automating complex processes. You’ll also see a customer explain their experience with multi-agent solutions.\n\n\u003Cp align=\"center\">\n  \u003Ca href=\"https:\u002F\u002Fyoutu.be\u002F7pvEYLW1yZw\">\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fawslabs_amazon-bedrock-agent-samples_readme_946759a48640.png\" \u002F>\u003C\u002Fa>\n\u003C\u002Fp>\n\n## �� Table of Contents ��\n\n- [Overview](#overview)\n- [Repository Structure](#repository-structure)\n- [Getting Started](#getting-started)\n- [Amazon Bedrock Agents examples](#agents-examples)\n- [Amazon Bedrock multi-agent collaboration examples](#multi-agent-collaboration-examples)\n- [Best Practices](#best-practices)\n- [Security](#security)\n- [License](#license)\n\n## Overview\n\nAmazon Bedrock Agents enables you to create AI-powered assistants that can perform complex tasks and interact with various APIs and services.\n\nThis repository provides practical examples to help you understand and implement agentic solutions.\n\nThe solutions presented here use the [boto3 SDK in Python](https:\u002F\u002Fboto3.amazonaws.com\u002Fv1\u002Fdocumentation\u002Fapi\u002Flatest\u002Freference\u002Fservices\u002Fbedrock-agent.html), however, you can create Bedrock Agents solutions using any of the AWS SDKs for [C++](https:\u002F\u002Fsdk.amazonaws.com\u002Fcpp\u002Fapi\u002FLATEST\u002Faws-cpp-sdk-bedrock-agent\u002Fhtml\u002Fannotated.html), [Go](https:\u002F\u002Fdocs.aws.amazon.com\u002Fsdk-for-go\u002Fapi\u002Fservice\u002Fbedrockagent\u002F), [Java](https:\u002F\u002Fsdk.amazonaws.com\u002Fjava\u002Fapi\u002Flatest\u002Fsoftware\u002Famazon\u002Fawssdk\u002Fservices\u002Fbedrockagent\u002Fpackage-summary.html), [JavaScript](https:\u002F\u002Fdocs.aws.amazon.com\u002FAWSJavaScriptSDK\u002Fv3\u002Flatest\u002Fclient\u002Fbedrock-agent\u002F), [Kotlin](https:\u002F\u002Fsdk.amazonaws.com\u002Fkotlin\u002Fapi\u002Flatest\u002Fbedrockagent\u002Findex.html), [.NET](https:\u002F\u002Fdocs.aws.amazon.com\u002Fsdkfornet\u002Fv3\u002Fapidocs\u002Fitems\u002FBedrockAgent\u002FNBedrockAgent.html), [PHP](https:\u002F\u002Fdocs.aws.amazon.com\u002Faws-sdk-php\u002Fv3\u002Fapi\u002Fnamespace-Aws.BedrockAgent.html), [Ruby](https:\u002F\u002Fdocs.aws.amazon.com\u002Fsdk-for-ruby\u002Fv3\u002Fapi\u002FAws\u002FBedrockAgent.html), [Rust](https:\u002F\u002Fdocs.rs\u002Faws-sdk-bedrockagent\u002Flatest\u002Faws_sdk_bedrockagent\u002F), [SAP ABAP](https:\u002F\u002Fdocs.aws.amazon.com\u002Fsdk-for-sap-abap\u002Fv1\u002Fapi\u002Flatest\u002Fbdr\u002Findex.html) or [Swift](https:\u002F\u002Fsdk.amazonaws.com\u002Fswift\u002Fapi\u002Fawsbedrockruntime\u002F0.34.0\u002Fdocumentation\u002Fawsbedrockruntime)\n\n\u003Cdetails>\n\u003Csummary>\n\u003Ch2>Repository Structure\u003Ch2>\n\u003C\u002Fsummary>\n\n```bash\n├── examples\u002Fagents\u002F\n│   ├── agent_with_code_interpretation\u002F\n│   ├── user_confirmation_agents\u002F\n│   ├── inline_agent\u002F\n|   └── ....\n├── examples\u002Fmulti_agent_collaboration\u002F\n│   ├── 00_hello_world_agent\u002F\n│   ├── devops_agent\u002F\n│   ├── energy_efficiency_management_agent\u002F\n|   └── ....\n├── src\u002Fshared\u002F\n│   ├── working_memory\u002F\n│   ├── stock_data\u002F\n│   ├── web_search\u002F\n|   └── ....\n├── src\u002Futils\u002F\n│   ├── bedrock_agent_helper.py\n|   ├── bedrock_agent.py\n|   ├── knowledge_base_helper.py\n|   └── ....\n```\n\n- [examples\u002Fagents\u002F](\u002Fexamples\u002Fagents\u002F): Shows Amazon Bedrock Agents examples.\n\n- [examples\u002Fmulti_agent_collaboration\u002F](\u002Fexamples\u002Fmulti_agent_collaboration\u002F): Shows Amazon Bedrock multi-agent collaboration examples.\n\n- [src\u002Fshared](\u002Fsrc\u002Fshared\u002F): This module consists of shared tools that can be reused by Amazon Bedrock Agents via Action Groups. They provide functionality like [Web Search](\u002Fsrc\u002Fshared\u002Ffile_store\u002F), [Working Memory](\u002Fsrc\u002Fshared\u002Fworking_memory\u002F), and [Stock Data Lookup](\u002Fsrc\u002Fshared\u002Fstock_data\u002F).\n\n- [src\u002Futils](\u002Fsrc\u002Futils\u002F): This module contains utilities for building and using various Amazon Bedrock features, providing a higher level of abstraction than the underlying APIs.\n\u003C\u002Fdetails>\n\n## Getting Started\n\n1. Navigate to [`src\u002F`](\u002Fsrc\u002F) for more details.\n2. To get started, navigate to the example you want to deploy in the [`examples\u002F*`](\u002Fexamples\u002F) directory.\n3. Follow the deployment steps in the `examples\u002F*\u002F*\u002FREADME.md` file of the example.\n\n## Agents examples\n\n- [Analyst assistant using Code Interpretation](\u002Fexamples\u002Fagents\u002Fagent_with_code_interpretation\u002F)\n- [Agent using Amazon Bedrock Guardrails](\u002Fexamples\u002Fagents\u002Fagent_with_guardrails_integration\u002F)\n- [Agent using Amazon Bedrock Knowledge Bases](\u002Fexamples\u002Fagents\u002Fagent_with_knowledge_base_integration\u002F)\n- [Agent with long term memory](\u002Fexamples\u002Fagents\u002Fagent_with_long_term_memory\u002F)\n- [Agent using models not yet optimized for Bedrock Agents](\u002Fexamples\u002Fagents\u002Fagent_with_models_not_yet_optimized_for_bedrock_agents\u002F)\n- [AWS CDK Agent](\u002Fexamples\u002Fagents\u002Fcdk_agent\u002F)\n- [Computer use Agent](\u002Fexamples\u002Fagents\u002Fcomputer_use\u002F)\n- [Custom orchestration Agent](\u002Fexamples\u002Fagents\u002Fcustom_orchestration_agent\u002F)\n- [Configure an inline agent at runtime](\u002Fexamples\u002Fagents\u002Finline_agent\u002F)\n- [Utilize LangChain Tools with Amazon Bedrock Inline Agents](\u002Fexamples\u002Fagents\u002Flangchain_tools_with_inline_agent\u002F)\n- [Provide conversation history to Amazon Bedrock Agents](\u002Fexamples\u002Fagents\u002Fmanage_conversation_history\u002F)\n- [Agent using OpenAPI schema](\u002Fexamples\u002Fagents\u002Fopen_api_schema_agent\u002F)\n- [Agents with user confirmation before action execution](\u002Fexamples\u002Fagents\u002Fuser_confirmation_agents\u002F)\n- [Agents with access to house security camera in cloudformation](\u002Fexamples\u002Fagents\u002Fconnected_house_agent\u002F)\n- [Agents with metadata filtering](\u002Fexamples\u002Fagents\u002Fmetadata_filtering_amazon_bedrock_agents\u002F)\n- [Agents with human_in_the_loop](\u002Fexamples\u002Fagents\u002Fhuman_in_the_loop\u002F)\n\n## Multi-agent collaboration examples\n\n- [00_hello_world_agent](\u002Fexamples\u002Fmulti_agent_collaboration\u002F00_hello_world_agent\u002F)\n- [DevOps Agent](\u002Fexamples\u002Fmulti_agent_collaboration\u002Fdevops_agent\u002F)\n- [Energy Efficiency Management Agent](\u002Fexamples\u002Fmulti_agent_collaboration\u002Fenergy_efficiency_management_agent\u002F)\n- [Assistant Agent with metadata filtering](\u002Fexamples\u002Fmulti_agent_collaboration\u002Fmetadata_filtering\u002F)\n- [Mortgage Assistant Agent](\u002Fexamples\u002Fmulti_agent_collaboration\u002Fmortgage_assistant\u002F)\n- [Portfolio Assistant Agent](\u002Fexamples\u002Fmulti_agent_collaboration\u002Fportfolio_assistant_agent\u002F)\n- [Real Estate Investment Agent](\u002Fexamples\u002Fmulti_agent_collaboration\u002Freal_estate_investment_agent\u002F)\n- [Startup Advisor Agent](\u002Fexamples\u002Fmulti_agent_collaboration\u002Fstartup_advisor_agent\u002F)\n- [Support Agent](examples\u002Fmulti_agent_collaboration\u002Fsupport_agent)\n- [Team Poems Agent](\u002Fexamples\u002Fmulti_agent_collaboration\u002Fteam_poems_agent\u002F)\n- [Trip Planner Agent](\u002Fexamples\u002Fmulti_agent_collaboration\u002Ftrip_planner_agent\u002F)\n- [Voyage Virtuso Agent](\u002Fexamples\u002Fmulti_agent_collaboration\u002Fvoyage_virtuoso_agent\u002F)\n- [Contract Assistant Agent](\u002Fexamples\u002Fmulti_agent_collaboration\u002Fcontract_assistant_agent\u002F)\n- [Financial Assitant Agent](\u002Fexamples\u002Fmulti_agent_collaboration\u002FFinancial-Analyst-Agents)\n- [Investment Research Agent](\u002Fexamples\u002Fmulti_agent_collaboration\u002Finvestment_research_agent\u002F)\n\n\n## UX Demos\n\n- [Streamlit Demo UI](\u002Fexamples\u002Fagents_ux\u002Fstreamlit_demo\u002F)\n- [Data Analyst Assistant for Video Game Sales](\u002Fexamples\u002Fagents_ux\u002Fvideo_games_sales_assistant_with_amazon_bedrock_agents\u002F)\n- [Dynamic AI Assistant Demo using Amazon Bedrock Inline Agents](\u002Fexamples\u002Fagents_ux\u002Finline-agent-hr-assistant\u002F)\n\n## Best Practices\n\nThe code samples highlighted in this repository focus on showcasing different Amazon Bedrock Agents capabilities.\n\nPlease check out our two-part blog series for best practices around building generative AI applications with Amazon Bedrock Agents:\n\n- [Best practices for building robust generative AI applications with Amazon Bedrock Agents – Part 1](https:\u002F\u002Faws.amazon.com\u002Fblogs\u002Fmachine-learning\u002Fbest-practices-for-building-robust-generative-ai-applications-with-amazon-bedrock-agents-part-1\u002F)\n- [Best practices for building robust generative AI applications with Amazon Bedrock Agents – Part 2](https:\u002F\u002Faws.amazon.com\u002Fblogs\u002Fmachine-learning\u002Fbest-practices-for-building-robust-generative-ai-applications-with-amazon-bedrock-agents-part-2\u002F)\n\nUnderstand Bedrock Multi-agents Collaboration concepts by reading our [blog post](https:\u002F\u002Faws.amazon.com\u002Fblogs\u002Fmachine-learning\u002Funlocking-complex-problem-solving-with-multi-agent-collaboration-on-amazon-bedrock\u002F) written by Bedrock Agent's science team\n\n🔗 **Related Links**:\n\n- [Amazon Bedrock Agents Documentation](https:\u002F\u002Fdocs.aws.amazon.com\u002Fbedrock\u002Flatest\u002Fuserguide\u002Fagents.html)\n- [Amazon Bedrock multi-agent collaboration](https:\u002F\u002Fdocs.aws.amazon.com\u002Fbedrock\u002Flatest\u002Fuserguide\u002Fagents-multi-agents-collaboration.html)\n- [Boto3 Python SDK Documentation](https:\u002F\u002Fboto3.amazonaws.com\u002Fv1\u002Fdocumentation\u002Fapi\u002Flatest\u002Freference\u002Fservices\u002Fbedrock-agent.html)\n- [Amazon Bedrock Samples](https:\u002F\u002Fgithub.com\u002Faws-samples\u002Famazon-bedrock-samples\u002Ftree\u002Fmain)\n\n## Security\n\nSee [CONTRIBUTING](CONTRIBUTING.md#security-issue-notifications) for more information.\n\n## License\n\nThis project is licensed under the Apache-2.0 License.\n\n> [!IMPORTANT]\n> Examples in this repository are for demonstration purposes.\n> Ensure proper security and testing when deploying to production environments.\n\n## Contributors :muscle:\n\n\u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fawslabs\u002Famazon-bedrock-agent-samples\u002Fgraphs\u002Fcontributors\">\n  \u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fawslabs_amazon-bedrock-agent-samples_readme_5dcfa766bc00.png\" \u002F>\n\u003C\u002Fa>\n\n## Stargazers :star:\n\n[![Stargazers repo roster for @awslabs\u002Famazon-bedrock-agent-samples](https:\u002F\u002Freporoster.com\u002Fstars\u002Fawslabs\u002Famazon-bedrock-agent-samples)](https:\u002F\u002Fgithub.com\u002Fawslabs\u002Famazon-bedrock-agent-samples\u002Fstargazers)\n\n## Forkers :raised_hands:\n\n[![Forkers repo roster for @awslabs\u002Famazon-bedrock-agent-samples](https:\u002F\u002Freporoster.com\u002Fforks\u002Fawslabs\u002Famazon-bedrock-agent-samples)](https:\u002F\u002Fgithub.com\u002Fawslabs\u002Famazon-bedrock-agent-samples\u002Fnetwork\u002Fmembers)\n","\u003Ch2 align=\"center\">Amazon Bedrock Agent 示例 \u003C\u002Fh2>\n\u003Cp align=\"center\">\n  :wave: :wave: 欢迎加入 Amazon Bedrock Agent 示例仓库 :wave: :wave:\n\u003C\u002Fp>\n\n> [!CAUTION]\n> 本仓库提供的示例仅供实验和教育用途。它们展示了概念和技术，但不打算直接用于生产环境。请确保已实施 Amazon Bedrock Guardrails（护栏），以防止 [prompt injection](https:\u002F\u002Fdocs.aws.amazon.com\u002Fbedrock\u002Flatest\u002Fuserguide\u002Fprompt-injection.html)（提示注入）。 \n\n本仓库提供了关于使用 [Amazon Bedrock Agents](https:\u002F\u002Faws.amazon.com\u002Fbedrock\u002Fagents\u002F) 的示例和最佳实践。\n\nAmazon Bedrock Agents 使您能够自动化复杂的工作流，从实验到生产构建稳健且可扩展的端到端解决方案，并快速适应新模型和实验。\n\n借助 [Amazon Bedrock 多智能体协作](https:\u002F\u002Fdocs.aws.amazon.com\u002Fbedrock\u002Flatest\u002Fuserguide\u002Fagents-multi-agents-collaboration.html)，您可以使用主管模式（supervisor mode）跨智能体规划和执行复杂任务。您还可以使用带有路由模式（routing mode）的主管进行内置意图分类，实现跨智能体的统一对话，并在无法检测到单一意图时回退到主管模式。Amazon Bedrock Agents 为您提供跟踪（traces）功能，以观察智能体在多智能体流程中的行为，并提供 Amazon Bedrock 功能标准的护栏、安全和隐私保护。\n\n![架构](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fawslabs_amazon-bedrock-agent-samples_readme_31d8d6298876.gif)\n\n\u003Cp align=\"center\">\n  \u003Ca href=\"\u002Fexamples\u002Fmulti_agent_collaboration\u002Fstartup_advisor_agent\u002F\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FExample-Startup_Advisor_Agent-blue\" \u002F>\u003C\u002Fa>\n\u003C\u002Fp>\n\n\u003Ch3>演示视频\u003C\u002Fh3>\n\u003Chr \u002F>\n这段一小时的视频深入介绍了 Amazon Bedrock 多智能体协作，包括两个演示，以及“统一客户体验”和“自动化复杂流程”的分步指南。您还将看到一位客户解释他们使用多智能体解决方案的体验。\n\n\u003Cp align=\"center\">\n  \u003Ca href=\"https:\u002F\u002Fyoutu.be\u002F7pvEYLW1yZw\">\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fawslabs_amazon-bedrock-agent-samples_readme_946759a48640.png\" \u002F>\u003C\u002Fa>\n\u003C\u002Fp>\n\n## 📑 目录\n\n- [概述](#overview)\n- [仓库结构](#repository-structure)\n- [入门指南](#getting-started)\n- [Amazon Bedrock Agents 示例](#agents-examples)\n- [Amazon Bedrock 多智能体协作示例](#multi-agent-collaboration-examples)\n- [最佳实践](#best-practices)\n- [安全](#security)\n- [许可证](#license)\n\n## 概述\n\nAmazon Bedrock Agents 使您能够创建 AI 驱动的智能助手，这些助手可以执行复杂任务并与各种 API（应用程序编程接口）和服务进行交互。\n\n本仓库提供实用示例，帮助您理解和实现智能体解决方案。\n\n此处展示的解决方案使用 [Python 中的 boto3 SDK（软件开发工具包）](https:\u002F\u002Fboto3.amazonaws.com\u002Fv1\u002Fdocumentation\u002Fapi\u002Flatest\u002Freference\u002Fservices\u002Fbedrock-agent.html)，不过，您也可以使用适用于 [C++](https:\u002F\u002Fsdk.amazonaws.com\u002Fcpp\u002Fapi\u002FLATEST\u002Faws-cpp-sdk-bedrock-agent\u002Fhtml\u002Fannotated.html)、[Go](https:\u002F\u002Fdocs.aws.amazon.com\u002Fsdk-for-go\u002Fapi\u002Fservice\u002Fbedrockagent\u002F)、[Java](https:\u002F\u002Fsdk.amazonaws.com\u002Fjava\u002Fapi\u002Flatest\u002Fsoftware\u002Famazon\u002Fawssdk\u002Fservices\u002Fbedrockagent\u002Fpackage-summary.html)、[JavaScript](https:\u002F\u002Fdocs.aws.amazon.com\u002FAWSJavaScriptSDK\u002Fv3\u002Flatest\u002Fclient\u002Fbedrock-agent\u002F)、[Kotlin](https:\u002F\u002Fsdk.amazonaws.com\u002Fkotlin\u002Fapi\u002Flatest\u002Fbedrockagent\u002Findex.html)、[.NET](https:\u002F\u002Fdocs.aws.amazon.com\u002Fsdkfornet\u002Fv3\u002Fapidocs\u002Fitems\u002FBedrockAgent\u002FNBedrockAgent.html)、[PHP](https:\u002F\u002Fdocs.aws.amazon.com\u002Faws-sdk-php\u002Fv3\u002Fapi\u002Fnamespace-Aws.BedrockAgent.html)、[Ruby](https:\u002F\u002Fdocs.aws.amazon.com\u002Fsdk-for-ruby\u002Fv3\u002Fapi\u002FAws\u002FBedrockAgent.html)、[Rust](https:\u002F\u002Fdocs.rs\u002Faws-sdk-bedrockagent\u002Flatest\u002Faws_sdk_bedrockagent\u002F)、[SAP ABAP](https:\u002F\u002Fdocs.aws.amazon.com\u002Fsdk-for-sap-abap\u002Fv1\u002Fapi\u002Flatest\u002Fbdr\u002Findex.html) 或 [Swift](https:\u002F\u002Fsdk.amazonaws.com\u002Fswift\u002Fapi\u002Fawsbedrockruntime\u002F0.34.0\u002Fdocumentation\u002Fawsbedrockruntime) 的任何 AWS SDK（AWS 软件开发工具包）来创建 Bedrock Agents 解决方案。\n\n\u003Cdetails>\n\u003Csummary>\n\u003Ch2>仓库结构\u003C\u002Fh2>\n\u003C\u002Fsummary>\n\n```bash\n├── examples\u002Fagents\u002F\n│   ├── agent_with_code_interpretation\u002F\n│   ├── user_confirmation_agents\u002F\n│   ├── inline_agent\u002F\n|   └── ....\n├── examples\u002Fmulti_agent_collaboration\u002F\n│   ├── 00_hello_world_agent\u002F\n│   ├── devops_agent\u002F\n│   ├── energy_efficiency_management_agent\u002F\n|   └── ....\n├── src\u002Fshared\u002F\n│   ├── working_memory\u002F\n│   ├── stock_data\u002F\n│   ├── web_search\u002F\n|   └── ....\n├── src\u002Futils\u002F\n│   ├── bedrock_agent_helper.py\n|   ├── bedrock_agent.py\n|   ├── knowledge_base_helper.py\n|   └── ....\n```\n\n- [examples\u002Fagents\u002F](\u002Fexamples\u002Fagents\u002F): 展示 Amazon Bedrock Agents 示例。\n\n- [examples\u002Fmulti_agent_collaboration\u002F](\u002Fexamples\u002Fmulti_agent_collaboration\u002F): 展示 Amazon Bedrock 多智能体协作示例。\n\n- [src\u002Fshared](\u002Fsrc\u002Fshared\u002F): 此模块包含可通过 Action Groups（操作组）由 Amazon Bedrock Agents 复用的共享工具。它们提供如 [Web Search](\u002Fsrc\u002Fshared\u002Ffile_store\u002F)（网页搜索）、[Working Memory](\u002Fsrc\u002Fshared\u002Fworking_memory\u002F)（工作记忆）和 [Stock Data Lookup](\u002Fsrc\u002Fshared\u002Fstock_data\u002F)（股票数据查询）等功能。\n\n- [src\u002Futils](\u002Fsrc\u002Futils\u002F): 此模块包含用于构建和使用各种 Amazon Bedrock 功能的工具，提供了比底层 API 更高级别的抽象。\n\u003C\u002Fdetails>\n\n## 入门指南\n\n1. 导航至 [`src\u002F`](\u002Fsrc\u002F) 以获取更多信息。\n2. 开始之前，请在 [`examples\u002F*`](\u002Fexamples\u002F) 目录中导航到您要部署的示例。\n3. 遵循示例的 `examples\u002F*\u002F*\u002FREADME.md` 文件中的部署步骤。\n\n## 智能体 (Agents) 示例\n\n- [使用代码解释 (Code Interpretation) 功能的分析师助手](\u002Fexamples\u002Fagents\u002Fagent_with_code_interpretation\u002F)\n- [使用 Amazon Bedrock 护栏 (Guardrails) 的智能体](\u002Fexamples\u002Fagents\u002Fagent_with_guardrails_integration\u002F)\n- [使用 Amazon Bedrock 知识库 (Knowledge Bases) 的智能体](\u002Fexamples\u002Fagents\u002Fagent_with_knowledge_base_integration\u002F)\n- [具有长期记忆 (long term memory) 的智能体](\u002Fexamples\u002Fagents\u002Fagent_with_long_term_memory\u002F)\n- [使用尚未针对 Bedrock Agents 优化的模型的智能体](\u002Fexamples\u002Fagents\u002Fagent_with_models_not_yet_optimized_for_bedrock_agents\u002F)\n- [AWS 云开发套件 (CDK) 智能体](\u002Fexamples\u002Fagents\u002Fcdk_agent\u002F)\n- [计算机操作 (Computer Use) 智能体](\u002Fexamples\u002Fagents\u002Fcomputer_use\u002F)\n- [自定义编排 (Orchestration) 智能体](\u002Fexamples\u002Fagents\u002Fcustom_orchestration_agent\u002F)\n- [在运行时配置内联智能体 (Inline Agent)](\u002Fexamples\u002Fagents\u002Finline_agent\u002F)\n- [结合 Amazon Bedrock 内联智能体 (Inline Agents) 使用 LangChain 工具](\u002Fexamples\u002Fagents\u002Flangchain_tools_with_inline_agent\u002F)\n- [向 Amazon Bedrock 智能体提供对话历史](\u002Fexamples\u002Fagents\u002Fmanage_conversation_history\u002F)\n- [使用 OpenAPI 模式 (Schema) 的智能体](\u002Fexamples\u002Fagents\u002Fopen_api_schema_agent\u002F)\n- [在执行操作前需要用户确认的智能体](\u002Fexamples\u002Fagents\u002Fuser_confirmation_agents\u002F)\n- [通过 CloudFormation 访问家庭安防摄像头的智能体](\u002Fexamples\u002Fagents\u002Fconnected_house_agent\u002F)\n- [具有元数据过滤 (Metadata Filtering) 功能的智能体](\u002Fexamples\u002Fagents\u002Fmetadata_filtering_amazon_bedrock_agents\u002F)\n- [具备人工介入 (human_in_the_loop) 功能的智能体](\u002Fexamples\u002Fagents\u002Fhuman_in_the_loop\u002F)\n\n## 多智能体 (Multi-agent) 协作示例\n\n- [00_hello_world_agent](\u002Fexamples\u002Fmulti_agent_collaboration\u002F00_hello_world_agent\u002F)\n- [DevOps 智能体](\u002Fexamples\u002Fmulti_agent_collaboration\u002Fdevops_agent\u002F)\n- [能源效率管理智能体](\u002Fexamples\u002Fmulti_agent_collaboration\u002Fenergy_efficiency_management_agent\u002F)\n- [具有元数据过滤功能的助理智能体](\u002Fexamples\u002Fmulti_agent_collaboration\u002Fmetadata_filtering\u002F)\n- [抵押贷款助理智能体](\u002Fexamples\u002Fmulti_agent_collaboration\u002Fmortgage_assistant\u002F)\n- [投资组合助理智能体](\u002Fexamples\u002Fmulti_agent_collaboration\u002Fportfolio_assistant_agent\u002F)\n- [房地产投资智能体](\u002Fexamples\u002Fmulti_agent_collaboration\u002Freal_estate_investment_agent\u002F)\n- [初创企业顾问智能体](\u002Fexamples\u002Fmulti_agent_collaboration\u002Fstartup_advisor_agent\u002F)\n- [支持智能体](examples\u002Fmulti_agent_collaboration\u002Fsupport_agent)\n- [团队诗歌智能体](\u002Fexamples\u002Fmulti_agent_collaboration\u002Fteam_poems_agent\u002F)\n- [旅行规划智能体](\u002Fexamples\u002Fmulti_agent_collaboration\u002Ftrip_planner_agent\u002F)\n- [旅行专家智能体](\u002Fexamples\u002Fmulti_agent_collaboration\u002Fvoyage_virtuoso_agent\u002F)\n- [合同助理智能体](\u002Fexamples\u002Fmulti_agent_collaboration\u002Fcontract_assistant_agent\u002F)\n- [财务分析智能体](\u002Fexamples\u002Fmulti_agent_collaboration\u002FFinancial-Analyst-Agents)\n- [投资研究智能体](\u002Fexamples\u002Fmulti_agent_collaboration\u002Finvestment_research_agent\u002F)\n\n\n## 用户体验演示\n\n- [Streamlit 演示 UI](\u002Fexamples\u002Fagents_ux\u002Fstreamlit_demo\u002F)\n- [用于视频游戏销售的数据分析师助理](\u002Fexamples\u002Fagents_ux\u002Fvideo_games_sales_assistant_with_amazon_bedrock_agents\u002F)\n- [使用 Amazon Bedrock 内联智能体的动态 AI 助理演示](\u002Fexamples\u002Fagents_ux\u002Finline-agent-hr-assistant\u002F)\n\n## 最佳实践\n\n本仓库中高亮显示的代码示例旨在展示不同的 Amazon Bedrock 智能体 (Agents) 功能。\n\n请查看我们关于使用 Amazon Bedrock 智能体构建生成式 AI (generative AI) 应用的最佳实践的系列博客文章（共两部分）：\n\n- [使用 Amazon Bedrock 智能体构建稳健的生成式 AI 应用的最佳实践 – 第 1 部分](https:\u002F\u002Faws.amazon.com\u002Fblogs\u002Fmachine-learning\u002Fbest-practices-for-building-robust-generative-ai-applications-with-amazon-bedrock-agents-part-1\u002F)\n- [使用 Amazon Bedrock 智能体构建稳健的生成式 AI 应用的最佳实践 – 第 2 部分](https:\u002F\u002Faws.amazon.com\u002Fblogs\u002Fmachine-learning\u002Fbest-practices-for-building-robust-generative-ai-applications-with-amazon-bedrock-agents-part-2\u002F)\n\n通过阅读 Bedrock 智能体科学团队撰写的 [博客文章](https:\u002F\u002Faws.amazon.com\u002Fblogs\u002Fmachine-learning\u002Funlocking-complex-problem-solving-with-multi-agent-collaboration-on-amazon-bedrock\u002F)，了解 Bedrock 多智能体协作概念\n\n🔗 **相关链接**:\n\n- [Amazon Bedrock 智能体文档](https:\u002F\u002Fdocs.aws.amazon.com\u002Fbedrock\u002Flatest\u002Fuserguide\u002Fagents.html)\n- [Amazon Bedrock 多智能体协作](https:\u002F\u002Fdocs.aws.amazon.com\u002Fbedrock\u002Flatest\u002Fuserguide\u002Fagents-multi-agents-collaboration.html)\n- [Boto3 Python SDK 文档](https:\u002F\u002Fboto3.amazonaws.com\u002Fv1\u002Fdocumentation\u002Fapi\u002Flatest\u002Freference\u002Fservices\u002Fbedrock-agent.html)\n- [Amazon Bedrock 示例](https:\u002F\u002Fgithub.com\u002Faws-samples\u002Famazon-bedrock-samples\u002Ftree\u002Fmain)\n\n## 安全性\n\n有关更多信息，请参阅 [贡献指南](CONTRIBUTING.md#security-issue-notifications)。\n\n## 许可证\n\n本项目采用 Apache-2.0 许可证进行授权。\n\n> [!IMPORTANT]\n> 本仓库中的示例仅供演示目的。\n> 在生产环境部署时，请确保采取适当的安全措施和测试。\n\n## 贡献者 :muscle:\n\n\u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fawslabs\u002Famazon-bedrock-agent-samples\u002Fgraphs\u002Fcontributors\">\n  \u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fawslabs_amazon-bedrock-agent-samples_readme_5dcfa766bc00.png\" \u002F>\n\u003C\u002Fa>\n\n## 星标用户 :star:\n\n[![Stargazers repo roster for @awslabs\u002Famazon-bedrock-agent-samples](https:\u002F\u002Freporoster.com\u002Fstars\u002Fawslabs\u002Famazon-bedrock-agent-samples)](https:\u002F\u002Fgithub.com\u002Fawslabs\u002Famazon-bedrock-agent-samples\u002Fstargazers)\n\n## 分叉用户 :raised_hands:\n\n[![Forkers repo roster for @awslabs\u002Famazon-bedrock-agent-samples](https:\u002F\u002Freporoster.com\u002Fforks\u002Fawslabs\u002Famazon-bedrock-agent-samples)](https:\u002F\u002Fgithub.com\u002Fawslabs\u002Famazon-bedrock-agent-samples\u002Fnetwork\u002Fmembers)","# Amazon Bedrock Agent Samples 快速上手指南\n\n本仓库提供了 Amazon Bedrock Agents 的示例代码和最佳实践，旨在帮助您理解并实现智能体解决方案。支持单代理工作流及多代理协作（Multi-Agent Collaboration），主要基于 Python (boto3) SDK 开发。\n\n> [!CAUTION] 安全警告\n> 仓库中的示例仅供实验和教育目的，**不建议直接用于生产环境**。在生产环境中部署前，请务必启用 Amazon Bedrock Guardrails 以防止提示词注入等安全风险。\n\n## 环境准备\n\n在开始之前，请确保您的本地环境满足以下要求：\n\n1.  **AWS 账户**：拥有有效的 AWS 账户，并已开通 Amazon Bedrock 服务权限。\n2.  **编程语言**：安装 Python 3.8 或更高版本。\n3.  **AWS 配置**：已安装并配置好 AWS CLI，确保 `~\u002F.aws\u002Fcredentials` 文件中有正确的访问密钥。\n4.  **区域选择**：确认您选择的 AWS 区域支持 Bedrock 服务（如 `us-east-1`, `ap-northeast-1` 等）。\n5.  **依赖库**：主要依赖 `boto3` SDK。\n\n## 安装步骤\n\n1.  **克隆仓库**\n    将项目克隆到本地：\n    ```bash\n    git clone https:\u002F\u002Fgithub.com\u002Fawslabs\u002Famazon-bedrock-agent-samples.git\n    ```\n\n2.  **进入目录**\n    切换到项目根目录：\n    ```bash\n    cd amazon-bedrock-agent-samples\n    ```\n\n3.  **安装依赖**\n    根据具体示例的不同，依赖可能有所差异。通常需要在示例目录下安装所需的 Python 包（例如 boto3）：\n    ```bash\n    pip install boto3\n    ```\n    *注：部分复杂示例可能在 `requirements.txt` 中列出了特定依赖，请参考对应示例文件夹内的说明。*\n\n## 基本使用\n\n本项目结构清晰，主要分为单代理示例和多代理协作示例。\n\n### 1. 选择示例\n浏览 `examples\u002F` 目录下的子文件夹以选择合适的场景：\n- **单代理示例**：位于 `examples\u002Fagents\u002F`，例如代码解释、知识库集成等。\n- **多代理协作示例**：位于 `examples\u002Fmulti_agent_collaboration\u002F`，例如 DevOps 助手、创业顾问等。\n\n### 2. 查看部署说明\n每个示例文件夹内都包含独立的 `README.md` 文件，其中详细说明了该特定场景的部署步骤和环境配置要求。\n```bash\n# 示例：进入一个具体的代理示例目录\ncd examples\u002Fagents\u002Fagent_with_code_interpretation\u002F\ncat README.md\n```\n\n### 3. 运行脚本\n按照示例说明完成资源创建（如 CloudFormation 模板）后，运行提供的 Python 脚本来测试交互：\n```bash\npython your_script_name.py\n```\n\n### 4. 多代理协作\n若需体验多智能体协作功能，可参考 `examples\u002Fmulti_agent_collaboration\u002F` 下的教程。通过 Supervisor 模式，您可以规划跨代理的复杂任务，并利用内置意图分类进行路由。\n\n## 最佳实践与安全建议\n\n- **生产环境防护**：务必为 Agent 配置 Guardrails，保护系统免受恶意输入影响。\n- **代码复用**：共享工具模块位于 `src\u002Fshared\u002F`，包含 Web 搜索、工作记忆等功能，可在构建时复用。\n- **文档参考**：\n  - [Amazon Bedrock Agents 文档](https:\u002F\u002Fdocs.aws.amazon.com\u002Fbedrock\u002Flatest\u002Fuserguide\u002Fagents.html)\n  - [多智能体协作概念](https:\u002F\u002Fdocs.aws.amazon.com\u002Fbedrock\u002Flatest\u002Fuserguide\u002Fagents-multi-agents-collaboration.html)\n  - [最佳实践博客系列](https:\u002F\u002Faws.amazon.com\u002Fblogs\u002Fmachine-learning\u002F)","某金融科技初创团队正在开发智能客服系统，需要处理复杂的账户查询与交易风控任务，同时要求高安全性。\n\n### 没有 amazon-bedrock-agent-samples 时\n- 团队需从零编写 Agent 编排逻辑，手动对接多个 API，耗时且容易在集成环节出错。\n- 面对复杂意图时无法自动分发任务，导致单一模型难以兼顾账户查询与风控判断的准确性。\n- 缺乏成熟的安全防护机制，开发者需自行研究如何防止提示词注入攻击，存在数据泄露风险。\n- 调试多步骤工作流极其困难，没有可视化的追踪手段，难以定位 Agent 决策失败的具体原因。\n\n### 使用 amazon-bedrock-agent-samples 后\n- 直接复用仓库中的 Jupyter Notebook 示例，快速搭建起包含权限验证的基础 Agent 框架。\n- 利用多 Agent 协作模式，自动将简单咨询路由给客服助手，复杂风控请求转交专家模型协同处理。\n- 集成官方推荐的 Guardrails 配置，有效拦截恶意输入，无需重复造轮子即可保障数据安全。\n- 通过内置的追踪功能，轻松监控 Agent 在多步任务中的行为路径，显著缩短排查问题的时间。\n\n这套方案不仅加速了原型验证，更为企业级 AI 应用提供了经过验证的安全架构与最佳实践。","https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fawslabs_amazon-bedrock-agent-samples_9ad206b9.png","awslabs","Amazon Web Services - Labs","https:\u002F\u002Foss.gittoolsai.com\u002Favatars\u002Fawslabs_9e60acf8.png","AWS Labs",null,"http:\u002F\u002Famazon.com\u002Faws\u002F","https:\u002F\u002Fgithub.com\u002Fawslabs",[83,87,91],{"name":84,"color":85,"percentage":86},"Python","#3572A5",99.9,{"name":88,"color":89,"percentage":90},"Makefile","#427819",0.1,{"name":92,"color":93,"percentage":94},"Dockerfile","#384d54",0,789,268,"2026-04-01T20:54:12","Apache-2.0","未说明",{"notes":101,"python":99,"dependencies":102},"本工具为 Amazon Bedrock 客户端示例代码库，核心功能依赖 AWS 云服务而非本地计算。运行需要有效的 AWS 账户、IAM 权限及网络连接。主要使用 Python boto3 SDK 调用 API，部分示例涉及 AWS CDK 或 Streamlit UI，可能需额外环境支持。代码仅供实验和教育用途，生产环境需配置安全策略。",[103],"boto3",[15],[106,107,108,109,110,111],"bedrock-agents","multi-agents-collaboration","amazon-bedrock","amazon-bedrock-agents","bedrock","generative-ai","2026-03-27T02:49:30.150509","2026-04-06T07:13:03.430734",[115,120,125,130,135,140],{"id":116,"question_zh":117,"answer_zh":118,"source_url":119},2685,"运行 SAM 部署时提示找不到配置文件或凭证无效怎么办？","维护者指出 `sam deploy --guided` 会自动创建 toml 配置文件。如果遇到凭证无效错误，请验证本地凭证。如果使用用户密钥配置 AWS CLI，请确保 `~\u002F.aws\u002Fcredentials` 文件中没有 token 行。","https:\u002F\u002Fgithub.com\u002Fawslabs\u002Famazon-bedrock-agent-samples\u002Fissues\u002F70",{"id":121,"question_zh":122,"answer_zh":123,"source_url":124},2686,"运行示例时报错缺少 'retrying' 模块如何解决？","维护者已提交修复。临时解决方案是手动安装该模块：执行 `pip install retrying`，然后更新依赖列表：`pip freeze > src\u002Frequirements.txt`。","https:\u002F\u002Fgithub.com\u002Fawslabs\u002Famazon-bedrock-agent-samples\u002Fissues\u002F7",{"id":126,"question_zh":127,"answer_zh":128,"source_url":129},2687,"Mortgages 示例中缺少资源清理功能怎么办？","维护者已提交修复以解决此问题。建议检查最新代码库以确保包含完整的清理脚本，或在测试完成后参考相关文档进行资源清理。","https:\u002F\u002Fgithub.com\u002Fawslabs\u002Famazon-bedrock-agent-samples\u002Fissues\u002F8",{"id":131,"question_zh":132,"answer_zh":133,"source_url":134},2688,"部署 ComputerUseAwsEnvironmentService 时报错找不到 entrypoint.sh 文件怎么办？","这是一个环境特定问题。维护者建议检查 Python 版本及安装的包。请使用 `pip freeze > requirements.txt` 分享你的环境信息以便排查。","https:\u002F\u002Fgithub.com\u002Fawslabs\u002Famazon-bedrock-agent-samples\u002Fissues\u002F131",{"id":136,"question_zh":137,"answer_zh":138,"source_url":139},2689,"运行 startup_advisor_agent 时遇到 \"max iterations exceeded\" 错误如何处理？","维护者建议重新运行查询以确认问题是否持续。如果是特定命令导致，请检查传入的参数（如 web_domain, project 描述）是否过于复杂导致模型无法在限制内完成。","https:\u002F\u002Fgithub.com\u002Fawslabs\u002Famazon-bedrock-agent-samples\u002Fissues\u002F26",{"id":141,"question_zh":142,"answer_zh":143,"source_url":144},2690,"使用 Sonnet 模型运行 Sports Team Poet Agent 时出现异常怎么办？","此错误可能与区域（Region）有关。维护者建议提供你遇到错误的 AWS 区域，以便进行复现和测试。","https:\u002F\u002Fgithub.com\u002Fawslabs\u002Famazon-bedrock-agent-samples\u002Fissues\u002F36",[]]