[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"similar-k8sgpt-ai--k8sgpt":3,"tool-k8sgpt-ai--k8sgpt":64},[4,17,27,35,43,56],{"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},3704,"NextChat","ChatGPTNextWeb\u002FNextChat","NextChat 是一款轻量且极速的 AI 助手，旨在为用户提供流畅、跨平台的大模型交互体验。它完美解决了用户在多设备间切换时难以保持对话连续性，以及面对众多 AI 模型不知如何统一管理的痛点。无论是日常办公、学习辅助还是创意激发，NextChat 都能让用户随时随地通过网页、iOS、Android、Windows、MacOS 或 Linux 端无缝接入智能服务。\n\n这款工具非常适合普通用户、学生、职场人士以及需要私有化部署的企业团队使用。对于开发者而言，它也提供了便捷的自托管方案，支持一键部署到 Vercel 或 Zeabur 等平台。\n\nNextChat 的核心亮点在于其广泛的模型兼容性，原生支持 Claude、DeepSeek、GPT-4 及 Gemini Pro 等主流大模型，让用户在一个界面即可自由切换不同 AI 能力。此外，它还率先支持 MCP（Model Context Protocol）协议，增强了上下文处理能力。针对企业用户，NextChat 提供专业版解决方案，具备品牌定制、细粒度权限控制、内部知识库整合及安全审计等功能，满足公司对数据隐私和个性化管理的高标准要求。",87618,"2026-04-05T07:20:52",[13,26],{"id":44,"name":45,"github_repo":46,"description_zh":47,"stars":48,"difficulty_score":23,"last_commit_at":49,"category_tags":50,"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",[14,51,52,53,15,54,26,13,55],"数据工具","视频","插件","其他","音频",{"id":57,"name":58,"github_repo":59,"description_zh":60,"stars":61,"difficulty_score":10,"last_commit_at":62,"category_tags":63,"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",[15,14,13,26,54],{"id":65,"github_repo":66,"name":67,"description_en":68,"description_zh":69,"ai_summary_zh":70,"readme_en":71,"readme_zh":72,"quickstart_zh":73,"use_case_zh":74,"hero_image_url":75,"owner_login":76,"owner_name":67,"owner_avatar_url":77,"owner_bio":78,"owner_company":79,"owner_location":79,"owner_email":79,"owner_twitter":67,"owner_website":80,"owner_url":81,"languages":82,"stars":97,"forks":98,"last_commit_at":99,"license":100,"difficulty_score":23,"env_os":101,"env_gpu":102,"env_ram":102,"env_deps":103,"category_tags":109,"github_topics":110,"view_count":23,"oss_zip_url":79,"oss_zip_packed_at":79,"status":16,"created_at":118,"updated_at":119,"faqs":120,"releases":151},2461,"k8sgpt-ai\u002Fk8sgpt","k8sgpt","Giving Kubernetes Superpowers to everyone","k8sgpt 是一款专为 Kubernetes 用户打造的智能诊断助手，旨在让复杂的集群管理变得简单直观。它的核心理念是“赋予每个人驾驭 Kubernetes 的超能力”，通过结合人工智能技术，将原本晦涩难懂的集群错误信息转化为通俗易懂的自然语言描述。\n\n在日常运维中，Kubernetes 的报错信息往往复杂且分散，排查问题需要深厚的专业知识和大量时间。k8sgpt 正是为了解决这一痛点而生。它能够自动扫描你的 Kubernetes 集群，精准定位潜在问题，并利用内置的分析器提取关键信息。这些分析器凝聚了资深站点可靠性工程师（SRE）的实战经验，能够确保诊断的专业性和准确性。随后，k8sgpt 会调用 AI 模型对信息进行深度加工，最终用简单的英语（未来支持更多语言）给出清晰的解释和修复建议，极大地降低了故障排查的门槛。\n\n在技术架构上，k8sgpt 展现了极佳的灵活性与开放性。它支持多种主流的大语言模型后端，包括 OpenAI、Azure、Cohere、Amazon Bedrock、Google Gemini 以及本地部署的模型，用户可以根据自身的数据安全需求和成本预算自由选择。此外","k8sgpt 是一款专为 Kubernetes 用户打造的智能诊断助手，旨在让复杂的集群管理变得简单直观。它的核心理念是“赋予每个人驾驭 Kubernetes 的超能力”，通过结合人工智能技术，将原本晦涩难懂的集群错误信息转化为通俗易懂的自然语言描述。\n\n在日常运维中，Kubernetes 的报错信息往往复杂且分散，排查问题需要深厚的专业知识和大量时间。k8sgpt 正是为了解决这一痛点而生。它能够自动扫描你的 Kubernetes 集群，精准定位潜在问题，并利用内置的分析器提取关键信息。这些分析器凝聚了资深站点可靠性工程师（SRE）的实战经验，能够确保诊断的专业性和准确性。随后，k8sgpt 会调用 AI 模型对信息进行深度加工，最终用简单的英语（未来支持更多语言）给出清晰的解释和修复建议，极大地降低了故障排查的门槛。\n\n在技术架构上，k8sgpt 展现了极佳的灵活性与开放性。它支持多种主流的大语言模型后端，包括 OpenAI、Azure、Cohere、Amazon Bedrock、Google Gemini 以及本地部署的模型，用户可以根据自身的数据安全需求和成本预算自由选择。此外，它还遵循开源最佳实践，拥有活跃的社区支持。\n\n这款工具非常适合各类与 Kubernetes 打交道的用户，无论是正在学习容器技术的开发者、需要高效运维的 SRE 工程师，还是希望降低团队运维成本的技术管理者。如果你正被 Kubernetes 的复杂配置和报错困扰，k8sgpt 将成为你得力的智能伙伴，帮助你快速从“救火”模式中解脱出来，专注于更有价值的业务创新。","\u003Cpicture>\n  \u003Csource media=\"(prefers-color-scheme: dark)\" srcset=\".\u002Fimages\u002Fbanner-white.png\" width=\"600px;\">\n  \u003Cimg alt=\"Text changing depending on mode. Light: 'So light!' Dark: 'So dark!'\" src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fk8sgpt-ai_k8sgpt_readme_4cd852d3f9aa.png\" width=\"600px;\">\n\u003C\u002Fpicture>\n\u003Cbr\u002F>\n\n![GitHub code size in bytes](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flanguages\u002Fcode-size\u002Fk8sgpt-ai\u002Fk8sgpt)\n![GitHub Workflow Status](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Factions\u002Fworkflow\u002Fstatus\u002Fk8sgpt-ai\u002Fk8sgpt\u002Frelease.yaml)\n![GitHub release (latest by date)](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fv\u002Frelease\u002Fk8sgpt-ai\u002Fk8sgpt)\n[![OpenSSF Best Practices](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fk8sgpt-ai_k8sgpt_readme_50ccde67b228.png)](https:\u002F\u002Fbestpractices.coreinfrastructure.org\u002Fprojects\u002F7272)\n[![Link to documentation](https:\u002F\u002Fimg.shields.io\u002Fstatic\u002Fv1?label=%F0%9F%93%96&message=Documentation&color=blue)](https:\u002F\u002Fdocs.k8sgpt.ai\u002F)\n[![FOSSA Status](https:\u002F\u002Fapp.fossa.com\u002Fapi\u002Fprojects\u002Fgit%2Bgithub.com%2Fk8sgpt-ai%2Fk8sgpt.svg?type=shield)](https:\u002F\u002Fapp.fossa.com\u002Fprojects\u002Fgit%2Bgithub.com%2Fk8sgpt-ai%2Fk8sgpt?ref=badge_shield)\n[![License](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FLicense-Apache_2.0-blue.svg)](https:\u002F\u002Fopensource.org\u002Flicenses\u002FApache-2.0)\n[![Go version](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fgo-mod\u002Fgo-version\u002Fk8sgpt-ai\u002Fk8sgpt.svg)](https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fk8sgpt)\n[![codecov](https:\u002F\u002Fcodecov.io\u002Fgithub\u002Fk8sgpt-ai\u002Fk8sgpt\u002Fgraph\u002Fbadge.svg?token=ZLR7NG8URE)](https:\u002F\u002Fcodecov.io\u002Fgithub\u002Fk8sgpt-ai\u002Fk8sgpt)\n![GitHub last commit (branch)](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002Fk8sgpt-ai\u002Fk8sgpt\u002Fmain)\n\n`k8sgpt` is a tool for scanning your Kubernetes clusters, diagnosing, and triaging issues in simple English.\n\nIt has SRE experience codified into its analyzers and helps to pull out the most relevant information to enrich it with AI.\n\n_Out of the box integration with OpenAI, Azure, Cohere, Amazon Bedrock, Google Gemini and local models._\n\n\n> **Sister project:** Check out [sympozium](https:\u002F\u002Fgithub.com\u002FAlexsJones\u002Fsympozium\u002F) for managing agents in Kubernetes.\n\n\n\u003Ca href=\"https:\u002F\u002Fwww.producthunt.com\u002Fposts\u002Fk8sgpt?utm_source=badge-featured&utm_medium=badge&utm_souce=badge-k8sgpt\" target=\"_blank\">\u003Cimg src=\"https:\u002F\u002Fapi.producthunt.com\u002Fwidgets\u002Fembed-image\u002Fv1\u002Ffeatured.svg?post_id=389489&theme=light\" alt=\"K8sGPT - K8sGPT gives Kubernetes Superpowers to everyone | Product Hunt\" style=\"width: 250px; height: 54px;\" width=\"250\" height=\"54\" \u002F>\u003C\u002Fa> \u003Ca href=\"https:\u002F\u002Fhellogithub.com\u002Frepository\u002F9dfe44c18dfb4d6fa0181baf8b2cf2e1\" target=\"_blank\">\u003Cimg src=\"https:\u002F\u002Fabroad.hellogithub.com\u002Fv1\u002Fwidgets\u002Frecommend.svg?rid=9dfe44c18dfb4d6fa0181baf8b2cf2e1&claim_uid=gqG4wmzkMrP0eFy\" alt=\"Featured｜HelloGitHub\" style=\"width: 250px; height: 54px;\" width=\"250\" height=\"54\" \u002F>\u003C\u002Fa>\n\n\n\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fk8sgpt-ai_k8sgpt_readme_1e235c7f3630.gif\" width=\"650px\">\n\n# Table of Contents\n- [Overview](#k8sgpt)\n- [Installation](#cli-installation)\n- [Quick Start](#quick-start)\n- [Analyzers](#analyzers)\n- [Examples](#examples)\n- [LLM AI Backends](#llm-ai-backends)\n- [Key Features](#key-features)\n- [Model Context Protocol (MCP)](#model-context-protocol-mcp)\n- [Documentation](#documentation)\n- [Contributing](#contributing)\n- [Community](#community)\n- [License](#license)\n\n# CLI Installation\n\n### Linux\u002FMac via brew\n\n```sh\nbrew install k8sgpt\n```\n\nor\n\n```sh\nbrew tap k8sgpt-ai\u002Fk8sgpt\nbrew install k8sgpt\n```\n\n\u003Cdetails>\n  \u003Csummary>RPM-based installation (RedHat\u002FCentOS\u002FFedora)\u003C\u002Fsummary>\n\n**32 bit:**\n\n  \u003C!---x-release-please-start-version-->\n\n  ```\n  sudo rpm -ivh https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fk8sgpt\u002Freleases\u002Fdownload\u002Fv0.4.31\u002Fk8sgpt_386.rpm\n  ```\n  \u003C!---x-release-please-end-->\n\n**64 bit:**\n\n  \u003C!---x-release-please-start-version-->\n  ```\n  sudo rpm -ivh https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fk8sgpt\u002Freleases\u002Fdownload\u002Fv0.4.31\u002Fk8sgpt_amd64.rpm\n  ```\n  \u003C!---x-release-please-end-->\n\u003C\u002Fdetails>\n\n\u003Cdetails>\n  \u003Csummary>DEB-based installation (Ubuntu\u002FDebian)\u003C\u002Fsummary>\n\n**32 bit:**\n\n  \u003C!---x-release-please-start-version-->\n\n```\ncurl -LO https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fk8sgpt\u002Freleases\u002Fdownload\u002Fv0.4.31\u002Fk8sgpt_386.deb\nsudo dpkg -i k8sgpt_386.deb\n```\n\n  \u003C!---x-release-please-end-->\n\n**64 bit:**\n\n  \u003C!---x-release-please-start-version-->\n\n```\ncurl -LO https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fk8sgpt\u002Freleases\u002Fdownload\u002Fv0.4.31\u002Fk8sgpt_amd64.deb\nsudo dpkg -i k8sgpt_amd64.deb\n```\n\n  \u003C!---x-release-please-end-->\n\u003C\u002Fdetails>\n\n\u003Cdetails>\n\n  \u003Csummary>APK-based installation (Alpine)\u003C\u002Fsummary>\n\n**32 bit:**\n\n  \u003C!---x-release-please-start-version-->\n  ```\n  wget https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fk8sgpt\u002Freleases\u002Fdownload\u002Fv0.4.31\u002Fk8sgpt_386.apk\n  apk add --allow-untrusted k8sgpt_386.apk\n  ```\n  \u003C!---x-release-please-end-->\n\n**64 bit:**\n\n  \u003C!---x-release-please-start-version-->\n  ```\n  wget https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fk8sgpt\u002Freleases\u002Fdownload\u002Fv0.4.31\u002Fk8sgpt_amd64.apk\n  apk add --allow-untrusted k8sgpt_amd64.apk\n  ```\n  \u003C!---x-release-please-end-->\n\u003C\u002Fdetails>\n\n\u003Cdetails>\n  \u003Csummary>Failing Installation on WSL or Linux (missing gcc)\u003C\u002Fsummary>\n  When installing Homebrew on WSL or Linux, you may encounter the following error:\n\n```\n==> Installing k8sgpt from k8sgpt-ai\u002Fk8sgpt Error: The following formula cannot be installed from a bottle and must be\nbuilt from the source. k8sgpt Install Clang or run brew install gcc.\n```\n\nIf you install gcc as suggested, the problem will persist. Therefore, you need to install the build-essential package.\n\n```\n   sudo apt-get update\n   sudo apt-get install build-essential\n```\n\n\u003C\u002Fdetails>\n\n### Windows\n\n- Download the latest Windows binaries of **k8sgpt** from the [Release](https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fk8sgpt\u002Freleases)\n  tab based on your system architecture.\n- Extract the downloaded package to your desired location. Configure the system _PATH_ environment variable with the binary location\n\n## Operator Installation\n\nTo install within a Kubernetes cluster please use our `k8sgpt-operator` with installation instructions available [here](https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fk8sgpt-operator)\n\n_This mode of operation is ideal for continuous monitoring of your cluster and can integrate with your existing monitoring such as Prometheus and Alertmanager._\n\n## Quick Start\n\n- Currently, the default AI provider is OpenAI, you will need to generate an API key from [OpenAI](https:\u002F\u002Fopenai.com)\n  - You can do this by running `k8sgpt generate` to open a browser link to generate it\n- Run `k8sgpt auth add` to set it in k8sgpt.\n  - You can provide the password directly using the `--password` flag.\n- Run `k8sgpt filters` to manage the active filters used by the analyzer. By default, all filters are executed during analysis.\n- Run `k8sgpt analyze` to run a scan.\n- And use `k8sgpt analyze --explain` to get a more detailed explanation of the issues.\n- You also run `k8sgpt analyze --with-doc` (with or without the explain flag) to get the official documentation from Kubernetes.\n\n# Using with Claude Desktop\n\nK8sGPT can be integrated with Claude Desktop to provide AI-powered Kubernetes cluster analysis. This integration requires K8sGPT v0.4.14 or later.\n\n## Prerequisites\n\n1. Install K8sGPT v0.4.14 or later:\n   ```sh\n   brew install k8sgpt\n   ```\n\n2. Install Claude Desktop from the official website\n\n3. Configure K8sGPT with your preferred AI backend:\n   ```sh\n   k8sgpt auth\n   ```\n\n## Setup\n\n1. Start the K8sGPT MCP server:\n   ```sh\n   k8sgpt serve --mcp\n   ```\n\n2. In Claude Desktop:\n   - Open Settings\n   - Navigate to the Integrations section\n   - Add K8sGPT as a new integration\n   - The MCP server will be automatically detected\n\n3. Configure Claude Desktop with the following JSON:\n\n  ```json\n  {\n    \"mcpServers\": {\n      \"k8sgpt\": {\n        \"command\": \"k8sgpt\",\n        \"args\": [\n          \"serve\",\n          \"--mcp\"\n        ]\n      }\n    }\n  }\n  ```\n\n## Usage\n\nOnce connected, you can use Claude Desktop to:\n- Analyze your Kubernetes cluster\n- Get detailed insights about cluster health\n- Receive recommendations for fixing issues\n- Query cluster information\n\nExample commands in Claude Desktop:\n- \"Analyze my Kubernetes cluster\"\n- \"What's the health status of my cluster?\"\n- \"Show me any issues in the default namespace\"\n\n## Troubleshooting\n\nIf you encounter connection issues:\n1. Ensure K8sGPT is running with the MCP server enabled\n2. Verify your Kubernetes cluster is accessible\n3. Check that your AI backend is properly configured\n4. Restart both K8sGPT and Claude Desktop\n\nFor more information, visit our [documentation](https:\u002F\u002Fdocs.k8sgpt.ai).\n\n## Analyzers\n\nK8sGPT uses analyzers to triage and diagnose issues in your cluster. It has a set of analyzers that are built in, but\nyou will be able to write your own analyzers.\n\n### Built in analyzers\n\n#### Enabled by default\n\n- [x] podAnalyzer\n- [x] pvcAnalyzer\n- [x] rsAnalyzer\n- [x] serviceAnalyzer\n- [x] eventAnalyzer\n- [x] ingressAnalyzer\n- [x] statefulSetAnalyzer\n- [x] deploymentAnalyzer\n- [x] jobAnalyzer\n- [x] cronJobAnalyzer\n- [x] nodeAnalyzer\n- [x] mutatingWebhookAnalyzer\n- [x] validatingWebhookAnalyzer\n- [x] configMapAnalyzer\n\n#### Optional\n\n- [x] hpaAnalyzer\n- [x] pdbAnalyzer\n- [x] networkPolicyAnalyzer\n- [x] gatewayClass\n- [x] gateway\n- [x] httproute\n- [x] logAnalyzer\n- [x] storageAnalyzer\n- [x] securityAnalyzer\n- [x] CatalogSource\n- [x] ClusterCatalog\n- [x] ClusterExtension\n- [x] ClusterService\n- [x] ClusterServiceVersion\n- [x] OperatorGroup\n- [x] InstallPlan\n- [x] Subscription\n\n## Examples\n\n_Run a scan with the default analyzers_\n\n```\nk8sgpt generate\nk8sgpt auth add\nk8sgpt analyze --explain\nk8sgpt analyze --explain --with-doc\n```\n\n_Filter on resource_\n\n```\nk8sgpt analyze --explain --filter=Service\n```\n\n_Filter by namespace_\n\n```\nk8sgpt analyze --explain --filter=Pod --namespace=default\n```\n\n_Output to JSON_\n\n```\nk8sgpt analyze --explain --filter=Service --output=json\n```\n\n_Anonymize during explain_\n\n```\nk8sgpt analyze --explain --filter=Service --output=json --anonymize\n```\n\n\u003Cdetails>\n\u003Csummary> Using filters \u003C\u002Fsummary>\n\n_List filters_\n\n```\nk8sgpt filters list\n```\n\n_Add default filters_\n\n```\nk8sgpt filters add [filter(s)]\n```\n\n### Examples :\n\n- Simple filter : `k8sgpt filters add Service`\n- Multiple filters : `k8sgpt filters add Ingress,Pod`\n\n_Remove default filters_\n\n```\nk8sgpt filters remove [filter(s)]\n```\n\n### Examples :\n\n- Simple filter : `k8sgpt filters remove Service`\n- Multiple filters : `k8sgpt filters remove Ingress,Pod`\n\n\u003C\u002Fdetails>\n\n\u003Cdetails>\n\n\u003Csummary> Additional commands \u003C\u002Fsummary>\n\n_List configured backends_\n\n```\nk8sgpt auth list\n```\n\n_Update configured backends_\n\n```\nk8sgpt auth update $MY_BACKEND1,$MY_BACKEND2..\n```\n\n_Remove configured backends_\n\n```\nk8sgpt auth remove -b $MY_BACKEND1,$MY_BACKEND2..\n```\n\n_List integrations_\n\n```\nk8sgpt integrations list\n```\n\n_Activate integrations_\n\n```\nk8sgpt integrations activate [integration(s)]\n```\n\n_Use integration_\n\n```\nk8sgpt analyze --filter=[integration(s)]\n```\n\n_Deactivate integrations_\n\n```\nk8sgpt integrations deactivate [integration(s)]\n```\n\n_Serve mode_\n\n```\nk8sgpt serve\n```\n\n_Serve mode with MCP (Model Context Protocol)_\n\n```\n# Enable MCP server on default port 8089\nk8sgpt serve --mcp --mcp-http\n\n# Enable MCP server on custom port\nk8sgpt serve --mcp --mcp-http --mcp-port 8089\n\n# Full serve mode with MCP\nk8sgpt serve --mcp --mcp-http --port 8080 --metrics-port 8081 --mcp-port 8089\n```\n\nThe MCP server enables integration with tools like Claude Desktop and other MCP-compatible clients. It runs on port 8089 by default and provides:\n- Kubernetes cluster analysis via MCP protocol\n- Resource information and health status\n- AI-powered issue explanations and recommendations\n\nFor Helm chart deployment with MCP support, see the `charts\u002Fk8sgpt\u002Fvalues-mcp-example.yaml` file.\n\n_Analysis with serve mode_\n\n```\ngrpcurl -plaintext -d '{\"namespace\": \"k8sgpt\", \"explain\" : \"true\"}' localhost:8080 schema.v1.ServerAnalyzerService\u002FAnalyze\n{\n  \"status\": \"OK\"\n}\n```\n\n_Analysis with custom headers_\n\n```\nk8sgpt analyze --explain --custom-headers CustomHeaderKey:CustomHeaderValue\n```\n\n_Print analysis stats_\n\n```\nk8sgpt analyze -s\nThe stats mode allows for debugging and understanding the time taken by an analysis by displaying the statistics of each analyzer.\n- Analyzer Ingress took 47.125583ms\n- Analyzer PersistentVolumeClaim took 53.009167ms\n- Analyzer CronJob took 57.517792ms\n- Analyzer Deployment took 156.6205ms\n- Analyzer Node took 160.109833ms\n- Analyzer ReplicaSet took 245.938333ms\n- Analyzer StatefulSet took 448.0455ms\n- Analyzer Pod took 5.662594708s\n- Analyzer Service took 38.583359166s\n```\n\n_Diagnostic information_\n\nTo collect diagnostic information use the following command to create a `dump_\u003Ctimestamp>_json` in your local directory.\n```\nk8sgpt dump\n```\n\n\u003C\u002Fdetails>\n\n## LLM AI Backends\n\nK8sGPT uses the chosen LLM, generative AI provider when you want to explain the analysis results using --explain flag e.g. `k8sgpt analyze --explain`. You can use `--backend` flag to specify a configured provider (it's `openai` by default).\n\nYou can list available providers using `k8sgpt auth list`:\n\n```\nDefault:\n> openai\nActive:\nUnused:\n> openai\n> localai\n> ollama\n> azureopenai\n> cohere\n> amazonbedrock\n> amazonsagemaker\n> google\n> huggingface\n> noopai\n> googlevertexai\n> watsonxai\n> customrest\n> ibmwatsonxai\n```\n\nFor detailed documentation on how to configure and use each provider see [here](https:\u002F\u002Fdocs.k8sgpt.ai\u002Freference\u002Fproviders\u002Fbackend\u002F).\n\n_To set a new default provider_\n\n```\nk8sgpt auth default -p azureopenai\nDefault provider set to azureopenai\n```\n\n_Using Amazon Bedrock Converse with inference profiles_\n\n_System Inference Profile_\n\n```\nk8sgpt auth add --backend amazonbedrockconverse --providerRegion us-east-1 --model arn:aws:bedrock:us-east-1:123456789012:inference-profile\u002Fmy-inference-profile\n\n```\n\n_Application Inference Profile_\n\n```\nk8sgpt auth add --backend amazonbedrockconverse --providerRegion us-east-1 --model arn:aws:bedrock:us-east-1:123456789012:application-inference-profile\u002F2uzp4s0w39t6\n\n```\n_Using Amazon Bedrock with inference profiles_\n\n_System Inference Profile_\n\n```\nk8sgpt auth add --backend amazonbedrock --providerRegion us-east-1 --model arn:aws:bedrock:us-east-1:123456789012:inference-profile\u002Fmy-inference-profile\n\n```\n\n_Application Inference Profile_\n\n```\nk8sgpt auth add --backend amazonbedrock --providerRegion us-east-1 --model arn:aws:bedrock:us-east-1:123456789012:application-inference-profile\u002F2uzp4s0w39t6\n\n```\n\n## Key Features\n\n\u003Cdetails>\n\nWith this option, the data is anonymized before being sent to the AI Backend. During the analysis execution, `k8sgpt` retrieves sensitive data (Kubernetes object names, labels, etc.). This data is masked when sent to the AI backend and replaced by a key that can be used to de-anonymize the data when the solution is returned to the user.\n\n\u003Csummary> Anonymization \u003C\u002Fsummary>\n\n1. Error reported during analysis:\n\n```bash\nError: HorizontalPodAutoscaler uses StatefulSet\u002Ffake-deployment as ScaleTargetRef which does not exist.\n```\n\n2. Payload sent to the AI backend:\n\n```bash\nError: HorizontalPodAutoscaler uses StatefulSet\u002FtGLcCRcHa1Ce5Rs as ScaleTargetRef which does not exist.\n```\n\n3. Payload returned by the AI:\n\n```bash\nThe Kubernetes system is trying to scale a StatefulSet named tGLcCRcHa1Ce5Rs using the HorizontalPodAutoscaler, but it cannot find the StatefulSet. The solution is to verify that the StatefulSet name is spelled correctly and exists in the same namespace as the HorizontalPodAutoscaler.\n```\n\n4. Payload returned to the user:\n\n```bash\nThe Kubernetes system is trying to scale a StatefulSet named fake-deployment using the HorizontalPodAutoscaler, but it cannot find the StatefulSet. The solution is to verify that the StatefulSet name is spelled correctly and exists in the same namespace as the HorizontalPodAutoscaler.\n```\n\n### Further Details\n\nNote: **Anonymization does not currently apply to events.**\n\n_In a few analysers like Pod, we feed to the AI backend the event messages which are not known beforehand thus we are not masking them for the **time being**._\n\n- The following is the list of analysers in which data is **being masked**:-\n\n  - Statefulset\n  - Service\n  - PodDisruptionBudget\n  - Node\n  - NetworkPolicy\n  - Ingress\n  - HPA\n  - Deployment\n  - Cronjob\n\n- The following is the list of analysers in which data is **not being masked**:-\n\n  - ReplicaSet\n  - PersistentVolumeClaim\n  - Pod\n  - Log\n  - **_\\*Events_**\n\n**\\*Note**:\n\n- k8gpt will not mask the above analysers because they do not send any identifying information except **Events** analyser.\n- Masking for **Events** analyzer is scheduled in the near future as seen in this [issue](https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fk8sgpt\u002Fissues\u002F560). _Further research has to be made to understand the patterns and be able to mask the sensitive parts of an event like pod name, namespace etc._\n\n- The following is the list of fields which are not **being masked**:-\n\n  - Describe\n  - ObjectStatus\n  - Replicas\n  - ContainerStatus\n  - **_\\*Event Message_**\n  - ReplicaStatus\n  - Count (Pod)\n\n**\\*Note**:\n\n- It is quite possible the payload of the event message might have something like \"super-secret-project-pod-X crashed\" which we don't currently redact _(scheduled in the near future as seen in this [issue](https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fk8sgpt\u002Fissues\u002F560))_.\n\n### Proceed with care\n\n- The K8gpt team recommends using an entirely different backend **(a local model) in critical production environments**. By using a local model, you can rest assured that everything stays within your DMZ, and nothing is leaked.\n- If there is any uncertainty about the possibility of sending data to a public LLM (open AI, Azure AI) and it poses a risk to business-critical operations, then, in such cases, the use of public LLM should be avoided based on personal assessment and the jurisdiction of risks involved.\n\n\u003C\u002Fdetails>\n\n\u003Cdetails>\n\u003Csummary> Configuration management\u003C\u002Fsummary>\n\n`k8sgpt` stores config data in the `$XDG_CONFIG_HOME\u002Fk8sgpt\u002Fk8sgpt.yaml` file. The data is stored in plain text, including your OpenAI key.\n\nConfig file locations:\n| OS | Path |\n| ------- | ------------------------------------------------ |\n| MacOS | ~\u002FLibrary\u002FApplication Support\u002Fk8sgpt\u002Fk8sgpt.yaml |\n| Linux | ~\u002F.config\u002Fk8sgpt\u002Fk8sgpt.yaml |\n| Windows | %LOCALAPPDATA%\u002Fk8sgpt\u002Fk8sgpt.yaml |\n\n\u003C\u002Fdetails>\n\n\u003Cdetails>\nThere may be scenarios where caching remotely is preferred.\nIn these scenarios K8sGPT supports AWS S3 or Azure Blob storage Integration.\n\n\u003Csummary> Remote caching \u003C\u002Fsummary>\n\u003Cem>Note: You can configure and use only one remote cache at a time\u003C\u002Fem>\n\n_Adding a remote cache_\n\n- AWS S3\n  - _As a prerequisite `AWS_ACCESS_KEY_ID` and `AWS_SECRET_ACCESS_KEY` are required as environmental variables._\n  - Configuration, `k8sgpt cache add s3 --region \u003Caws region> --bucket \u003Cname>`\n  - Minio Configuration with HTTP endpoint ` k8sgpt cache add s3 --bucket \u003Cname> --endpoint \u003Chttp:\u002F\u002Flocalhost:9000>`\n  - Minio Configuration with HTTPs endpoint, skipping TLS verification ` k8sgpt cache add s3 --bucket \u003Cname> --endpoint \u003Chttps:\u002F\u002Flocalhost:9000> --insecure`\n    - K8sGPT will create the bucket if it does not exist\n- Azure Storage\n  - We support a number of [techniques](https:\u002F\u002Flearn.microsoft.com\u002Fen-us\u002Fazure\u002Fdeveloper\u002Fgo\u002Fazure-sdk-authentication?tabs=bash#2-authenticate-with-azure) to authenticate against Azure\n  - Configuration, `k8sgpt cache add azure --storageacc \u003Cstorage account name> --container \u003Ccontainer name>`\n    - K8sGPT assumes that the storage account already exist and it will create the container if it does not exist\n    - It is the **user** responsibility have to grant specific permissions to their identity in order to be able to upload blob files and create SA containers (e.g Storage Blob Data Contributor)\n- Google Cloud Storage\n  - _As a prerequisite `GOOGLE_APPLICATION_CREDENTIALS` are required as environmental variables._\n  - Configuration, ` k8sgpt cache add gcs --region \u003Cgcp region> --bucket \u003Cname> --projectid \u003Cproject id>`\n    - K8sGPT will create the bucket if it does not exist\n\n_Listing cache items_\n\n```\nk8sgpt cache list\n```\n\n_Purging an object from the cache_\nNote: purging an object using this command will delete upstream files, so it requires appropriate permissions.\n\n```\nk8sgpt cache purge $OBJECT_NAME\n```\n\n_Removing the remote cache_\nNote: this will not delete the upstream S3 bucket or Azure storage container\n\n```\nk8sgpt cache remove\n```\n\n\u003C\u002Fdetails>\n\n\u003Cdetails>\n\u003Csummary> Custom Analyzers\u003C\u002Fsummary>\n\nThere may be scenarios where you wish to write your own analyzer in a language of your choice.\nK8sGPT now supports the ability to do so by abiding by the [schema](https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fschemas\u002Fblob\u002Fmain\u002Fprotobuf\u002Fschema\u002Fv1\u002Fcustom_analyzer.proto) and serving the analyzer for consumption.\nTo do so, define the analyzer within the K8sGPT configuration and it will add it into the scanning process.\nIn addition to this you will need to enable the following flag on analysis:\n\n```\nk8sgpt analyze --custom-analysis\n```\n\nHere is an example local host analyzer in [Rust](https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fhost-analyzer)\nWhen this is run on `localhost:8080` the K8sGPT config can pick it up with the following additions:\n\n```\ncustom_analyzers:\n  - name: host-analyzer\n    connection:\n      url: localhost\n      port: 8080\n```\n\nThis now gives the ability to pass through hostOS information ( from this analyzer example ) to K8sGPT to use as context with normal analysis.\n\n_See the docs on how to write a custom analyzer_\n\n_Listing custom analyzers configured_\n```\nk8sgpt custom-analyzer list\n```\n\n_Adding custom analyzer without install_\n```\nk8sgpt custom-analyzer add --name my-custom-analyzer --port 8085\n```\n\n_Removing custom analyzer_\n```\nk8sgpt custom-analyzer remove --names \"my-custom-analyzer,my-custom-analyzer-2\"\n```\n\n\u003C\u002Fdetails>\n## Model Context Protocol (MCP)\n\nK8sGPT provides a Model Context Protocol server that exposes Kubernetes operations as standardized tools for AI assistants like Claude, ChatGPT, and other MCP-compatible clients.\n\n**Start the MCP server:**\n\nStdio mode (for local AI assistants):\n```bash\nk8sgpt serve --mcp\n```\n\nHTTP mode (for network access):\n```bash\nk8sgpt serve --mcp --mcp-http --mcp-port 8089\n```\n\n**Features:**\n- 12 tools for cluster analysis, resource management, and debugging\n- 3 resources for cluster information access\n- 3 interactive troubleshooting prompts\n- Stateless HTTP mode for one-off invocations\n- Full integration with Claude Desktop and other MCP clients\n\n**Learn more:** See [MCP.md](MCP.md) for complete documentation, usage examples, and integration guides.\n## Documentation\n\nFind our official documentation available [here](https:\u002F\u002Fdocs.k8sgpt.ai)\n\n## Contributing\n\nPlease read our [contributing guide](.\u002FCONTRIBUTING.md).\n\n## Community\n\nFind us on [Slack](https:\u002F\u002Fjoin.slack.com\u002Ft\u002Fk8sgpt\u002Fshared_invite\u002Fzt-332vhyaxv-bfjJwHZLXWVCB3QaXafEYQ)\n\n\u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fk8sgpt\u002Fgraphs\u002Fcontributors\">\n  \u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fk8sgpt-ai_k8sgpt_readme_e213d47ea004.png\" \u002F>\n\u003C\u002Fa>\n\n## License\n\n[![FOSSA Status](https:\u002F\u002Fapp.fossa.com\u002Fapi\u002Fprojects\u002Fgit%2Bgithub.com%2Fk8sgpt-ai%2Fk8sgpt.svg?type=large)](https:\u002F\u002Fapp.fossa.com\u002Fprojects\u002Fgit%2Bgithub.com%2Fk8sgpt-ai%2Fk8sgpt?ref=badge_large)\n","\u003Cpicture>\n  \u003Csource media=\"(prefers-color-scheme: dark)\" srcset=\".\u002Fimages\u002Fbanner-white.png\" width=\"600px;\">\n  \u003Cimg alt=\"根据模式变化的文本。浅色模式：‘好亮啊！’；深色模式：‘好暗啊！’\" src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fk8sgpt-ai_k8sgpt_readme_4cd852d3f9aa.png\" width=\"600px;\">\n\u003C\u002Fpicture>\n\u003Cbr\u002F>\n\n![GitHub 代码大小（字节）](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flanguages\u002Fcode-size\u002Fk8sgpt-ai\u002Fk8sgpt)\n![GitHub 工作流状态](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Factions\u002Fworkflow\u002Fstatus\u002Fk8sgpt-ai\u002Fk8sgpt\u002Frelease.yaml)\n![GitHub 最新发布版本](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fv\u002Frelease\u002Fk8sgpt-ai\u002Fk8sgpt)\n[![OpenSSF 最佳实践](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fk8sgpt-ai_k8sgpt_readme_50ccde67b228.png)](https:\u002F\u002Fbestpractices.coreinfrastructure.org\u002Fprojects\u002F7272)\n[![文档链接](https:\u002F\u002Fimg.shields.io\u002Fstatic\u002Fv1?label=%F0%9F%93%96&message=Documentation&color=blue)](https:\u002F\u002Fdocs.k8sgpt.ai\u002F)\n[![FOSSA 状态](https:\u002F\u002Fapp.fossa.com\u002Fapi\u002Fprojects\u002Fgit%2Bgithub.com%2Fk8sgpt-ai%2Fk8sgpt.svg?type=shield)](https:\u002F\u002Fapp.fossa.com\u002Fprojects\u002Fgit%2Bgithub.com%2Fk8sgpt-ai%2Fk8sgpt?ref=badge_shield)\n[![许可证](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FLicense-Apache_2.0-blue.svg)](https:\u002F\u002Fopensource.org\u002Flicenses\u002FApache-2.0)\n[![Go 版本](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fgo-mod\u002Fgo-version\u002Fk8sgpt-ai\u002Fk8sgpt.svg)](https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fk8sgpt)\n[![Codecov](https:\u002F\u002Fcodecov.io\u002Fgithub\u002Fk8sgpt-ai\u002Fk8sgpt\u002Fgraph\u002Fbadge.svg?token=ZLR7NG8URE)](https:\u002F\u002Fcodecov.io\u002Fgithub\u002Fk8sgpt-ai\u002Fk8sgpt)\n![GitHub 最后一次提交（分支）](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002Fk8sgpt-ai\u002Fk8sgpt\u002Fmain)\n\n`k8sgpt` 是一款用于扫描 Kubernetes 集群、诊断并以简单英语对问题进行分类处理的工具。\n\n它将 SRE 经验编码到分析器中，并帮助提取最相关的信息，再结合 AI 技术进一步丰富这些信息。\n\n**开箱即用，支持与 OpenAI、Azure、Cohere、Amazon Bedrock、Google Gemini 以及本地模型集成。**\n\n\n> **姊妹项目：** 如果您想在 Kubernetes 中管理代理，请查看 [sympozium](https:\u002F\u002Fgithub.com\u002FAlexsJones\u002Fsympozium\u002F)。\n\n\n\u003Ca href=\"https:\u002F\u002Fwww.producthunt.com\u002Fposts\u002Fk8sgpt?utm_source=badge-featured&utm_medium=badge&utm_souce=badge-k8sgpt\" target=\"_blank\">\u003Cimg src=\"https:\u002F\u002Fapi.producthunt.com\u002Fwidgets\u002Fembed-image\u002Fv1\u002Ffeatured.svg?post_id=389489&theme=light\" alt=\"K8sGPT - K8sGPT gives Kubernetes Superpowers to everyone | Product Hunt\" style=\"width: 250px; height: 54px;\" width=\"250\" height=\"54\" \u002F>\u003C\u002Fa> \u003Ca href=\"https:\u002F\u002Fhellogithub.com\u002Frepository\u002F9dfe44c18dfb4d6fa0181baf8b2cf2e1\" target=\"_blank\">\u003Cimg src=\"https:\u002F\u002Fabroad.hellogithub.com\u002Fv1\u002Fwidgets\u002Frecommend.svg?rid=9dfe44c18dfb4d6fa0181baf8b2cf2e1&claim_uid=gqG4wmzkMrP0eFy\" alt=\"精选｜HelloGitHub\" style=\"width: 250px; height: 54px;\" width=\"250\" height=\"54\" \u002F>\u003C\u002Fa>\n\n\n\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fk8sgpt-ai_k8sgpt_readme_1e235c7f3630.gif\" width=\"650px\">\n\n# 目录\n- [概述](#k8sgpt)\n- [安装](#cli-installation)\n- [快速入门](#quick-start)\n- [分析器](#analyzers)\n- [示例](#examples)\n- [LLM AI 后端](#llm-ai-backends)\n- [关键特性](#key-features)\n- [模型上下文协议 (MCP)](#model-context-protocol-mcp)\n- [文档](#documentation)\n- [贡献](#contributing)\n- [社区](#community)\n- [许可证](#license)\n\n# CLI 安装\n\n### Linux\u002FMac 通过 brew\n\n```sh\nbrew install k8sgpt\n```\n\n或者\n\n```sh\nbrew tap k8sgpt-ai\u002Fk8sgpt\nbrew install k8sgpt\n```\n\n\u003Cdetails>\n  \u003Csummary>RPM 包安装（RedHat\u002FCentOS\u002FFedora）\u003C\u002Fsummary>\n\n**32 位：**\n\n  \u003C!---x-release-please-start-version-->\n\n  ```\n  sudo rpm -ivh https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fk8sgpt\u002Freleases\u002Fdownload\u002Fv0.4.31\u002Fk8sgpt_386.rpm\n  ```\n  \u003C!---x-release-please-end-->\n\n**64 位：**\n\n  \u003C!---x-release-please-start-version-->\n  ```\n  sudo rpm -ivh https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fk8sgpt\u002Freleases\u002Fdownload\u002Fv0.4.31\u002Fk8sgpt_amd64.rpm\n  ```\n  \u003C!---x-release-please-end-->\n\u003C\u002Fdetails>\n\n\u003Cdetails>\n  \u003Csummary>DEB 包安装（Ubuntu\u002FDebian）\u003C\u002Fsummary>\n\n**32 位：**\n\n  \u003C!---x-release-please-start-version-->\n\n```\ncurl -LO https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fk8sgpt\u002Freleases\u002Fdownload\u002Fv0.4.31\u002Fk8sgpt_386.deb\nsudo dpkg -i k8sgpt_386.deb\n```\n\n  \u003C!---x-release-please-end-->\n\n**64 位：**\n\n  \u003C!---x-release-please-start-version-->\n\n```\ncurl -LO https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fk8sgpt\u002Freleases\u002Fdownload\u002Fv0.4.31\u002Fk8sgpt_amd64.deb\nsudo dpkg -i k8sgpt_amd64.deb\n```\n\n  \u003C!---x-release-please-end-->\n\u003C\u002Fdetails>\n\n\u003Cdetails>\n\n  \u003Csummary>APK 包安装（Alpine）\u003C\u002Fsummary>\n\n**32 位：**\n\n  \u003C!---x-release-please-start-version-->\n  ```\n  wget https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fk8sgpt\u002Freleases\u002Fdownload\u002Fv0.4.31\u002Fk8sgpt_386.apk\n  apk add --allow-untrusted k8sgpt_386.apk\n  ```\n  \u003C!---x-release-please-end-->\n\n**64 位：**\n\n  \u003C!---x-release-please-start-version-->\n  ```\n  wget https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fk8sgpt\u002Freleases\u002Fdownload\u002Fv0.4.31\u002Fk8sgpt_amd64.apk\n  apk add --allow-untrusted k8sgpt_amd64.apk\n  ```\n  \u003C!---x-release-please-end-->\n\u003C\u002Fdetails>\n\n\u003Cdetails>\n  \u003Csummary>WSL 或 Linux 上安装失败（缺少 gcc）\u003C\u002Fsummary>\n  在 WSL 或 Linux 上安装 Homebrew 时，可能会遇到以下错误：\n\n```\n==> Installing k8sgpt from k8sgpt-ai\u002Fk8sgpt Error: The following formula cannot be installed from a bottle and must be\nbuilt from the source. k8sgpt Install Clang or run brew install gcc.\n```\n\n即使按照提示安装了 gcc，问题仍然存在。因此，您需要安装 build-essential 软件包。\n\n```\n   sudo apt-get update\n   sudo apt-get install build-essential\n```\n\n\u003C\u002Fdetails>\n\n### Windows\n\n- 请根据您的系统架构，从 [Release](https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fk8sgpt\u002Freleases) 页面下载最新版本的 `k8sgpt` Windows 二进制文件。\n- 将下载的压缩包解压到您希望存放的位置，并配置系统的 _PATH_ 环境变量以指向该二进制文件所在目录。\n\n## Operator 安装\n\n如需在 Kubernetes 集群内安装，请使用我们的 `k8sgpt-operator`，安装说明请参见 [此处](https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fk8sgpt-operator)。\n\n**此运行模式非常适合对集群进行持续监控，并可与您现有的监控系统（如 Prometheus 和 Alertmanager）集成。**\n\n## 快速入门\n\n- 当前默认的 AI 提供商是 OpenAI，您需要先从 [OpenAI](https:\u002F\u002Fopenai.com) 生成一个 API 密钥。\n  - 您可以通过运行 `k8sgpt generate` 打开浏览器链接来生成密钥。\n- 运行 `k8sgpt auth add` 将其设置到 k8sgpt 中。\n  - 您也可以直接使用 `--password` 标志提供密码。\n- 运行 `k8sgpt filters` 来管理分析器使用的活动过滤器。默认情况下，所有过滤器都会在分析过程中执行。\n- 运行 `k8sgpt analyze` 开始扫描。\n- 使用 `k8sgpt analyze --explain` 可以获得更详细的故障说明。\n- 您还可以运行 `k8sgpt analyze --with-doc`（无论是否使用 explain 标志），以获取来自 Kubernetes 的官方文档。\n\n# 与 Claude Desktop 配合使用\n\nK8sGPT 可以与 Claude Desktop 集成，从而提供基于 AI 的 Kubernetes 集群分析功能。此集成需要 K8sGPT v0.4.14 或更高版本。\n\n## 前置条件\n\n1. 安装 K8sGPT v0.4.14 或更高版本：\n   ```sh\n   brew install k8sgpt\n   ```\n\n2. 从官方网站安装 Claude Desktop\n\n3. 使用您偏好的 AI 后端配置 K8sGPT：\n   ```sh\n   k8sgpt auth\n   ```\n\n## 设置\n\n1. 启动 K8sGPT 的 MCP 服务器：\n   ```sh\n   k8sgpt serve --mcp\n   ```\n\n2. 在 Claude Desktop 中：\n   - 打开设置\n   - 导航到集成部分\n   - 添加 K8sGPT 作为新的集成\n   - MCP 服务器将自动被检测到\n\n3. 使用以下 JSON 配置 Claude Desktop：\n\n  ```json\n  {\n    \"mcpServers\": {\n      \"k8sgpt\": {\n        \"command\": \"k8sgpt\",\n        \"args\": [\n          \"serve\",\n          \"--mcp\"\n        ]\n      }\n    }\n  }\n  ```\n\n## 使用\n\n连接成功后，您可以使用 Claude Desktop 来：\n- 分析您的 Kubernetes 集群\n- 获取关于集群健康状况的详细信息\n- 获得修复问题的建议\n- 查询集群信息\n\nClaude Desktop 中的示例命令：\n- “分析我的 Kubernetes 集群”\n- “我的集群健康状况如何？”\n- “显示 default 命名空间中的任何问题”\n\n## 故障排除\n\n如果遇到连接问题：\n1. 确保 K8sGPT 已启用 MCP 服务器并正在运行\n2. 验证您的 Kubernetes 集群是否可访问\n3. 检查您的 AI 后端是否已正确配置\n4. 重启 K8sGPT 和 Claude Desktop\n\n如需更多信息，请访问我们的 [文档](https:\u002F\u002Fdocs.k8sgpt.ai)。\n\n## 分析器\n\nK8sGPT 使用分析器来对集群中的问题进行分类和诊断。它内置了一组分析器，但您也可以编写自己的分析器。\n\n### 内置分析器\n\n#### 默认启用\n\n- [x] podAnalyzer\n- [x] pvcAnalyzer\n- [x] rsAnalyzer\n- [x] serviceAnalyzer\n- [x] eventAnalyzer\n- [x] ingressAnalyzer\n- [x] statefulSetAnalyzer\n- [x] deploymentAnalyzer\n- [x] jobAnalyzer\n- [x] cronJobAnalyzer\n- [x] nodeAnalyzer\n- [x] mutatingWebhookAnalyzer\n- [x] validatingWebhookAnalyzer\n- [x] configMapAnalyzer\n\n#### 可选\n\n- [x] hpaAnalyzer\n- [x] pdbAnalyzer\n- [x] networkPolicyAnalyzer\n- [x] gatewayClass\n- [x] gateway\n- [x] httproute\n- [x] logAnalyzer\n- [x] storageAnalyzer\n- [x] securityAnalyzer\n- [x] CatalogSource\n- [x] ClusterCatalog\n- [x] ClusterExtension\n- [x] ClusterService\n- [x] ClusterServiceVersion\n- [x] OperatorGroup\n- [x] InstallPlan\n- [x] Subscription\n\n## 示例\n\n_使用默认分析器进行扫描_\n\n```\nk8sgpt generate\nk8sgpt auth add\nk8sgpt analyze --explain\nk8sgpt analyze --explain --with-doc\n```\n\n_按资源筛选_\n\n```\nk8sgpt analyze --explain --filter=Service\n```\n\n_按命名空间筛选_\n\n```\nk8sgpt analyze --explain --filter=Pod --namespace=default\n```\n\n_输出为 JSON_\n\n```\nk8sgpt analyze --explain --filter=Service --output=json\n```\n\n_解释时匿名化_\n\n```\nk8sgpt analyze --explain --filter=Service --output=json --anonymize\n```\n\n\u003Cdetails>\n\u003Csummary> 使用筛选器 \u003C\u002Fsummary>\n\n_列出筛选器_\n\n```\nk8sgpt filters list\n```\n\n_添加默认筛选器_\n\n```\nk8sgpt filters add [筛选器]\n```\n\n### 示例：\n\n- 单一筛选器：`k8sgpt filters add Service`\n- 多个筛选器：`k8sgpt filters add Ingress,Pod`\n\n_删除默认筛选器_\n\n```\nk8sgpt filters remove [筛选器]\n```\n\n### 示例：\n\n- 单一筛选器：`k8sgpt filters remove Service`\n- 多个筛选器：`k8sgpt filters remove Ingress,Pod`\n\n\u003C\u002Fdetails>\n\n\u003Cdetails>\n\n\u003Csummary> 其他命令 \u003C\u002Fsummary>\n\n_列出已配置的后端_\n\n```\nk8sgpt auth list\n```\n\n_更新已配置的后端_\n\n```\nk8sgpt auth update $MY_BACKEND1,$MY_BACKEND2..\n```\n\n_删除已配置的后端_\n\n```\nk8sgpt auth remove -b $MY_BACKEND1,$MY_BACKEND2..\n```\n\n_列出集成_\n\n```\nk8sgpt integrations list\n```\n\n_激活集成_\n\n```\nk8sgpt integrations activate [集成]\n```\n\n_使用集成_\n\n```\nk8sgpt analyze --filter=[集成]\n```\n\n_停用集成_\n\n```\nk8sgpt integrations deactivate [集成]\n```\n\n_服务模式_\n\n```\nk8sgpt serve\n```\n\n_带有 MCP（模型上下文协议）的服务模式_\n\n```\n# 在默认端口 8089 上启用 MCP 服务器\nk8sgpt serve --mcp --mcp-http\n\n# 在自定义端口上启用 MCP 服务器\nk8sgpt serve --mcp --mcp-http --mcp-port 8089\n\n# 完整的服务模式，包含 MCP\nk8sgpt serve --mcp --mcp-http --port 8080 --metrics-port 8081 --mcp-port 8089\n```\n\nMCP 服务器支持与 Claude Desktop 等兼容 MCP 的客户端集成。它默认运行在端口 8089 上，提供：\n- 通过 MCP 协议进行的 Kubernetes 集群分析\n- 资源信息和健康状况\n- 基于 AI 的问题解释和建议\n\n有关支持 MCP 的 Helm Chart 部署，请参阅 `charts\u002Fk8sgpt\u002Fvalues-mcp-example.yaml` 文件。\n\n_使用服务模式进行分析_\n\n```\ngrpcurl -plaintext -d '{\"namespace\": \"k8sgpt\", \"explain\" : \"true\"}' localhost:8080 schema.v1.ServerAnalyzerService\u002FAnalyze\n{\n  \"status\": \"OK\"\n}\n```\n\n_使用自定义头部进行分析_\n\n```\nk8sgpt analyze --explain --custom-headers CustomHeaderKey:CustomHeaderValue\n```\n\n_打印分析统计_\n\n```\nk8sgpt analyze -s\n统计模式允许通过显示每个分析器的统计数据来进行调试和了解分析所花费的时间。\n- Ingress 分析器耗时 47.125583 毫秒\n- PersistentVolumeClaim 分析器耗时 53.009167 毫秒\n- CronJob 分析器耗时 57.517792 毫秒\n- Deployment 分析器耗时 156.6205 毫秒\n- Node 分析器耗时 160.109833 毫秒\n- ReplicaSet 分析器耗时 245.938333 毫秒\n- StatefulSet 分析器耗时 448.0455 毫秒\n- Pod 分析器耗时 5.662594708 秒\n- Service 分析器耗时 38.583359166 秒\n```\n\n_诊断信息_\n\n要收集诊断信息，请使用以下命令在本地目录中创建一个 `dump_\u003Ctimestamp>_json` 文件。\n```\nk8sgpt dump\n```\n\n\u003C\u002Fdetails>\n\n## LLM AI 后端\n\nK8sGPT 会在您使用 `--explain` 标志（例如 `k8sgpt analyze --explain`）解释分析结果时，使用您选择的 LLM 或生成式 AI 提供商。您可以使用 `--backend` 标志来指定已配置的提供商（默认为 `openai`）。\n\n您可以通过 `k8sgpt auth list` 列出可用的提供商：\n\n```\n默认：\n> openai\n活跃：\n未使用：\n> openai\n> localai\n> ollama\n> azureopenai\n> cohere\n> amazonbedrock\n> amazonsagemaker\n> google\n> huggingface\n> noopai\n> googlevertexai\n> watsonxai\n> customrest\n> ibmwatsonxai\n```\n\n有关如何配置和使用每个提供商的详细文档，请参阅[此处](https:\u002F\u002Fdocs.k8sgpt.ai\u002Freference\u002Fproviders\u002Fbackend\u002F)。\n\n_设置新的默认提供商_\n\n```\nk8sgpt auth default -p azureopenai\n默认提供商已设置为 azureopenai\n```\n\n_使用 Amazon Bedrock Converse 和推理配置文件_\n\n_系统推理配置文件_\n\n```\nk8sgpt auth add --backend amazonbedrockconverse --providerRegion us-east-1 --model arn:aws:bedrock:us-east-1:123456789012:inference-profile\u002Fmy-inference-profile\n\n```\n\n_应用推理配置文件_\n\n```\nk8sgpt auth add --backend amazonbedrockconverse --providerRegion us-east-1 --model arn:aws:bedrock:us-east-1:123456789012:application-inference-profile\u002F2uzp4s0w39t6\n\n```\n\n_使用 Amazon Bedrock 和推理配置文件_\n\n_系统推理配置文件_\n\n```\nk8sgpt auth add --backend amazonbedrock --providerRegion us-east-1 --model arn:aws:bedrock:us-east-1:123456789012:inference-profile\u002Fmy-inference-profile\n\n```\n\n_应用推理配置文件_\n\n```\nk8sgpt auth add --backend amazonbedrock --providerRegion us-east-1 --model arn:aws:bedrock:us-east-1:123456789012:application-inference-profile\u002F2uzp4s0w39t6\n\n```\n\n## 主要特性\n\n\u003Cdetails>\n\n通过此选项，数据在发送到 AI 后端之前会被匿名化。在分析执行过程中，`k8sgpt` 会检索敏感数据（Kubernetes 对象名称、标签等）。这些数据在发送到 AI 后端时会被掩码替换，并用一个密钥代替，该密钥可在解决方案返回给用户时用于去匿名化。\n\n\u003Csummary> 匿名化 \u003C\u002Fsummary>\n\n1. 分析期间报告的错误：\n\n```bash\n错误：HorizontalPodAutoscaler 使用名为 StatefulSet\u002Ffake-deployment 的 ScaleTargetRef，但该对象不存在。\n```\n\n2. 发送到 AI 后端的数据负载：\n\n```bash\n错误：HorizontalPodAutoscaler 使用名为 StatefulSet\u002FtGLcCRcHa1Ce5Rs 的 ScaleTargetRef，但该对象不存在。\n```\n\n3. AI 返回的数据负载：\n\n```bash\nKubernetes 系统正尝试使用 HorizontalPodAutoscaler 扩缩名为 tGLcCRcHa1Ce5Rs 的 StatefulSet，但未能找到该 StatefulSet。解决方法是检查 StatefulSet 名称拼写是否正确，并确认其与 HorizontalPodAutoscaler 位于同一命名空间中。\n```\n\n4. 返回给用户的最终数据负载：\n\n```bash\nKubernetes 系统正尝试使用 HorizontalPodAutoscaler 扩缩名为 fake-deployment 的 StatefulSet，但未能找到该 StatefulSet。解决方法是检查 StatefulSet 名称拼写是否正确，并确认其与 HorizontalPodAutoscaler 位于同一命名空间中。\n```\n\n### 更多细节\n\n注意：**匿名化目前不适用于事件。**\n\n_在一些分析器中，例如 Pod，我们会将事先未知的事件消息传递给 AI 后端，因此我们暂时不会对这些消息进行掩码处理。_\n\n- 以下列出了正在被掩码的数据分析器：-\n\n  - Statefulset\n  - Service\n  - PodDisruptionBudget\n  - Node\n  - NetworkPolicy\n  - Ingress\n  - HPA\n  - Deployment\n  - Cronjob\n\n- 以下列出了尚未被掩码的数据分析器：-\n\n  - ReplicaSet\n  - PersistentVolumeClaim\n  - Pod\n  - Log\n  - **_\\*事件_**\n\n**\\*注**：\n\n- k8gpt 不会对上述分析器进行掩码处理，因为它们不会发送任何可识别信息，除了 **事件** 分析器。\n- 对 **事件** 分析器的掩码处理计划在不久的将来实施，具体可见此[议题](https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fk8sgpt\u002Fissues\u002F560)。还需要进一步研究以了解模式，并能够对事件中的敏感部分（如 Pod 名称、命名空间等）进行掩码处理。\n\n- 以下列出了尚未被掩码的字段：-\n\n  - Describe\n  - ObjectStatus\n  - Replicas\n  - ContainerStatus\n  - **_\\*事件消息_**\n  - ReplicaStatus\n  - Count (Pod)\n\n**\\*注**：\n\n- 事件消息的内容很可能包含类似“超级秘密项目 Pod-X 崩溃”的信息，而我们目前尚未对其进行脱敏处理（计划在不久的将来实施，具体见此[议题](https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fk8sgpt\u002Fissues\u002F560)）。\n\n### 请谨慎操作\n\n- K8gpt 团队建议在关键生产环境中使用完全不同的后端 **（本地模型）**。通过使用本地模型，您可以确保所有数据都保留在您的 DMZ 内，不会发生任何数据泄露。\n- 如果对是否可能将数据发送到公共 LLM（如 OpenAI、Azure AI）存在不确定性，并且这会对业务关键操作构成风险，则在这种情况下，应根据个人评估和所涉及的风险管辖范围，避免使用公共 LLM。\n\n\u003C\u002Fdetails>\n\n\u003Cdetails>\n\u003Csummary> 配置管理\u003C\u002Fsummary>\n\n`k8sgpt` 将配置数据存储在 `$XDG_CONFIG_HOME\u002Fk8sgpt\u002Fk8sgpt.yaml` 文件中。这些数据以明文形式存储，包括您的 OpenAI 密钥。\n\n配置文件位置：\n| 操作系统 | 路径 |\n| ------- | ------------------------------------------------ |\n| MacOS | ~\u002FLibrary\u002FApplication Support\u002Fk8sgpt\u002Fk8sgpt.yaml |\n| Linux | ~\u002F.config\u002Fk8sgpt\u002Fk8sgpt.yaml |\n| Windows | %LOCALAPPDATA%\u002Fk8sgpt\u002Fk8sgpt.yaml |\n\n\u003C\u002Fdetails>\n\n\u003Cdetails>\n在某些场景下，可能更倾向于使用远程缓存。\n在这种情况下，K8sGPT 支持与 AWS S3 或 Azure Blob 存储集成。\n\n\u003Csummary> 远程缓存 \u003C\u002Fsummary>\n\u003Cem>注意：您一次只能配置并使用一个远程缓存\u003C\u002Fem>\n\n_添加远程缓存_\n\n- AWS S3\n  - _作为前提条件，需要设置 `AWS_ACCESS_KEY_ID` 和 `AWS_SECRET_ACCESS_KEY` 环境变量。_\n  - 配置命令：`k8sgpt cache add s3 --region \u003Caws region> --bucket \u003Cname>`\n  - 使用 HTTP 端点的 Minio 配置：` k8sgpt cache add s3 --bucket \u003Cname> --endpoint \u003Chttp:\u002F\u002Flocalhost:9000>`\n  - 使用 HTTPS 端点且跳过 TLS 验证的 Minio 配置：` k8sgpt cache add s3 --bucket \u003Cname> --endpoint \u003Chttps:\u002F\u002Flocalhost:9000> --insecure`\n    - 如果存储桶不存在，K8sGPT 会自动创建它。\n- Azure 存储\n  - 我们支持多种 [方法](https:\u002F\u002Flearn.microsoft.com\u002Fen-us\u002Fazure\u002Fdeveloper\u002Fgo\u002Fazure-sdk-authentication?tabs=bash#2-authenticate-with-azure) 来进行 Azure 身份验证。\n  - 配置命令：`k8sgpt cache add azure --storageacc \u003C存储账户名称> --container \u003C容器名称>`\n    - K8sGPT 假设存储账户已存在，如果容器不存在则会自动创建。\n    - 用户有责任为其身份授予特定权限，以便能够上传 blob 文件并创建 SA 容器（例如 Storage Blob Data Contributor）。\n- Google Cloud Storage\n  - _作为前提条件，需要设置 `GOOGLE_APPLICATION_CREDENTIALS` 环境变量。_\n  - 配置命令：` k8sgpt cache add gcs --region \u003Cgcp region> --bucket \u003Cname> --projectid \u003C项目 ID>`\n    - 如果存储桶不存在，K8sGPT 会自动创建它。\n\n_列出缓存项_\n\n```\nk8sgpt cache list\n```\n\n_从缓存中清除对象_\n注意：使用此命令清除对象会删除上游文件，因此需要适当的权限。\n\n```\nk8sgpt cache purge $OBJECT_NAME\n```\n\n_移除远程缓存_\n注意：这不会删除上游的 S3 存储桶或 Azure 存储容器。\n\n```\nk8sgpt cache remove\n```\n\n\u003C\u002Fdetails>\n\n\u003Cdetails>\n\u003Csummary> 自定义分析器\u003C\u002Fsummary>\n\n在某些场景下，您可能希望用自己选择的语言编写自定义分析器。\nK8sGPT 现在支持通过遵循 [schema](https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fschemas\u002Fblob\u002Fmain\u002Fprotobuf\u002Fschema\u002Fv1\u002Fcustom_analyzer.proto) 并提供该分析器供使用来实现这一功能。\n为此，您只需在 K8sGPT 配置中定义分析器，它就会将其纳入扫描流程。\n此外，您还需要在分析时启用以下标志：\n\n```\nk8sgpt analyze --custom-analysis\n```\n\n这里有一个用 [Rust](https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fhost-analyzer) 编写的本地主机分析器示例。\n当此程序在 `localhost:8080` 上运行时，K8sGPT 配置可以通过以下方式识别并加载它：\n\n```\ncustom_analyzers:\n  - name: host-analyzer\n    connection:\n      url: localhost\n      port: 8080\n```\n\n这样，K8sGPT 就可以接收来自该分析器的主机操作系统信息，并将其作为上下文用于常规分析。\n\n_查看有关如何编写自定义分析器的文档_\n\n_列出已配置的自定义分析器_\n```\nk8sgpt custom-analyzer list\n```\n\n_无需安装即可添加自定义分析器_\n```\nk8sgpt custom-analyzer add --name my-custom-analyzer --port 8085\n```\n\n_移除自定义分析器_\n```\nk8sgpt custom-analyzer remove --names \"my-custom-analyzer,my-custom-analyzer-2\"\n```\n\n\u003C\u002Fdetails>\n## 模型上下文协议 (MCP)\n\nK8sGPT 提供了一个模型上下文协议服务器，它将 Kubernetes 操作暴露为标准化工具，供像 Claude、ChatGPT 等 MCP 兼容客户端使用。\n\n**启动 MCP 服务器：**\n\n标准输入输出模式（适用于本地 AI 助手）：\n```bash\nk8sgpt serve --mcp\n```\n\nHTTP 模式（用于网络访问）：\n```bash\nk8sgpt serve --mcp --mcp-http --mcp-port 8089\n```\n\n**功能：**\n- 12 种用于集群分析、资源管理和调试的工具\n- 3 种用于访问集群信息的资源\n- 3 个交互式故障排除提示\n- 无状态 HTTP 模式，适用于一次性调用\n- 与 Claude Desktop 及其他 MCP 客户端的全面集成\n\n**了解更多：** 请参阅 [MCP.md](MCP.md)，获取完整的文档、使用示例和集成指南。\n## 文档\n\n我们的官方文档可在 [这里](https:\u002F\u002Fdocs.k8sgpt.ai) 找到。\n\n## 贡献\n\n请阅读我们的 [贡献指南](.\u002FCONTRIBUTING.md)。\n\n## 社区\n\n您可以在 [Slack](https:\u002F\u002Fjoin.slack.com\u002Ft\u002Fk8sgpt\u002Fshared_invite\u002Fzt-332vhyaxv-bfjJwHZLXWVCB3QaXafEYQ) 上找到我们。\n\n\u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fk8sgpt\u002Fgraphs\u002Fcontributors\">\n  \u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fk8sgpt-ai_k8sgpt_readme_e213d47ea004.png\" \u002F>\n\u003C\u002Fa>\n\n## 许可证\n\n[![FOSSA Status](https:\u002F\u002Fapp.fossa.com\u002Fapi\u002Fprojects\u002Fgit%2Bgithub.com%2Fk8sgpt-ai%2Fk8sgpt.svg?type=large)](https:\u002F\u002Fapp.fossa.com\u002Fprojects\u002Fgit%2Bgithub.com%2Fk8sgpt-ai%2Fk8sgpt?ref=badge_large)","# k8sgpt 快速上手指南\n\nk8sgpt 是一款用于扫描 Kubernetes 集群、诊断问题并以自然语言提供修复建议的 AI 工具。它将 SRE 经验编码到分析器中，并结合 AI 能力帮助用户快速定位和解决集群问题。\n\n## 环境准备\n\n*   **操作系统**：Linux (Ubuntu\u002FDebian, CentOS\u002FRHEL, Alpine), macOS, Windows\n*   **前置依赖**：\n    *   已配置好 `kubectl` 并能正常访问 Kubernetes 集群\n    *   （可选）Homebrew（macOS\u002FLinux 推荐安装方式）\n    *   AI 提供商 API Key（默认支持 OpenAI，也支持 Azure, Cohere, Amazon Bedrock, Google Gemini 及本地模型）\n\n## 安装步骤\n\n### macOS \u002F Linux (推荐)\n\n使用 Homebrew 安装是最便捷的方式：\n\n```sh\nbrew install k8sgpt\n```\n\n或者通过 Tap 安装：\n\n```sh\nbrew tap k8sgpt-ai\u002Fk8sgpt\nbrew install k8sgpt\n```\n\n### Linux (手动安装)\n\n**Ubuntu\u002FDebian:**\n\n```sh\n# 64位系统\ncurl -LO https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fk8sgpt\u002Freleases\u002Fdownload\u002Fv0.4.31\u002Fk8sgpt_amd64.deb\nsudo dpkg -i k8sgpt_amd64.deb\n```\n\n**CentOS\u002FRHEL\u002FFedora:**\n\n```sh\n# 64位系统\nsudo rpm -ivh https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fk8sgpt\u002Freleases\u002Fdownload\u002Fv0.4.31\u002Fk8sgpt_amd64.rpm\n```\n\n**Alpine:**\n\n```sh\n# 64位系统\nwget https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fk8sgpt\u002Freleases\u002Fdownload\u002Fv0.4.31\u002Fk8sgpt_amd64.apk\napk add --allow-untrusted k8sgpt_amd64.apk\n```\n\n> **注意**：如果在 WSL 或 Linux 上使用 Homebrew 安装失败并提示缺少 gcc，请运行 `sudo apt-get install build-essential` 安装构建依赖。\n\n### Windows\n\n1.  从 [Release 页面](https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fk8sgpt\u002Freleases) 下载对应架构的最新二进制文件。\n2.  解压到指定目录。\n3.  将该目录添加到系统的 `PATH` 环境变量中。\n\n## 基本使用\n\n### 1. 配置 AI 后端\n\nk8sgpt 默认使用 OpenAI。你需要先获取 API Key 并进行配置。\n\n**生成\u002F获取 API Key：**\n你可以运行以下命令打开浏览器链接生成 Key，或直接在 OpenAI 官网获取：\n\n```sh\nk8sgpt generate\n```\n\n**添加认证信息：**\n\n```sh\nk8sgpt auth add\n```\n*   按提示输入 API Key。\n*   或者直接使用 flag 传递：`k8sgpt auth add --password \u003CYOUR_API_KEY>`\n\n> 如果使用其他 AI 提供商（如 Azure, Google Gemini 等），请参考官方文档配置对应的 backend。\n\n### 2. 执行集群分析\n\n**基础扫描：**\n对集群进行快速健康检查：\n\n```sh\nk8sgpt analyze\n```\n\n**获取详细解释：**\n使用 `--explain` 参数，AI 将对发现的问题提供自然语言的详细解释和修复建议：\n\n```sh\nk8sgpt analyze --explain\n```\n\n**结合官方文档：**\n使用 `--with-doc` 参数，在解释的同时附带 Kubernetes 官方文档链接：\n\n```sh\nk8sgpt analyze --explain --with-doc\n```\n\n### 3. 高级用法示例\n\n**指定资源类型过滤：**\n只分析特定资源（如 Service 或 Pod）：\n\n```sh\nk8sgpt analyze --explain --filter=Service\n```\n\n**指定命名空间：**\n只分析特定命名空间下的资源：\n\n```sh\nk8sgpt analyze --explain --filter=Pod --namespace=default\n```\n\n**匿名化输出：**\n如果担心敏感信息泄露，可以使用 `--anonymize` 参数对数据进行脱敏处理：\n\n```sh\nk8sgpt analyze --explain --filter=Service --output=json --anonymize\n```\n\n**管理过滤器：**\n查看、添加或移除默认启用的分析器：\n\n```sh\n# 列出所有可用过滤器\nk8sgpt filters list\n\n# 添加默认过滤器\nk8sgpt filters add Service,Pod\n\n# 移除默认过滤器\nk8sgpt filters remove Service\n```","某电商公司的初级运维工程师小李，在周五下午突然收到生产环境 Kubernetes 集群中核心订单服务频繁重启的告警，急需快速定位并解决问题以恢复业务。\n\n### 没有 k8sgpt 时\n- **排查路径迷茫**：面对 `CrashLoopBackOff` 状态，小李需要手动执行 `kubectl get pods`、`describe` 和 `logs` 等多个命令，在海量日志中盲目搜索错误关键词，效率极低。\n- **专业知识门槛高**：由于缺乏深厚的 SRE 经验，他难以将分散的资源事件（如 OOMKilled、配置错误、依赖服务超时）关联起来，无法判断是代码缺陷还是基础设施问题。\n- **沟通成本高昂**：为了确认根因，他不得不截图各种 YAML 配置和日志片段，紧急呼叫资深架构师介入，导致问题响应时间被拉长，业务中断风险加剧。\n- **心理压力巨大**：在生产故障的高压环境下，人工逐行排查容易出错，且每多一分钟未解决，对公司的损失和个人的考核压力就增加一分。\n\n### 使用 k8sgpt 后\n- **一键智能诊断**：小李只需运行 `k8sgpt analyze`，工具自动扫描集群状态，直接指出订单服务 Pod 重启的具体原因是环境变量配置错误导致数据库连接失败。\n- **自然语言解读**：k8sgpt 将复杂的 Kubernetes 事件和技术术语转化为通俗易懂的英文解释（可配合翻译工具），清晰说明了“为什么出错”以及“哪些资源受影响”，降低了理解门槛。\n- **提供修复建议**：工具不仅给出根因，还基于内置的 SRE 知识库提供了具体的修复步骤，例如建议检查 Secret 名称拼写或更新 Deployment 的环境变量字段。\n- **独立快速闭环**：借助 AI 辅助，小李无需等待专家支援，在 5 分钟内修正配置并重新部署，迅速恢复了服务，极大提升了故障处理的自信和效率。\n\nk8sgpt 通过将资深 SRE 的经验编码化并结合 AI 能力，让普通开发者也能具备专家级的 Kubernetes 故障排查能力，显著缩短平均修复时间（MTTR）。","https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fk8sgpt-ai_k8sgpt_4cd852d3.png","k8sgpt-ai","https:\u002F\u002Foss.gittoolsai.com\u002Favatars\u002Fk8sgpt-ai_fb843f1e.png","",null,"https:\u002F\u002Fk8sgpt.ai","https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai",[83,87,91,94],{"name":84,"color":85,"percentage":86},"Go","#00ADD8",98.9,{"name":88,"color":89,"percentage":90},"Makefile","#427819",0.7,{"name":92,"color":85,"percentage":93},"Go Template",0.2,{"name":95,"color":96,"percentage":93},"Dockerfile","#384d54",7623,969,"2026-04-02T22:10:50","Apache-2.0","Linux, macOS, Windows","未说明",{"notes":104,"python":102,"dependencies":105},"该工具主要作为预编译的二进制文件分发（支持 RPM, DEB, APK, Brew 及 Windows 二进制包），并非 Python 项目。核心运行依赖是能够访问 Kubernetes 集群（通常需要配置 kubeconfig）。AI 功能依赖外部 LLM 提供商（如 OpenAI, Azure, Google Gemini 等）的 API 密钥，或者通过 MCP 协议连接本地\u002F远程模型服务。若在 WSL\u002FLinux 上通过源码构建 Homebrew 公式，可能需要安装 gcc 或 build-essential。",[106,107,108],"Go (语言基础)","kubectl (Kubernetes 命令行工具，隐含依赖)","Claude Desktop (可选，用于 MCP 集成)",[15,14,13,26],[111,112,113,114,115,116,117],"devops","kubernetes","openai","sre","tooling","ai","llama","2026-03-27T02:49:30.150509","2026-04-06T07:16:03.506549",[121,126,131,136,141,146],{"id":122,"question_zh":123,"answer_zh":124,"source_url":125},11327,"在 OpenShift 或启用 SCC 的 Kubernetes 集群中部署 K8sGPT 时，出现 \"mkdir \u002F.config: permission denied\" 错误如何解决？","这是由于容器试图在根目录创建配置文件夹但权限不足导致的。解决方案是修改部署配置：\n1. 添加一个 emptyDir 卷挂载到用户主目录下的 `.config\u002F` 路径。\n2. 设置环境变量 `XDG_CONFIG_HOME` 指向该挂载卷的路径。\n这样可以将配置写入临时卷而不是受限制的根文件系统。维护者已通过 PR #454 在 Helm chart 中修复了此问题，Operator 也需要相应更新以支持创建 emptyDir 卷和设置环境变量。","https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fk8sgpt\u002Fissues\u002F440",{"id":127,"question_zh":128,"answer_zh":129,"source_url":130},11328,"使用 LocalAI 作为后端时，运行 `k8sgpt analyse --explain` 报错 \"401 You didn't provide an API key\" 怎么办？","虽然 LocalAI 是本地模型，但 K8sGPT 的某些实现可能仍尝试发送 API Key 头信息，或者配置未正确识别为无需密钥的模式。确保你的 LocalAI 服务正常运行且可访问。如果问题持续，检查是否混淆了 VLLM 或其他后端配置。有用户分享了结合 K8sGPT 和开源 LLM（如通过 VLLM 或 LocalAI）的博客指南可供参考配置细节。通常需确保后端配置中未强制要求 OpenAI 格式的密钥，或在该字段留空\u002F填写占位符以绕过验证（具体取决于版本实现）。","https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fk8sgpt\u002Fissues\u002F981",{"id":132,"question_zh":133,"answer_zh":134,"source_url":135},11329,"K8sGPT Operator 部署时出现 \"An empty namespace may not be set during creation\" 错误是什么原因？","这是一个已知的 Bug，发生在 K8sGPT Operator v0.3.30 及附近版本。问题在于 Operator 在创建资源时错误地处理了命名空间字段。该问题已在后续版本中修复（参考 PR #449）。请升级 K8sGPT Operator 到最新版本即可解决。","https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fk8sgpt\u002Fissues\u002F1107",{"id":137,"question_zh":138,"answer_zh":139,"source_url":140},11330,"如何为 K8sGPT 编写新的集成（Integration）？是否有相关文档？","目前官方文档中关于编写新集成的步骤较为晦涩且缺乏详细文档。建议先在 K8sGPT Slack 社区寻求帮助以了解当前集成系统的工作原理。现有的 CLI 过滤器文档（https:\u002F\u002Fdocs.k8sgpt.ai\u002Freference\u002Fcli\u002Ffilters\u002F）提供了一些基础信息，但不足以指导完整开发。社区正在计划编写逐步指南以降低贡献门槛。","https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fk8sgpt\u002Fissues\u002F360",{"id":142,"question_zh":143,"answer_zh":144,"source_url":145},11331,"K8sGPT 是否支持本地模型（如 LLaMa, GPT4ALL）？","是的，K8sGPT 已经增加了对本地模型的支持，包括 LLaMa 和 GPT4ALL 等。你可以通过配置相应的后端来使用这些本地运行的模型，而无需依赖云端 API。具体配置方法可参考相关 PR 或社区博客（如结合 LocalAI 或 VLLM 的使用指南）。","https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fk8sgpt\u002Fissues\u002F188",{"id":147,"question_zh":148,"answer_zh":149,"source_url":150},11332,"是否有用于 K8sGPT 的 GitHub Action？","社区曾讨论过创建用于 K8sGPT 的 GitHub Action。虽然该特定 Issue 被关闭，但这可能是因为功能已通过 K8sGPT Operator 或其他方式实现，或者需求发生了变化。建议查看 K8sGPT Operator 仓库或官方文档以获取最新的 CI\u002FCD 集成方案。","https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fk8sgpt\u002Fissues\u002F137",[152,157,162,167,172,177,182,187,192,197,202,207,212,217,222,227,232,237,242,247],{"id":153,"version":154,"summary_zh":155,"released_at":156},61807,"v0.4.31","## [0.4.31](https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fk8sgpt\u002Fcompare\u002Fv0.4.30...v0.4.31)（2026-02-26）\n\n\n### 其他\n\n* 更新了 README 文件（[#1620](https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fk8sgpt\u002Fissues\u002F1620)）（[fd5bba6](https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fk8sgpt\u002Fcommit\u002Ffd5bba6ab3ad7a81ef982f1980ac9c9de23bc46c)）\n\n\n### 文档\n\n* 将 Go 版本与 go.mod 工具链对齐（[#1609](https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fk8sgpt\u002Fissues\u002F1609)）（[19a172e](https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fk8sgpt\u002Fcommit\u002F19a172e575ffba6cd89330479033731426358342)）","2026-03-24T14:02:49",{"id":158,"version":159,"summary_zh":160,"released_at":161},61808,"v0.4.30","## [0.4.30](https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fk8sgpt\u002Fcompare\u002Fv0.4.29...v0.4.30) (2026-02-20)\n\n\n### 错误修复\n\n* 在运行自定义分析器之前验证命名空间 ([#1617](https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fk8sgpt\u002Fissues\u002F1617)) ([458aa9d](https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fk8sgpt\u002Fcommit\u002F458aa9debac7590eb0855ffd12141b702e999a36))","2026-02-20T10:48:05",{"id":163,"version":164,"summary_zh":165,"released_at":166},61809,"v0.4.29","## [0.4.29](https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fk8sgpt\u002Fcompare\u002Fv0.4.28...v0.4.29) (2026-02-20)\n\n\n### 功能特性\n\n* **serve:** 添加指标端口的简短标志和环境变量 ([#1616](https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fk8sgpt\u002Fissues\u002F1616)) ([4f63e97](https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fk8sgpt\u002Fcommit\u002F4f63e9737c6a2306686bd3b6f37e81f210665949))\n\n\n### 错误修复\n\n* **deps:** 更新 k8s.io\u002Futils 的摘要至 b8788ab ([#1572](https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fk8sgpt\u002Fissues\u002F1572)) ([a56e478](https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fk8sgpt\u002Fcommit\u002Fa56e4788c3361a64df17175f163f33422a8fe606))\n* 对 customrest 提示使用正确的 JSON 序列化，以正确处理特殊字符 ([#1615](https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fk8sgpt\u002Fissues\u002F1615)) ([99911fb](https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fk8sgpt\u002Fcommit\u002F99911fbb3ac8c950fd7ee1b3210f8a9c2a6b0ad7)), 关闭 [#1556](https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fk8sgpt\u002Fissues\u002F1556)\n\n\n### 重构\n\n* 改进 MCP 服务器处理器，增强错误处理和分页功能 ([#1613](https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fk8sgpt\u002Fissues\u002F1613)) ([abc4647](https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fk8sgpt\u002Fcommit\u002Fabc46474e372bcd27201f1a64372c04269acee13))","2026-02-20T09:06:33",{"id":168,"version":169,"summary_zh":170,"released_at":171},61810,"v0.4.28","## [0.4.28](https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fk8sgpt\u002Fcompare\u002Fv0.4.27...v0.4.28) (2026-02-15)\n\n\n### 功能特性\n\n* 添加 Groq 作为 LLM 提供商 ([#1600](https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fk8sgpt\u002Fissues\u002F1600)) ([867bce1](https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fk8sgpt\u002Fcommit\u002F867bce1907f5dd3387128b72c694e98091d55554))\n* 多项安全修复。Prometheus：v0.302.1 → v0.306.0 ([#1597](https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fk8sgpt\u002Fissues\u002F1597)) ([f5fb2a7](https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fk8sgpt\u002Fcommit\u002Ff5fb2a7e12e14fad8107940aeead5e60b064add1))\n\n\n### Bug 修复\n\n* 对齐 CI 中的 Go 版本与 go.mod，以确保一致性 ([#1611](https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fk8sgpt\u002Fissues\u002F1611)) ([1f2ff98](https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fk8sgpt\u002Fcommit\u002F1f2ff988342b8ef2aa3e3263eb845c0ee09fe24c))\n* **依赖更新：** 将模块 gopkg.in\u002Fyaml.v2 更新至 v3 ([#1550](https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fk8sgpt\u002Fissues\u002F1550)) ([7fe3bdb](https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fk8sgpt\u002Fcommit\u002F7fe3bdbd952bc9a1975121de5f21ad31dc1f691d))\n* 在 OpenAI 中使用 MaxCompletionTokens 替代已弃用的 MaxTokens ([#1604](https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fk8sgpt\u002Fissues\u002F1604)) ([c80b2e2](https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fk8sgpt\u002Fcommit\u002Fc80b2e2c346845336593ce515fe90fd501b1d0a7))\n\n\n### 其他\n\n* **依赖更新：** 将 actions\u002Fcheckout 的摘要更新至 93cb6ef ([#1592](https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fk8sgpt\u002Fissues\u002F1592)) ([40ffcbe](https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fk8sgpt\u002Fcommit\u002F40ffcbec6b65e3a99e40be5f414a3f2c087bffbb))\n* **依赖更新：** 将 actions\u002Fsetup-go 的摘要更新至 40f1582 ([#1593](https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fk8sgpt\u002Fissues\u002F1593)) ([a303ffa](https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fk8sgpt\u002Fcommit\u002Fa303ffa21c7ede3dd9391185bc91fb3b4e8276b6))\n* 工具测试 ([#1594](https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fk8sgpt\u002Fissues\u002F1594)) ([21369c5](https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fk8sgpt\u002Fcommit\u002F21369c5c0917fd2b6ae4173378b2e257e2b1de7b))","2026-02-15T11:12:01",{"id":173,"version":174,"summary_zh":175,"released_at":176},61811,"v0.4.27","## [0.4.27](https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fk8sgpt\u002Fcompare\u002Fv0.4.26...v0.4.27) (2025-12-18)\n\n\n### 功能\n\n* mcp v2 ([#1589](https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fk8sgpt\u002Fissues\u002F1589)) ([5480051](https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fk8sgpt\u002Fcommit\u002F5480051230ce83b89c0382abd7992c7ecc4a85b8))","2025-12-18T13:52:26",{"id":178,"version":179,"summary_zh":180,"released_at":181},61812,"v0.4.26","## [0.4.26](https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fk8sgpt\u002Fcompare\u002Fv0.4.25...v0.4.26) (2025-10-16)\n\n\n### 其他\n\n* 在 serve 命令中缺少 filter 参数 ([#1583](https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fk8sgpt\u002Fissues\u002F1583)) ([f1d2e30](https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fk8sgpt\u002Fcommit\u002Ff1d2e306f32eb1e01a2788174084be29a7fa1282))","2025-10-16T07:31:25",{"id":183,"version":184,"summary_zh":185,"released_at":186},61813,"v0.4.25","## [0.4.25](https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fk8sgpt\u002Fcompare\u002Fv0.4.24...v0.4.25) (2025-09-03)\n\n\n### 功能特性\n\n* 修复推理中断问题 ([#1575](https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fk8sgpt\u002Fissues\u002F1575)) ([291e42d](https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fk8sgpt\u002Fcommit\u002F291e42dc4b81ffb0672c21fbb325ddebc5d531a3))","2025-09-03T19:09:43",{"id":188,"version":189,"summary_zh":190,"released_at":191},61814,"v0.4.24","## [0.4.24](https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fk8sgpt\u002Fcompare\u002Fv0.4.23...v0.4.24) (2025-08-18)\n\n\n### 功能特性\n\n* 添加 ClusterServiceVersion、Subscription、InstallPlan、OperatorGroup 和 CatalogSource 分析器 ([#1564](https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fk8sgpt\u002Fissues\u002F1564)) ([0cf4cae](https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fk8sgpt\u002Fcommit\u002F0cf4cae07e32a0025246abcf2d1a5a91f82d093a))\n* 重新引入推理代码 ([#1548](https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fk8sgpt\u002Fissues\u002F1548)) ([7e33276](https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fk8sgpt\u002Fcommit\u002F7e332761d89d953989b4f33509208dd4db4d4b91))\n* 更新 Helm Chart，支持 MCP 并修复 Google ADA 问题 ([#1568](https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fk8sgpt\u002Fissues\u002F1568)) ([5334589](https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fk8sgpt\u002Fcommit\u002F53345895deec4c74cac00ee3fd5e230f6a92cf4a))\n\n\n### 错误修复\n\n* 迁移到维护更为活跃的 MCP Go 库，并添加 AI 解释功能 ([#1557](https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fk8sgpt\u002Fissues\u002F1557)) ([c47ae59](https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fk8sgpt\u002Fcommit\u002Fc47ae595fb9fc5bf22afef3bc6764b3e87e4553d))\n\n\n### 其他\n\n* **依赖项：** 将 actions\u002Fcheckout 操作更新至 v5 版本 ([#1562](https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fk8sgpt\u002Fissues\u002F1562)) ([e385e77](https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fk8sgpt\u002Fcommit\u002Fe385e77da93a65fe52a152bf1f8f1415552698d5))\n* **依赖项：** 将 amannn\u002Faction-semantic-pull-request 操作更新至 v6 版本 ([#1565](https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fk8sgpt\u002Fissues\u002F1565)) ([c5c9135](https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fk8sgpt\u002Fcommit\u002Fc5c9135900ec6f95b63dac47df751269e7420e87))\n* **依赖项：** 将 docker\u002Flogin-action 的摘要更新至 184bdaa ([#1559](https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fk8sgpt\u002Fissues\u002F1559)) ([0239b2f](https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fk8sgpt\u002Fcommit\u002F0239b2fe6e7105bbcf3256c559c30ec7065b25f3))\n* **依赖项：** 将 goreleaser\u002Fgoreleaser-action 的摘要更新至 e435ccd ([#1569](https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fk8sgpt\u002Fissues\u002F1569)) ([5e86f49](https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fk8sgpt\u002Fcommit\u002F5e86f4925c4209b0eb2959227229c2994cfc5b6f))","2025-08-24T17:59:55",{"id":193,"version":194,"summary_zh":195,"released_at":196},61815,"v0.4.23","## [0.4.23](https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fk8sgpt\u002Fcompare\u002Fv0.4.22...v0.4.23) (2025-08-08)\n\n\n### 功能特性\n\n* 添加 ClusterCatalog 和 ClusterExtension 分析器 ([#1555](https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fk8sgpt\u002Fissues\u002F1555)) ([a821814](https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fk8sgpt\u002Fcommit\u002Fa821814125e25c062ff2faebf9df1b880414c22c))\n* OCI 生成式 AI 聊天模型 ([#1337](https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fk8sgpt\u002Fissues\u002F1337)) ([290a4be](https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fk8sgpt\u002Fcommit\u002F290a4be210fbb508214070c31218138781d96142))\n\n\n### 错误修复\n\n* **依赖项：** 将模块 gopkg.in\u002Fyaml.v2 更新至 v3 ([#1537](https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fk8sgpt\u002Fissues\u002F1537)) ([50d5d78](https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fk8sgpt\u002Fcommit\u002F50d5d78c06e42d75a2448989528e5e6be12ea825))\n* **依赖项：** 将模块 helm.sh\u002Fhelm\u002Fv3 更新至 v3.17.4 [安全] ([#1541](https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fk8sgpt\u002Fissues\u002F1541)) ([5b42249](https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fk8sgpt\u002Fcommit\u002F5b4224951e7348e9d78292dadc9b9786957117f1))","2025-08-10T06:48:16",{"id":198,"version":199,"summary_zh":200,"released_at":201},61816,"v0.4.22","## [0.4.22](https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fk8sgpt\u002Fcompare\u002Fv0.4.21...v0.4.22) (2025-07-18)\n\n\n### 功能特性\n\n* 为 Amazon Bedrock 添加亚太地区 Claude 模型支持 ([#1543](https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fk8sgpt\u002Fissues\u002F1543)) ([1819e6f](https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fk8sgpt\u002Fcommit\u002F1819e6f410d078fce2bda8bbdb22054dfb4fc092))\n* 为 MCP 服务器添加可流式传输的 HTTP 支持 ([#1546](https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fk8sgpt\u002Fissues\u002F1546)) ([3a1187a](https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fk8sgpt\u002Fcommit\u002F3a1187ad5a190713b9216cf6d9d52d54cdb3e4da))","2025-07-18T14:28:17",{"id":203,"version":204,"summary_zh":205,"released_at":206},61817,"v0.4.21","## [0.4.21](https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fk8sgpt\u002Fcompare\u002Fv0.4.20...v0.4.21) (2025-06-27)\n\n\n### Features\n\n* add latest and legacy stable models ([#1539](https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fk8sgpt\u002Fissues\u002F1539)) ([00c0799](https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fk8sgpt\u002Fcommit\u002F00c07999e2290e70a6ecb95b255b4924f55ecd5f))\n* support for claude4 && model names listed ([#1540](https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fk8sgpt\u002Fissues\u002F1540)) ([8002d94](https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fk8sgpt\u002Fcommit\u002F8002d943453aac8c3675d7072b25dfdc3aec1c1d))\n\n\n### Bug Fixes\n\n* **deps:** update module gopkg.in\u002Fyaml.v2 to v3 ([#1511](https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fk8sgpt\u002Fissues\u002F1511)) ([08f2855](https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fk8sgpt\u002Fcommit\u002F08f2855a4d7e61f3422cb68b0966272a85f617a5))\n\n\n### Other\n\n* **deps:** update docker\u002Fsetup-buildx-action digest to e468171 ([#1527](https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fk8sgpt\u002Fissues\u002F1527)) ([0c917fc](https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fk8sgpt\u002Fcommit\u002F0c917fc60115ef0dc775e858a55964382b20c5e1))","2025-06-27T10:55:26",{"id":208,"version":209,"summary_zh":210,"released_at":211},61818,"v0.4.20","## [0.4.20](https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fk8sgpt\u002Fcompare\u002Fv0.4.19...v0.4.20) (2025-06-20)\n\n\n### Features\n\n* added cache purge ([#1532](https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fk8sgpt\u002Fissues\u002F1532)) ([74fbde0](https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fk8sgpt\u002Fcommit\u002F74fbde00537e627c408b317ff9098227be11e2ad))\n\n\n### Other\n\n* model name ([#1535](https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fk8sgpt\u002Fissues\u002F1535)) ([0f700f0](https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fk8sgpt\u002Fcommit\u002F0f700f0cd39bf5881d6c05240b842f4df7a6c016))","2025-06-20T15:56:30",{"id":213,"version":214,"summary_zh":215,"released_at":216},61819,"v0.4.19","## [0.4.19](https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fk8sgpt\u002Fcompare\u002Fv0.4.18...v0.4.19) (2025-06-20)\n\n\n### Features\n\n* fixed haiku ([#1530](https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fk8sgpt\u002Fissues\u002F1530)) ([5636515](https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fk8sgpt\u002Fcommit\u002F5636515db98b529689a214af5066d50b5e42d3a1))","2025-06-20T12:54:29",{"id":218,"version":219,"summary_zh":220,"released_at":221},61820,"v0.4.18","## [0.4.18](https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fk8sgpt\u002Fcompare\u002Fv0.4.17...v0.4.18) (2025-06-20)\n\n\n### Bug Fixes\n\n* **deps:** update k8s.io\u002Futils digest to 4c0f3b2 ([#1523](https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fk8sgpt\u002Fissues\u002F1523)) ([7d4cb26](https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fk8sgpt\u002Fcommit\u002F7d4cb267130f60088350213482795f37594cb0bc))\n* **deps:** update module gopkg.in\u002Fyaml.v2 to v3 ([#1509](https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fk8sgpt\u002Fissues\u002F1509)) ([d7cb19a](https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fk8sgpt\u002Fcommit\u002Fd7cb19ad29c92eaba552ba723945c937fc3c42da))\n\n\n### Other\n\n* **deps:** update codecov\u002Fcodecov-action digest to 18283e0 ([#1513](https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fk8sgpt\u002Fissues\u002F1513)) ([42654e7](https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fk8sgpt\u002Fcommit\u002F42654e7f55d7a9e9be5b664adaaa8979106e7298))\n* **deps:** update docker\u002Fbuild-push-action digest to 1dc7386 ([#1512](https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fk8sgpt\u002Fissues\u002F1512)) ([dfcc5dc](https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fk8sgpt\u002Fcommit\u002Fdfcc5dc5a15a3d59a7f6317944784e3ecd86fb50))\n* **deps:** update docker\u002Fbuild-push-action digest to 2634353 ([#1517](https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fk8sgpt\u002Fissues\u002F1517)) ([7dfe8be](https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fk8sgpt\u002Fcommit\u002F7dfe8bef0face65f607475a6620923fdfed57961))\n* **deps:** update softprops\u002Faction-gh-release digest to 72f2c25 ([#1526](https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fk8sgpt\u002Fissues\u002F1526)) ([5947876](https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fk8sgpt\u002Fcommit\u002F5947876e4942729eea883937faf5e2b47d1f16ec))\n* **deps:** update softprops\u002Faction-gh-release digest to d5382d3 ([#1525](https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fk8sgpt\u002Fissues\u002F1525)) ([6b9f346](https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fk8sgpt\u002Fcommit\u002F6b9f346bf668ed3517b23b99000611ea14afafe2))\n* model access ([#1529](https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fk8sgpt\u002Fissues\u002F1529)) ([be4fb1c](https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fk8sgpt\u002Fcommit\u002Fbe4fb1cc034d9c3843cf3e9912a26e05bd54c146))","2025-06-20T12:29:10",{"id":223,"version":224,"summary_zh":225,"released_at":226},61821,"v0.4.17","## [0.4.17](https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fk8sgpt\u002Fcompare\u002Fv0.4.16...v0.4.17) (2025-05-14)\n\n\n### Features\n\n* adding fixes for Messages API issue 1391 ([#1504](https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fk8sgpt\u002Fissues\u002F1504)) ([b2241c0](https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fk8sgpt\u002Fcommit\u002Fb2241c03c975aeab02897d73e57cd351f60f3af3))\n* new job analyzer ([#1506](https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fk8sgpt\u002Fissues\u002F1506)) ([0b7ddf5](https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fk8sgpt\u002Fcommit\u002F0b7ddf5e3b93e56ea92dfb6447e97c067cad9e54))\n\n\n### Bug Fixes\n\n* align documentation to reflect default analyzers properly ([#1498](https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fk8sgpt\u002Fissues\u002F1498)) ([7e375a3](https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fk8sgpt\u002Fcommit\u002F7e375a30bee24198f9221e4a4aea17fcd2fe005c))\n* **deps:** update module gopkg.in\u002Fyaml.v2 to v3 ([#1454](https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fk8sgpt\u002Fissues\u002F1454)) ([d0f0364](https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fk8sgpt\u002Fcommit\u002Fd0f03641ae372a00cd0eca1f41ef30a988d436bc))\n* **deps:** update module gopkg.in\u002Fyaml.v2 to v3 ([#1500](https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fk8sgpt\u002Fissues\u002F1500)) ([d308c51](https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fk8sgpt\u002Fcommit\u002Fd308c511fbe06e012c641dfa08c4dcf4181b243a))\n* panic in k8sgpt auth update ([#1497](https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fk8sgpt\u002Fissues\u002F1497)) ([cae94e7](https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fk8sgpt\u002Fcommit\u002Fcae94e7b6df1684a3b61af3e7aa0f4e68e8df594))\n\n\n### Other\n\n* **deps:** update actions\u002Fsetup-go digest to d35c59a ([#1495](https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fk8sgpt\u002Fissues\u002F1495)) ([e76bdb0](https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fk8sgpt\u002Fcommit\u002Fe76bdb0c23b7d23972d99661c8fe1bffe5f9f398))\n* **deps:** update golangci\u002Fgolangci-lint-action action to v8 ([#1490](https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fk8sgpt\u002Fissues\u002F1490)) ([1e57b77](https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fk8sgpt\u002Fcommit\u002F1e57b7774c20bda4ae0b0d765278bcd3504cfb33))\n* golangci lint ([#1508](https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fk8sgpt\u002Fissues\u002F1508)) ([4faf77d](https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fk8sgpt\u002Fcommit\u002F4faf77d91a3da8fdd6166ec1c381a151e5846057))","2025-05-14T19:58:10",{"id":228,"version":229,"summary_zh":230,"released_at":231},61822,"v0.4.16","## [0.4.16](https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fk8sgpt\u002Fcompare\u002Fv0.4.15...v0.4.16) (2025-05-06)\n\n\n### Features\n\n* add support for Amazon Bedrock Inference Profiles ([#1492](https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fk8sgpt\u002Fissues\u002F1492)) ([21bc76e](https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fk8sgpt\u002Fcommit\u002F21bc76e5b77524b48f09ef6707204742dcd879a7))\n* enhancement of deployment analyzer ([#1406](https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fk8sgpt\u002Fissues\u002F1406)) ([61b60d5](https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fk8sgpt\u002Fcommit\u002F61b60d5768b54f98232dcc415e89aa38987dc6e3))\n* supported regions govcloud ([#1483](https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fk8sgpt\u002Fissues\u002F1483)) ([752a16c](https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fk8sgpt\u002Fcommit\u002F752a16c40728f42f10ab6c3177cb7e24f44db339))\n\n\n### Bug Fixes\n\n* **deps:** update k8s.io\u002Futils digest to 0f33e8f ([#1484](https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fk8sgpt\u002Fissues\u002F1484)) ([6a81d2c](https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fk8sgpt\u002Fcommit\u002F6a81d2c140f00a405b651d6c6dae5e343ffddb4f))\n\n\n### Other\n\n* **deps:** update docker\u002Fbuild-push-action digest to 14487ce ([#1472](https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fk8sgpt\u002Fissues\u002F1472)) ([81da402](https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fk8sgpt\u002Fcommit\u002F81da402d46e1a1db83a41b717dfb23eb07d2e919))\n* **deps:** update golangci\u002Fgolangci-lint-action digest to 9fae48a ([#1489](https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fk8sgpt\u002Fissues\u002F1489)) ([d5341f3](https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fk8sgpt\u002Fcommit\u002Fd5341f3c0019c1114254ac05f00c743a0354ec0b))","2025-05-06T18:24:45",{"id":233,"version":234,"summary_zh":235,"released_at":236},61823,"v0.4.15","## [0.4.15](https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fk8sgpt\u002Fcompare\u002Fv0.4.14...v0.4.15) (2025-04-29)\n\n\n### Features\n\n* added token for goreleaser ([#1476](https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fk8sgpt\u002Fissues\u002F1476)) ([85935a4](https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fk8sgpt\u002Fcommit\u002F85935a46d8f137b0339435cf19ce7f83ead97f8c))","2025-04-29T11:57:47",{"id":238,"version":239,"summary_zh":240,"released_at":241},61824,"v0.4.14","## [0.4.14](https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fk8sgpt\u002Fcompare\u002Fv0.4.13...v0.4.14) (2025-04-29)\n\n\n### Features\n\n* add MCP support ([#1471](https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fk8sgpt\u002Fissues\u002F1471)) ([e41ffd8](https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fk8sgpt\u002Fcommit\u002Fe41ffd80d01ce7ae1fac9ce7e07344020d8bf914))\n* using modelName will calling completion ([#1469](https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fk8sgpt\u002Fissues\u002F1469)) ([f603948](https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fk8sgpt\u002Fcommit\u002Ff603948935f1c4cb171378634714577205de7b08))","2025-04-29T08:27:04",{"id":243,"version":244,"summary_zh":245,"released_at":246},61825,"v0.4.13","## [0.4.13](https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fk8sgpt\u002Fcompare\u002Fv0.4.12...v0.4.13) (2025-04-22)\n\n\n### Features\n\n* slack announce ([#1466](https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fk8sgpt\u002Fissues\u002F1466)) ([3b6ad06](https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fk8sgpt\u002Fcommit\u002F3b6ad06de1121c870fb486e0fe2bd1f87be16627))\n\n\n### Bug Fixes\n\n* reverse hpa ScalingLimited error condition ([#1366](https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fk8sgpt\u002Fissues\u002F1366)) ([ebb0373](https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fk8sgpt\u002Fcommit\u002Febb0373f69ad64a6cc43d0695d07e1d076c6366e))\n\n\n### Other\n\n* **deps:** update softprops\u002Faction-gh-release digest to da05d55 ([#1464](https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fk8sgpt\u002Fissues\u002F1464)) ([4434699](https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fk8sgpt\u002Fcommit\u002F443469960a6b6791e358ee0a97e4c1dc5c3018e6))","2025-04-22T10:28:44",{"id":248,"version":249,"summary_zh":250,"released_at":251},61826,"v0.4.12","## [0.4.12](https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fk8sgpt\u002Fcompare\u002Fv0.4.11...v0.4.12) (2025-04-17)\n\n\n### Features\n\n* new analyzers ([#1459](https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fk8sgpt\u002Fissues\u002F1459)) ([a128906](https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fk8sgpt\u002Fcommit\u002Fa128906136431189812d4d2dea68ea98cbfe5eeb))\n\n\n### Bug Fixes\n\n* **deps:** update module golang.org\u002Fx\u002Fnet to v0.38.0 [security] ([#1462](https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fk8sgpt\u002Fissues\u002F1462)) ([e588fc3](https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fk8sgpt\u002Fcommit\u002Fe588fc316d29a29a7dde6abe2302833b38f1d302))\n\n\n### Other\n\n* **deps:** update codecov\u002Fcodecov-action digest to ad3126e ([#1456](https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fk8sgpt\u002Fissues\u002F1456)) ([0553b98](https:\u002F\u002Fgithub.com\u002Fk8sgpt-ai\u002Fk8sgpt\u002Fcommit\u002F0553b984b7c87b345f171bf6e5d632d890db689c))","2025-04-17T19:57:24"]