[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"similar-plandex-ai--plandex":3,"tool-plandex-ai--plandex":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":69,"readme_en":70,"readme_zh":71,"quickstart_zh":72,"use_case_zh":73,"hero_image_url":74,"owner_login":75,"owner_name":75,"owner_avatar_url":76,"owner_bio":77,"owner_company":78,"owner_location":78,"owner_email":79,"owner_twitter":78,"owner_website":78,"owner_url":80,"languages":81,"stars":119,"forks":120,"last_commit_at":121,"license":122,"difficulty_score":10,"env_os":123,"env_gpu":124,"env_ram":124,"env_deps":125,"category_tags":127,"github_topics":128,"view_count":145,"oss_zip_url":78,"oss_zip_packed_at":78,"status":16,"created_at":146,"updated_at":147,"faqs":148,"releases":163},1211,"plandex-ai\u002Fplandex","plandex","Open source AI coding agent. Designed for large projects and real world tasks.","Plandex是一个开源的AI编码代理，专为大型项目和真实世界任务设计。它能帮你规划和执行跨越多个文件的复杂编码任务，比如开发新功能或修复大型代码库中的问题。传统AI工具常在项目规模增大或任务复杂时失效，Plandex通过智能上下文管理（支持高达200万token的上下文）和累积差异审查沙盒，安全隔离AI生成的更改，直到你确认后再应用。你可以无缝集成Anthropic、OpenAI等主流模型，实现从规划到自动调试的全流程自动化。Plandex特别适合处理大型项目的开发者，让你在终端中高效工作，避免项目混乱，轻松驾驭AI辅助开发。","\u003Ch1 align=\"center\">\r\n \u003Ca href=\"https:\u002F\u002Fplandex.ai\">\r\n  \u003Cpicture>\r\n    \u003Csource media=\"(prefers-color-scheme: dark)\" srcset=\"images\u002Fplandex-logo-dark-v2.png\"\u002F>\r\n    \u003Csource media=\"(prefers-color-scheme: light)\" srcset=\"images\u002Fplandex-logo-light-v2.png\"\u002F>\r\n    \u003Cimg width=\"400\" src=\"images\u002Fplandex-logo-dark-bg-v2.png\"\u002F>\r\n \u003C\u002Fa>\r\n \u003Cbr \u002F>\r\n\u003C\u002Fh1>\r\n\u003Cbr \u002F>\r\n\r\n\u003Cdiv align=\"center\">\r\n\r\n\u003Cp align=\"center\">\r\n  \u003C!-- Call to Action Links -->\r\n  \u003Ca href=\"#install\">\r\n    \u003Cb>30-Second Install\u003C\u002Fb>\r\n  \u003C\u002Fa>\r\n   ·\r\n  \u003Ca href=\"https:\u002F\u002Fplandex.ai\">\r\n    \u003Cb>Website\u003C\u002Fb>\r\n  \u003C\u002Fa>\r\n   ·\r\n  \u003Ca href=\"https:\u002F\u002Fdocs.plandex.ai\u002F\">\r\n    \u003Cb>Docs\u003C\u002Fb>\r\n  \u003C\u002Fa>\r\n   ·\r\n  \u003Ca href=\"#examples-\">\r\n    \u003Cb>Examples\u003C\u002Fb>\r\n  \u003C\u002Fa>\r\n   ·\r\n  \u003Ca href=\"https:\u002F\u002Fdocs.plandex.ai\u002Fhosting\u002Fself-hosting\u002Flocal-mode-quickstart\">\r\n    \u003Cb>Local Self-Hosted Mode\u003C\u002Fb>\r\n  \u003C\u002Fa>\r\n\u003C\u002Fp>\r\n\r\n\u003Cbr>\r\n\r\n[![Discord](https:\u002F\u002Fimg.shields.io\u002Fdiscord\u002F1214825831973785600.svg?style=flat&logo=discord&label=Discord&refresh=1)](https:\u002F\u002Fdiscord.gg\u002Fplandex-ai)\r\n[![GitHub Repo stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fplandex-ai\u002Fplandex?style=social)](https:\u002F\u002Fgithub.com\u002Fplandex-ai\u002Fplandex)\r\n[![Twitter Follow](https:\u002F\u002Fimg.shields.io\u002Ftwitter\u002Ffollow\u002FPlandexAI?style=social)](https:\u002F\u002Ftwitter.com\u002FPlandexAI)\r\n\r\n\u003C\u002Fdiv>\r\n\r\n\u003Cp align=\"center\">\r\n  \u003C!-- Badges -->\r\n\u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fplandex-ai\u002Fplandex\u002Fpulls\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FPRs-welcome-brightgreen.svg\" alt=\"PRs Welcome\" \u002F>\u003C\u002Fa> \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fplandex-ai\u002Fplandex\u002Freleases?q=cli\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fv\u002Frelease\u002Fplandex-ai\u002Fplandex?filter=cli*\" alt=\"Release\" \u002F>\u003C\u002Fa>\r\n\u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fplandex-ai\u002Fplandex\u002Freleases?q=server\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fv\u002Frelease\u002Fplandex-ai\u002Fplandex?filter=server*\" alt=\"Release\" \u002F>\u003C\u002Fa>\r\n\r\n  \u003C!-- \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fyour_username\u002Fyour_project\u002Fissues\">\r\n    \u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fissues-closed\u002Fyour_username\u002Fyour_project.svg\" alt=\"Issues Closed\" \u002F>\r\n  \u003C\u002Fa> -->\r\n\r\n\u003C\u002Fp>\r\n\r\n\u003Cbr \u002F>\r\n\r\n\u003Cdiv align=\"center\">\r\n\u003Ca href=\"https:\u002F\u002Ftrendshift.io\u002Frepositories\u002F8994\" target=\"_blank\">\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fplandex-ai_plandex_readme_4a68feb902da.png\" alt=\"plandex-ai%2Fplandex | Trendshift\" style=\"width: 250px; height: 55px;\" width=\"250\" height=\"55\"\u002F>\u003C\u002Fa>\r\n\u003C\u002Fdiv>\r\n\r\n\u003Cbr>\r\n\r\n\u003Ch1 align=\"center\" >\r\n  An AI coding agent designed for large tasks and real world projects.\u003Cbr\u002F>\u003Cbr\u002F>\r\n\u003C\u002Fh1>\r\n\r\n\u003C!-- \u003Ch2 align=\"center\">\r\n  Designed for large tasks and real world projects.\u003Cbr\u002F>\u003Cbr\u002F>\r\n  \u003C\u002Fh2> -->\r\n  \u003Cbr\u002F>\r\n\r\n\u003Cdiv align=\"center\">\r\n  \u003Ca href=\"https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=SFSu2vNmlLk\">\r\n    \u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fplandex-ai_plandex_readme_6cb7be028cce.png\" alt=\"Plandex v2 Demo Video\" width=\"800\">\r\n  \u003C\u002Fa>\r\n\u003C\u002Fdiv>\r\n\r\n\u003Cbr\u002F>\r\n\r\n💻  Plandex is a terminal-based AI development tool that can **plan and execute** large coding tasks that span many steps and touch dozens of files. It can handle up to 2M tokens of context directly (~100k per file), and can index directories with 20M tokens or more using tree-sitter project maps.\r\n\r\n🔬  **A cumulative diff review sandbox** keeps AI-generated changes separate from your project files until they are ready to go. Command execution is controlled so you can easily roll back and debug. Plandex helps you get the most out of AI without leaving behind a mess in your project.\r\n\r\n🧠  **Combine the best models** from Anthropic, OpenAI, Google, and open source providers to build entire features and apps with a robust terminal-based workflow.\r\n\r\n🚀  Plandex is capable of \u003Cstrong>full autonomy\u003C\u002Fstrong>—it can load relevant files, plan and implement changes, execute commands, and automatically debug—but it's also highly flexible and configurable, giving developers fine-grained control and a step-by-step review process when needed.\r\n\r\n💪  Plandex is designed to be resilient to \u003Cstrong>large projects and files\u003C\u002Fstrong>. If you've found that others tools struggle once your project gets past a certain size or the changes are too complex, give Plandex a shot.\r\n\r\n## Smart context management that works in big projects\r\n\r\n- 🐘 **2M token effective context window** with default model pack. Plandex loads only what's needed for each step.\r\n\r\n- 🗄️ **Reliable in large projects and files.** Easily generate, review, revise, and apply changes spanning dozens of files.\r\n\r\n- 🗺️ **Fast project map generation** and syntax validation with tree-sitter. Supports 30+ languages.\r\n\r\n- 💰 **Context caching** is used across the board for OpenAI, Anthropic, and Google models, reducing costs and latency.\r\n\r\n## Tight control or full autonomy—it's up to you\r\n\r\n- 🚦 **Configurable autonomy:** go from full auto mode to fine-grained control depending on the task.\r\n\r\n- 🐞 **Automated debugging** of terminal commands (like builds, linters, tests, deployments, and scripts). If you have Chrome installed, you can also automatically debug browser applications.\r\n\r\n## Tools that help you get production-ready results\r\n\r\n- 💬 **A project-aware chat mode** that helps you flesh out ideas before moving to implementation. Also great for asking questions and learning about a codebase.\r\n\r\n- 🧠 **Easily try + combine models** from multiple providers. Curated model packs offer different tradeoffs of capability, cost, and speed, as well as open source and provider-specific packs.\r\n\r\n- 🛡️ **Reliable file edits** that prioritize correctness. While most edits are quick and cheap, Plandex validates both syntax and logic as needed, with multiple fallback layers when there are problems.\r\n\r\n- 🔀 **Full-fledged version control** for every update to the plan, including branches for exploring multiple paths or comparing different models.\r\n\r\n- 📂 **Git integration** with commit message generation and optional automatic commits.\r\n\r\n## Dev-friendly, easy to install\r\n\r\n- 🧑‍💻 **REPL mode** with fuzzy auto-complete for commands and file loading. Just run `plandex` in any project to get started.\r\n\r\n- 🛠️ **CLI interface** for scripting or piping data into context.\r\n\r\n- 📦 **One-line, zero dependency CLI install**. Dockerized local mode for easily self-hosting the server. Cloud-hosting options for extra reliability and convenience.\r\n\r\n## Workflow  🔄\r\n\r\n\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fplandex-ai_plandex_readme_e05ce900fc10.png\" alt=\"Plandex workflow\" width=\"100%\"\u002F>\r\n\r\n## Examples  🎥\r\n\r\n  \u003Cbr\u002F>\r\n\r\n\u003Cdiv align=\"center\">\r\n  \u003Ca href=\"https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=g-_76U_nK0Y\">\r\n    \u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fplandex-ai_plandex_readme_97b0cbcc754e.png\" alt=\"Plandex Browser Debugging Example\" width=\"800\">\r\n  \u003C\u002Fa>\r\n\u003C\u002Fdiv>\r\n\r\n\u003Cbr\u002F>\r\n\r\n## Install  📥\r\n\r\n```bash\r\ncurl -sL https:\u002F\u002Fplandex.ai\u002Finstall.sh | bash\r\n```\r\n\r\n**Note:** Windows is supported via [WSL](https:\u002F\u002Flearn.microsoft.com\u002Fen-us\u002Fwindows\u002Fwsl\u002Finstall). Plandex only works correctly on Windows in the WSL shell. It doesn't work in the Windows CMD prompt or PowerShell.\r\n\r\n[More installation options.](https:\u002F\u002Fdocs.plandex.ai\u002Finstall)\r\n\r\n## Hosting  ⚖️\r\n\r\n| Option                     | Description                                                                                                                                                                                                                                                                                                                                                 |\r\n| -------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |\r\n| **Plandex Cloud**          | Winding down as of 10\u002F3\u002F2025 and no longer accepting new users. \u003Ca href=\"https:\u002F\u002Fplandex.ai\u002Fblog\u002Fwinding-down\">Learn more.\u003C\u002Fa>                                                                                                                                                                                                                              |\r\n| **Self-hosted\u002FLocal Mode** | • Run Plandex locally with Docker or host on your own server.\u003Cbr\u002F>• Use your own [OpenRouter.ai](https:\u002F\u002Fopenrouter.ai) key (or [other model provider](https:\u002F\u002Fdocs.plandex.ai\u002Fmodels\u002Fmodel-providers) accounts and API keys).\u003Cbr\u002F>• Follow the [local-mode quickstart](https:\u002F\u002Fdocs.plandex.ai\u002Fhosting\u002Fself-hosting\u002Flocal-mode-quickstart) to get started. |\r\n\r\n## Provider keys  🔑\r\n\r\n\u003C!-- If you're going with a 'BYO API Key' option above (whether cloud or self-hosted), you'll need to set API keys for the [model providers](https:\u002F\u002Fdocs.plandex.ai\u002Fmodels\u002Fmodel-providers) you're using: -->\r\n\r\n```bash\r\nexport OPENROUTER_API_KEY=... # if using OpenRouter.ai\r\n```\r\n\r\n\u003Cbr\u002F>\r\n\r\n## Claude Pro\u002FMax subscription  🖇️\r\n\r\nIf you have a Claude Pro or Max subscription, Plandex can use it when calling Anthropic models. You'll be asked if you want to connect a subscription the first time you run Plandex.\r\n\r\n\u003Cbr\u002F>\r\n\r\n## Get started  🚀\r\n\r\nFirst, `cd` into a **project directory** where you want to get something done or chat about the project. Make a new directory first with `mkdir your-project-dir` if you're starting on a new project.\r\n\r\n```bash\r\ncd your-project-dir\r\n```\r\n\r\nFor a new project, you might also want to initialize a git repo. Plandex doesn't require that your project is in a git repo, but it does integrate well with git if you use it.\r\n\r\n```bash\r\ngit init\r\n```\r\n\r\nNow start the Plandex REPL in your project:\r\n\r\n```bash\r\nplandex\r\n```\r\n\r\nor for short:\r\n\r\n```bash\r\npdx\r\n```\r\n\r\n\u003C!-- ☁️ _If you're using Plandex Cloud, you'll be prompted at this point to start a trial._\r\n\r\nThen just give the REPL help text a quick read, and you're ready go. The REPL starts in _chat mode_ by default, which is good for fleshing out ideas before moving to implementation. Once the task is clear, Plandex will prompt you to switch to _tell mode_ to make a detailed plan and start writing code. -->\r\n\r\n\u003Cbr\u002F>\r\n\r\n## Docs  🛠️\r\n\r\n### [👉  Full documentation.](https:\u002F\u002Fdocs.plandex.ai\u002F)\r\n\r\n\u003Cbr\u002F>\r\n\r\n## Discussion and discord  💬\r\n\r\nPlease feel free to give your feedback, ask questions, report a bug, or just hang out:\r\n\r\n- [Discord](https:\u002F\u002Fdiscord.gg\u002Fplandex-ai)\r\n- [Discussions](https:\u002F\u002Fgithub.com\u002Fplandex-ai\u002Fplandex\u002Fdiscussions)\r\n- [Issues](https:\u002F\u002Fgithub.com\u002Fplandex-ai\u002Fplandex\u002Fissues)\r\n\r\n## Follow and subscribe\r\n\r\n- [Follow @PlandexAI](https:\u002F\u002Fx.com\u002FPlandexAI)\r\n- [Follow @Danenania](https:\u002F\u002Fx.com\u002FDanenania) (Plandex's creator)\r\n- [Subscribe on YouTube](https:\u002F\u002Fx.com\u002FPlandexAI)\r\n\r\n\u003Cbr\u002F>\r\n\r\n## Contributors  👥\r\n\r\n⭐️  Please star, fork, explore, and contribute to Plandex. There's a lot of work to do and so much that can be improved.\r\n\r\n[Here's an overview on setting up a development environment.](https:\u002F\u002Fdocs.plandex.ai\u002Fdevelopment)\r\n","\u003Ch1 align=\"center\">\r\n \u003Ca href=\"https:\u002F\u002Fplandex.ai\">\r\n  \u003Cpicture>\r\n    \u003Csource media=\"(prefers-color-scheme: dark)\" srcset=\"images\u002Fplandex-logo-dark-v2.png\"\u002F>\r\n    \u003Csource media=\"(prefers-color-scheme: light)\" srcset=\"images\u002Fplandex-logo-light-v2.png\"\u002F>\r\n    \u003Cimg width=\"400\" src=\"images\u002Fplandex-logo-dark-bg-v2.png\"\u002F>\r\n \u003C\u002Fa>\r\n \u003Cbr \u002F>\r\n\u003C\u002Fh1>\r\n\u003Cbr \u002F>\r\n\r\n\u003Cdiv align=\"center\">\r\n\r\n\u003Cp align=\"center\">\r\n  \u003C!-- 行动号召链接 -->\r\n  \u003Ca href=\"#install\">\r\n    \u003Cb>30秒安装\u003C\u002Fb>\r\n  \u003C\u002Fa>\r\n   ·\r\n  \u003Ca href=\"https:\u002F\u002Fplandex.ai\">\r\n    \u003Cb>官网\u003C\u002Fb>\r\n  \u003C\u002Fa>\r\n   ·\r\n  \u003Ca href=\"https:\u002F\u002Fdocs.plandex.ai\u002F\">\r\n    \u003Cb>文档\u003C\u002Fb>\r\n  \u003C\u002Fa>\r\n   ·\r\n  \u003Ca href=\"#examples-\">\r\n    \u003Cb>示例\u003C\u002Fb>\r\n  \u003C\u002Fa>\r\n   ·\r\n  \u003Ca href=\"https:\u002F\u002Fdocs.plandex.ai\u002Fhosting\u002Fself-hosting\u002Flocal-mode-quickstart\">\r\n    \u003Cb>本地自托管模式\u003C\u002Fb>\r\n  \u003C\u002Fa>\r\n\u003C\u002Fp>\r\n\r\n\u003Cbr>\r\n\r\n[![Discord](https:\u002F\u002Fimg.shields.io\u002Fdiscord\u002F1214825831973785600.svg?style=flat&logo=discord&label=Discord&refresh=1)](https:\u002F\u002Fdiscord.gg\u002Fplandex-ai)\r\n[![GitHub仓库星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fplandex-ai\u002Fplandex?style=social)](https:\u002F\u002Fgithub.com\u002Fplandex-ai\u002Fplandex)\r\n[![Twitter关注](https:\u002F\u002Fimg.shields.io\u002Ftwitter\u002Ffollow\u002FPlandexAI?style=social)](https:\u002F\u002Ftwitter.com\u002FPlandexAI)\r\n\r\n\u003C\u002Fdiv>\r\n\r\n\u003Cp align=\"center\">\r\n  \u003C!-- 徽章 -->\r\n\u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fplandex-ai\u002Fplandex\u002Fpulls\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FPRs-welcome-brightgreen.svg\" alt=\"欢迎提交PR\" \u002F>\u003C\u002Fa> \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fplandex-ai\u002Fplandex\u002Freleases?q=cli\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fv\u002Frelease\u002Fplandex-ai\u002Fplandex?filter=cli*\" alt=\"发布版本\" \u002F>\u003C\u002Fa>\r\n\u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fplandex-ai\u002Fplandex\u002Freleases?q=server\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fv\u002Frelease\u002Fplandex-ai\u002Fplandex?filter=server*\" alt=\"发布版本\" \u002F>\u003C\u002Fa>\r\n\r\n  \u003C!-- \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fyour_username\u002Fyour_project\u002Fissues\">\r\n    \u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fissues-closed\u002Fyour_username\u002Fyour_project.svg\" alt=\"已关闭的问题\" \u002F>\r\n  \u003C\u002Fa> -->\r\n\r\n\u003C\u002Fp>\r\n\r\n\u003Cbr \u002F>\r\n\r\n\u003Cdiv align=\"center\">\r\n\u003Ca href=\"https:\u002F\u002Ftrendshift.io\u002Frepositories\u002F8994\" target=\"_blank\">\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fplandex-ai_plandex_readme_4a68feb902da.png\" alt=\"plandex-ai%2Fplandex | Trendshift\" style=\"width: 250px; height: 55px;\" width=\"250\" height=\"55\"\u002F>\u003C\u002Fa>\r\n\u003C\u002Fdiv>\r\n\r\n\u003Cbr>\r\n\r\n\u003Ch1 align=\"center\" >\r\n  一款专为大型任务和真实世界项目设计的AI编码助手。\u003Cbr\u002F>\u003Cbr\u002F>\r\n\u003C\u002Fh1>\r\n\r\n\u003C!-- \u003Ch2 align=\"center\">\r\n  专为大型任务和真实世界项目设计。\u003Cbr\u002F>\u003Cbr\u002F>\r\n  \u003C\u002Fh2> -->\r\n  \u003Cbr\u002F>\r\n\r\n\u003Cdiv align=\"center\">\r\n  \u003Ca href=\"https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=SFSu2vNmlLk\">\r\n    \u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fplandex-ai_plandex_readme_6cb7be028cce.png\" alt=\"Plandex v2 演示视频\" width=\"800\">\r\n  \u003C\u002Fa>\r\n\u003C\u002Fdiv>\r\n\r\n\u003Cbr\u002F>\r\n\r\n💻  Plandex是一款基于终端的AI开发工具，能够**规划并执行**涉及多步骤、触及数十个文件的大型编码任务。它可直接处理高达200万token的上下文（约每文件10万token），并通过Tree-Sitter项目映射索引包含2000万token或更多内容的目录。\n\n🔬  **累积差异审查沙盒**会将AI生成的更改与您的项目文件隔离开来，直到它们准备就绪。命令执行受到严格控制，因此您可以轻松回滚和调试。Plandex帮助您充分利用AI的能力，同时不会在项目中留下混乱的痕迹。\n\n🧠  **结合Anthropic、OpenAI、Google以及开源提供商的最佳模型**，借助稳健的终端工作流构建完整的功能和应用程序。\n\n🚀  Plandex具备\u003C强>完全自主性\u003C\u002F强>——它可以加载相关文件、规划并实施更改、执行命令，并自动进行调试——但它也非常灵活且可配置，可在需要时为开发者提供细粒度的控制和逐步审查流程。\n\n💪  Plandex专为应对\u003C强>大型项目和文件\u003C\u002F强>而设计。如果您发现其他工具在项目规模超过一定限度或更改过于复杂时会遇到困难，不妨试试Plandex。\n\n## 适用于大型项目的智能上下文管理\n\n- 🐘 **200万token的有效上下文窗口**，配备默认模型包。Plandex仅加载每一步所需的上下文。\n\n- 🗄️ **在大型项目和文件中表现可靠。** 轻松生成、审查、修改并应用跨越数十个文件的更改。\n\n- 🗺️ **快速生成项目映射**及使用Tree-Sitter进行语法验证。支持30多种语言。\n\n- 💰 **上下文缓存**广泛应用于OpenAI、Anthropic和Google的模型，从而降低费用并减少延迟。\n\n## 紧密控制或完全自主——由您决定\n\n- 🚦 **可配置的自主性：** 根据任务需求，从完全自动模式切换到细粒度控制。\n\n- 🐞 **终端命令的自动化调试**（如构建、代码检查器、测试、部署和脚本）。如果已安装Chrome浏览器，还可以自动调试浏览器应用程序。\n\n## 助力您获得生产就绪成果的工具\n\n- 💬 **项目感知聊天模式**，可在进入实现阶段前帮助您完善想法。也非常适合提问和了解代码库。\n\n- 🧠 **轻松尝试并组合来自不同提供商的模型。** 精选的模型包提供了能力、成本和速度之间的不同权衡，同时还包括开源和特定提供商的模型包。\n\n- 🛡️ **可靠的文件编辑**优先考虑正确性。虽然大多数编辑快速且经济，但Plandex会根据需要验证语法和逻辑，并在出现问题时提供多重后备机制。\n\n- 🔀 **完善的版本控制**，用于计划的每一次更新，包括用于探索多条路径或比较不同模型的分支。\n\n- 📂 **Git集成**，支持生成提交信息，并可选择自动提交。\n\n## 开发者友好，易于安装\n\n- 🧑‍💻 **REPL模式**，具有模糊自动补全功能，可用于输入命令和加载文件。只需在任何项目中运行`plandex`即可开始使用。\n\n- 🛠️ **CLI界面**，可用于编写脚本或将数据导入上下文。\n\n- 📦 **一行命令、零依赖的CLI安装**。提供容器化的本地模式，方便用户自行托管服务器。同时也有云托管选项，以提升可靠性和便利性。\n\n## 工作流程  🔄\r\n\r\n\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fplandex-ai_plandex_readme_e05ce900fc10.png\" alt=\"Plandex工作流程\" width=\"100%\"\u002F>\r\n\r\n## 示例  🎥\r\n\r\n  \u003Cbr\u002F>\r\n\r\n\u003Cdiv align=\"center\">\r\n  \u003Ca href=\"https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=g-_76U_nK0Y\">\r\n    \u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fplandex-ai_plandex_readme_97b0cbcc754e.png\" alt=\"Plandex 浏览器调试示例\" width=\"800\">\r\n  \u003C\u002Fa>\r\n\u003C\u002Fdiv>\r\n\r\n\u003Cbr\u002F>\r\n\r\n## 安装  📥\r\n\r\n```bash\r\ncurl -sL https:\u002F\u002Fplandex.ai\u002Finstall.sh | bash\r\n```\r\n\r\n**注意：** Windows系统可通过[WSL](https:\u002F\u002Flearn.microsoft.com\u002Fen-us\u002Fwindows\u002Fwsl\u002Finstall)支持。Plandex仅在WSL shell中才能正常运行，在Windows CMD提示符或PowerShell中则无法使用。\n\n[更多安装选项。](https:\u002F\u002Fdocs.plandex.ai\u002Finstall)\n\n## 托管  ⚖️\n\n| 选项                     | 描述                                                                                                                                                                                                                                                                                                                                                 |\n| -------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |\n| **Plandex Cloud**          | 自2025年10月3日起逐步停止服务，不再接受新用户。 \u003Ca href=\"https:\u002F\u002Fplandex.ai\u002Fblog\u002Fwinding-down\">了解详情。\u003C\u002Fa>                                                                                                                                                                                                                              |\n| **自托管\u002F本地模式**       | • 使用 Docker 在本地运行 Plandex，或将其部署在您自己的服务器上。\u003Cbr\u002F>• 使用您自己的 [OpenRouter.ai](https:\u002F\u002Fopenrouter.ai) 密钥（或[其他模型提供商](https:\u002F\u002Fdocs.plandex.ai\u002Fmodels\u002Fmodel-providers) 的账户和 API 密钥）。\u003Cbr\u002F>• 按照[本地模式快速入门](https:\u002F\u002Fdocs.plandex.ai\u002Fhosting\u002Fself-hosting\u002Flocal-mode-quickstart) 文档开始使用。 |\n\n## 提供商密钥  🔑\n\n\u003C!-- 如果您选择了上述“自带 API 密钥”的选项（无论是云端还是自托管），则需要为正在使用的[模型提供商](https:\u002F\u002Fdocs.plandex.ai\u002Fmodels\u002Fmodel-providers) 设置 API 密钥： -->\n\n```bash\nexport OPENROUTER_API_KEY=... # 如果使用 OpenRouter.ai\n```\n\n\u003Cbr\u002F>\n\n## Claude Pro\u002FMax 订阅  🖇️\n\n如果您拥有 Claude Pro 或 Max 订阅，Plandex 在调用 Anthropic 模型时可以使用该订阅。首次运行 Plandex 时，系统会询问您是否要连接订阅。\n\n\u003Cbr\u002F>\n\n## 开始使用  🚀\n\n首先，`cd` 到您希望完成任务或讨论项目的**项目目录**中。如果您刚开始一个新项目，请先使用 `mkdir your-project-dir` 创建一个新目录。\n\n```bash\ncd your-project-dir\n```\n\n对于新项目，您可能还想初始化一个 Git 仓库。虽然 Plandex 并不要求您的项目必须位于 Git 仓库中，但如果使用 Git，Plandex 可以很好地与之集成。\n\n```bash\ngit init\n```\n\n现在，在您的项目中启动 Plandex REPL：\n\n```bash\nplandex\n```\n\n或者简写为：\n\n```bash\npdx\n```\n\n\u003C!-- ☁️ _如果您使用的是 Plandex Cloud，此时系统将提示您开始试用。_\n\n然后只需快速阅读一下 REPL 的帮助文档，您就可以开始了。REPL 默认以_聊天模式_启动，这非常适合在进入实现阶段之前梳理思路。一旦任务明确，Plandex 会提示您切换到_指令模式_，以便制定详细计划并开始编写代码。 -->\n\n\u003Cbr\u002F>\n\n## 文档  🛠️\n\n### [👉  完整文档。](https:\u002F\u002Fdocs.plandex.ai\u002F)\n\n\u003Cbr\u002F>\n\n## 讨论与 Discord  💬\n\n欢迎您提出反馈、提问、报告问题，或只是来聊聊天：\n\n- [Discord](https:\u002F\u002Fdiscord.gg\u002Fplandex-ai)\n- [讨论区](https:\u002F\u002Fgithub.com\u002Fplandex-ai\u002Fplandex\u002Fdiscussions)\n- [问题追踪](https:\u002F\u002Fgithub.com\u002Fplandex-ai\u002Fplandex\u002Fissues)\n\n## 关注与订阅\n\n- [关注 @PlandexAI](https:\u002F\u002Fx.com\u002FPlandexAI)\n- [关注 @Danenania](https:\u002F\u002Fx.com\u002FDanenania)（Plandex 的创建者）\n- [订阅 YouTube 频道](https:\u002F\u002Fx.com\u002FPlandexAI)\n\n\u003Cbr\u002F>\n\n## 贡献者  👥\n\n⭐️  请为 Plandex 点赞、叉出、探索并贡献代码。我们还有很多工作要做，也还有许多可以改进的地方。\n\n[这里提供了关于搭建开发环境的概述。](https:\u002F\u002Fdocs.plandex.ai\u002Fdevelopment)","# Plandex 快速上手指南\n\n## 环境准备\n- **系统要求**：Linux\u002FmacOS 推荐。Windows 用户需使用 WSL（Windows Subsystem for Linux），不支持 CMD\u002FPowerShell。\n- **前置依赖**：无额外依赖（安装脚本自动处理）。\n\n## 安装步骤\n```bash\ncurl -sL https:\u002F\u002Fplandex.ai\u002Finstall.sh | bash\n```\n> **注意**：Windows 用户必须在 WSL 终端中运行此命令。\n\n## 基本使用\n1. 创建项目目录并进入：\n   ```bash\n   mkdir my-project && cd my-project\n   ```\n2. 初始化 Git（可选但推荐）：\n   ```bash\n   git init\n   ```\n3. 启动 Plandex REPL：\n   ```bash\n   plandex\n   ```\n   或简写：\n   ```bash\n   pdx\n   ```\n\n> 启动后默认进入聊天模式，可直接描述需求（如“添加用户登录功能”），Plandex 会引导你完成任务规划和代码生成。","某电商公司后端团队正维护一个包含500+文件的用户认证系统，需重构登录流程以支持多因素认证，涉及数据库模型、API接口和前端集成，原方案依赖人工操作。\n\n### 没有 plandex 时\n- - 人工逐文件修改，易遗漏关联逻辑（如数据库迁移和API验证），导致功能冲突。\n- - 项目规模庞大，开发人员频繁切换上下文，需反复查阅文档，效率低下。\n- - 生成代码后需手动测试和调试，耗时数小时且易引入新Bug。\n- - 修改直接写入主分支，无法安全回滚，线上故障风险高。\n\n### 使用 plandex 后\n- - 自动规划任务路径，精准覆盖所有相关文件（如`auth\u002Fmodels.py`和`api\u002Froutes.py`），确保变更完整无遗漏。\n- - 智能处理20M tokens项目上下文，轻松管理500+文件的代码依赖，无需反复查阅文档。\n- - 生成代码在沙盒中预览，通过累积diff审查确认无误后才合并，避免直接污染项目。\n- - 命令执行受控，可一键回滚或调试，将调试时间从数小时缩短至分钟级。\n\nplandex让大型重构从高风险操作变为安全、高效的自动化流程，开发者能专注核心逻辑而非琐碎维护。","https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fplandex-ai_plandex_6cb7be02.png","plandex-ai","https:\u002F\u002Foss.gittoolsai.com\u002Favatars\u002Fplandex-ai_2a756531.png","",null,"support@plandex.ai","https:\u002F\u002Fgithub.com\u002Fplandex-ai",[82,86,90,94,98,102,106,109,112,116],{"name":83,"color":84,"percentage":85},"Go","#00ADD8",93.4,{"name":87,"color":88,"percentage":89},"Shell","#89e051",1.5,{"name":91,"color":92,"percentage":93},"TypeScript","#3178c6",0.6,{"name":95,"color":96,"percentage":97},"PLpgSQL","#336790",0.5,{"name":99,"color":100,"percentage":101},"Python","#3572A5",0.4,{"name":103,"color":104,"percentage":105},"C","#555555",0.3,{"name":107,"color":108,"percentage":105},"HTML","#e34c26",{"name":110,"color":111,"percentage":105},"Elixir","#6e4a7e",{"name":113,"color":114,"percentage":115},"PHP","#4F5D95",0.2,{"name":117,"color":118,"percentage":115},"Java","#b07219",15202,1112,"2026-04-05T10:37:54","MIT","Linux, macOS, Windows","未说明",{"notes":126,"python":124,"dependencies":124},"Windows 仅支持 WSL 环境；安装为单行命令，无需依赖；首次运行需设置 API key（如 OPENROUTER_API_KEY）。",[15,26,14,53,13],[129,130,131,132,133,134,135,136,137,138,139,140,141,142,143,144],"ai","ai-developer-tools","gpt-4","llm","openai","ai-agents","ai-tools","cli","developer-tools","polyglot-programming","terminal-based","golang","git","terminal","terminal-ui","command-line",9,"2026-03-27T02:49:30.150509","2026-04-06T05:37:47.579655",[149,154,158],{"id":150,"question_zh":151,"answer_zh":152,"source_url":153},5516,"执行 `tell` 命令时出现 segfault 错误，如何解决？","问题已修复。请使用 `model-packs show` 查看模型包详情，`model-packs update` 更新模型包。若模型包创建后为空，需运行 `set-model` 重新选择模型和规划器。","https:\u002F\u002Fgithub.com\u002Fplandex-ai\u002Fplandex\u002Fissues\u002F217",{"id":155,"question_zh":156,"answer_zh":157,"source_url":153},5517,"模型包创建后总是空的，如何正确配置？","创建模型包后，必须运行 `set-model` 命令重新选择模型和规划器。例如：输入 `set-model`，然后从列表中选择所需模型（如 Google Gemini）和规划器。",{"id":159,"question_zh":160,"answer_zh":161,"source_url":162},5518,"运行时出现 'The AI model stopped streaming with error code 400'，如何解决？","尝试将计划拆分为更小的、聚焦的更改（如仅修改少量文件），避免超过上下文限制。小规模计划通常能避免此错误，等待新版本更新（已计划添加大上下文回退选项）。","https:\u002F\u002Fgithub.com\u002Fplandex-ai\u002Fplandex\u002Fissues\u002F232",[164,169,174,179,184,189,194,199,204,209,214,219,224,229,234,239,244,249,254,259],{"id":165,"version":166,"summary_zh":167,"released_at":168},105045,"server\u002Fv2.2.1","See CLI 2.2.1 release notes.","2025-07-16T16:21:00",{"id":170,"version":171,"summary_zh":172,"released_at":173},105046,"cli\u002Fv2.2.1","## 🖇️  Connect your Claude Pro or Max subscription\n\nIf you have a Claude Pro or Max subscription, Plandex can use it when calling Anthropic models. You can use it in either Integrated Models Mode on Plandex Cloud, or in BYO Key Mode (whether on Cloud or self-hosting).\n\nAssuming you're using Anthropic models (which the default model pack does), you'll be asked if you want to connect your Claude subscription the first time you run Plandex. Follow the instructions to connect.\n\n[Learn more in the docs.](https:\u002F\u002Fdocs.plandex.ai\u002Fmodels\u002Fclaude-subscription)\n\n## 🐞  Bug fixes\n\nFixed an [issue](https:\u002F\u002Fgithub.com\u002Fplandex-ai\u002Fplandex\u002Fissues\u002F291) with custom models and providers.","2025-07-16T16:54:55",{"id":175,"version":176,"summary_zh":177,"released_at":178},105047,"server\u002Fv2.2.0","See CLI 2.2.0 release notes.","2025-07-01T21:21:16",{"id":180,"version":181,"summary_zh":182,"released_at":183},105048,"cli\u002Fv2.2.0","This is a big release that is mainly focused on Plandex's model provider and model config system. It significantly increases model provider flexibility, makes custom model configuration much easier, reduces costs on Cloud, and adds built-in support for Ollama.\n\n## 🔌  Model provider flexibility for BYO key mode\n\n- Now when using Plandex in BYO key mode (either Cloud or self-hosted), you can easily use Plandex with a wide range of built-in model providers.\n\n- Apart from OpenRouter and the OpenAI API (which were already built-in), built-in providers now include:\n  - Anthropic API\n  - Google AI Studio\n  - Google Vertex AI\n  - Azure OpenAI\n  - AWS Bedrock\n  - DeepSeek API\n  - Perplexity API\n  - Ollama (for local models—see below for details)\n\n- See the new [model provider docs](https:\u002F\u002Fdocs.plandex.ai\u002Fmodels\u002Fmodel-providers) for more details.\n\n![plandex-model-providers](https:\u002F\u002Fgithub.com\u002Fplandex-ai\u002Fplandex\u002Fblob\u002Fmain\u002Freleases\u002Fimages\u002Fcli\u002F2.2.0\u002Fnew-providers.gif)\n\n## 🛟  Provider fallback\n\n- When API keys\u002Fcredentials are provided for multiple providers for a model, Plandex will fail over to the last valid provider if the first one fails. This is especially useful when using a direct provider (like OpenAI or Anthropic) alongside OpenRouter. If the direct call fails, Plandex will fall back to OpenRouter, which has its *own* internal fallback system across multiple providers. You get the best of both worlds: direct access by default, with no additional cost or latency, plus multi-layered resilience in case of stability issues.\n\n## 💰  5.5% price reduction for Plandex Cloud Integrated Models mode\n\n- Thanks to the new model provider system described above, Plandex Cloud with Integrated Models mode can now make direct provider calls under the hood rather than defaulting to OpenRouter, which allows us to avoid OpenRouter's 5.5% surcharge on model calls and pass the savings on to you. OpenRouter is still used as a fallback for added resilience.\n\n## ⚙️  JSON-based model config with IDE support\n\n- Plandex now supports JSON-based model config, which make it much easier to try out different models, different settings, and to use custom models, providers, and model packs.\n\n- The new JSON model config system integrates cleanly with your IDE or editor. When you first edit model settings, Plandex will prompt you to set a preferred editor, and the JSON config file will be opened in that editor.\n\n- Model config files use JSON schemas, which allows for autocomplete, validation, and inline documentation\u002Ftype hints in most IDEs and editors.\n\n- Check out the new docs for [model settings](https:\u002F\u002Fdocs.plandex.ai\u002Fmodels\u002Fmodel-settings) and [custom models](https:\u002F\u002Fdocs.plandex.ai\u002Fmodels\u002Fcustom-models) for full details.\n\n### `set-model` and `set-model default` commands\n\n- `set-model` has been simplified to work with the new system. If run without arguments, you'll be prompted to either select a built-in or custom model pack, or to directly edit the current plan's model config inline in JSON. You can also pass it a model pack name (`set-model daily-driver`) or jump straight to the JSON settings with `set-model --json`.\n\n- `set-model default` works the same way, but allows you to configure the default model settings for new plans.\n\n![plandex-model-settings-json](https:\u002F\u002Fgithub.com\u002Fplandex-ai\u002Fplandex\u002Fblob\u002Fmain\u002Freleases\u002Fimages\u002Fcli\u002F2.2.0\u002Fmodel-settings-json.gif)\n\n\n### `models custom` command\n\n- `models custom` is a new all-in-one command for managing custom providers, models, and model packs in one place. It replaces the `models add`, `models delete`, `model-packs create`, `model-packs update`, and `model-packs delete` commands.\n\n- The first time you run it, if you haven't already configured any custom models or model packs, an example config file will be created to get you started. If you *do* already have custom models or model packs configured, the config file will be populated with those models and model packs.\n\n![plandex-custom-models-json](https:\u002F\u002Fgithub.com\u002Fplandex-ai\u002Fplandex\u002Fblob\u002Fmain\u002Freleases\u002Fimages\u002Fcli\u002F2.2.0\u002Fcustom-models-json.gif)\n\n### `models` and `models default` commands\n\n- The `models` and `models default` commands now show simplified output by default, with a new `--all` flag to show all properties.\n\n- These commands also now show all fallback models (for large context, large output, errors, etc.) for each role, including multiple levels of fallback, which previously weren't always included in the output.\n\n## 🦙  Built-in Ollama support\n\n- Plandex now offers built-in support for Ollama, which makes it much easier to use local models. Check out the new [Ollama quickstart](https:\u002F\u002Fdocs.plandex.ai\u002Fmodels\u002Follama) for details.\n\n![plandex-ollama](https:\u002F\u002Fgithub.com\u002Fplandex-ai\u002Fplandex\u002Fblob\u002Fmain\u002Freleases\u002Fimages\u002Fcli\u002F2.2.0\u002Follama.gif)\n\n## 📖  Built-in models and models packs\n\n- The docs now include all built-in [models](https:\u002F\u002Fdocs.plandex.ai\u002Fmodels\u002Fbuilt-in\u002Fbuilt-in-models) and [model packs](https:\u002F\u002Fdocs.plandex.ai\u002Fmodels\u002Fbuilt-in\u002Fbuilt-in-","2025-07-01T21:36:07",{"id":185,"version":186,"summary_zh":187,"released_at":188},105049,"server\u002Fv2.1.8","- Fix for potential hang in file map queue","2025-06-08T19:42:27",{"id":190,"version":191,"summary_zh":192,"released_at":193},105050,"server\u002Fv2.1.7","- Fix for \"conversation summary timestamp not found in conversation\" error (https:\u002F\u002Fgithub.com\u002Fplandex-ai\u002Fplandex\u002Fissues\u002F274)\n- Fix for potential panic\u002Fcrash during plan stream (https:\u002F\u002Fgithub.com\u002Fplandex-ai\u002Fplandex\u002Fissues\u002F275)\n- Better protection against panics\u002Fcrashes in server goroutines across the board","2025-06-04T21:29:11",{"id":195,"version":196,"summary_zh":197,"released_at":198},105051,"server\u002Fv2.1.6+1","See CLI 2.1.6+1 release notes.","2025-05-27T02:42:51",{"id":200,"version":201,"summary_zh":202,"released_at":203},105052,"server\u002Fv2.1.6","See CLI 2.1.6 release notes.","2025-05-27T00:12:18",{"id":205,"version":206,"summary_zh":207,"released_at":208},105053,"cli\u002Fv2.1.6+1","- Error handling fix\n- Fix for some roles in the `daily-driver` model pack that weren't correctly updated to Sonnet 4 in 2.1.6\n- Added fallback from Sonnet 4 to Sonnet 3.7 to deal with occasional provider errors and rate limit issues","2025-05-27T02:49:37",{"id":210,"version":211,"summary_zh":212,"released_at":213},105054,"cli\u002Fv2.1.6","- The newly released Claude Sonnet 4 is now stable in testing, so it now replaces Sonnet 3.7 as the default model for context sizes under 200k across all model packs where 3.7 was previously used.\n- A new `strong-opus` model pack is now available. It uses Claude Opus 4 for planning and coding, and is otherwise the same as the 'strong' pack. Use it with `\\set-model strong-opus` to try it out.\n- The `opus-4-planner` model pack that was introduced in 2.1.5 has been renamed to `opus-planner`, but the old name is still supported. This model pack uses Claude Opus 4 for planning, and the default models for other roles.\n- Fix for occasional garbled error message when the model is unresponsive.\n- Fix for occasional 'couldn't aquire lock' error after stream finishes.\n- Additional retry when model is unresponsive or hits provider rate limits—helps particularly with new Opus 4 model on OpenRouter.","2025-05-27T00:20:23",{"id":215,"version":216,"summary_zh":217,"released_at":218},105055,"server\u002Fv2.1.5","See CLI 2.1.5 release notes.","2025-05-24T00:09:13",{"id":220,"version":221,"summary_zh":222,"released_at":223},105056,"cli\u002Fv2.1.5","- Added newly released Claude Sonnet 4 and Claude Opus 4 as built-in models.\n- Sonnet 4 isn't yet used in the default 'daily-driver' model pack due to sporadic errors in early testing, but it can be used with the 'sonnet-4-daily' model pack (use '\\set-model sonnet-4-daily' to use it). It will be promoted to the default model pack soon.\n- Opus 4 can be used with the 'opus-4-planner' model pack ( '\\set-model opus-4-planner'), which uses Opus 4 for planning and Sonnet 4 for coding.\n- Removed error fallbacks for o4-mini and gemini-2.5-pro-preview.","2025-05-24T00:13:13",{"id":225,"version":226,"summary_zh":227,"released_at":228},105057,"server\u002Fv2.1.4","- Fix to remove occasional extraneous blank lines from start\u002Fend of edited files.","2025-05-20T18:29:33",{"id":230,"version":231,"summary_zh":232,"released_at":233},105058,"server\u002Fv2.1.3","- Fix for 'panic in execTellPlan' error when using a model pack that doesn't explicitly set the 'coder' or 'whole-file-builder' roles","2025-05-19T17:23:00",{"id":235,"version":236,"summary_zh":237,"released_at":238},105059,"cli\u002Fv2.1.3","- Fix for default model pack not being correctly applied to new plans\n- Fix for potential crash on Linux when applying a plan","2025-05-15T18:59:01",{"id":240,"version":241,"summary_zh":242,"released_at":243},105060,"server\u002Fv2.1.2","- Fix for auto-load context error: 'Error decoding response → EOF'","2025-05-08T17:41:13",{"id":245,"version":246,"summary_zh":247,"released_at":248},105061,"cli\u002Fv2.1.2","- Fix for rare auto-load context timeout error when no files are loaded.","2025-05-08T17:52:42",{"id":250,"version":251,"summary_zh":252,"released_at":253},105062,"server\u002Fv2.1.1+1","- Improve error handling to catch yet another \"context length exceeded\" error message variation from Anthropic.","2025-05-05T18:20:00",{"id":255,"version":256,"summary_zh":257,"released_at":258},105063,"server\u002Fv2.1.1","See CLI 2.1.1 release notes.","2025-05-02T17:37:33",{"id":260,"version":261,"summary_zh":262,"released_at":263},105064,"cli\u002Fv2.1.1","- Fix for free Gemini 2.5 Pro Experimental OpenRouter endpoint.\n- Retries for \"No endpoints found that support cache control\" error that showed up when OpenRouter temporarily disabled caching for Gemini 2.5 Pro Preview.\n- Other minor improvements to error handling and retries.","2025-05-02T17:38:16"]