[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"similar-abhagsain--ai-cli":3,"tool-abhagsain--ai-cli":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",140436,2,"2026-04-05T23:32:43",[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":76,"owner_avatar_url":77,"owner_bio":78,"owner_company":79,"owner_location":80,"owner_email":81,"owner_twitter":75,"owner_website":82,"owner_url":83,"languages":84,"stars":97,"forks":98,"last_commit_at":99,"license":100,"difficulty_score":23,"env_os":101,"env_gpu":102,"env_ram":101,"env_deps":103,"category_tags":110,"github_topics":111,"view_count":10,"oss_zip_url":81,"oss_zip_packed_at":81,"status":16,"created_at":118,"updated_at":119,"faqs":120,"releases":146},1219,"abhagsain\u002Fai-cli","ai-cli","Get answers for CLI commands from ChatGPT right from your terminal","ai-cli 让你在终端里直接用自然语言提问，就能获得 ChatGPT 生成的 CLI 命令解答。比如输入 `ai ask \"如何查看端口占用\"`，它会立刻返回 `lsof -i :端口号` 这样的实用命令。这解决了开发者在写命令时频繁查文档、反复试错的痛点，让终端操作更高效。特别适合日常使用命令行的开发者，无论是新手快速上手还是老手提升效率都超实用。技术亮点在于它基于 GPT-3.5-turbo 模型，平均响应仅 40 tokens，成本低至约 0.0009 美元\u002F命令；还支持一键自动补全功能，安装后输入命令更流畅。安装只需简单执行 `npm i @abhagsain\u002Fai-cli -g`，再配置 OpenAI API key 即可使用，让命令行工作变得智能又轻松。","\u003Cp align=\"center\">\n\u003Ch1 align=\"center\"> GPT3 Powered CLI \u003C\u002Fh1>\n\n\u003Cp align=\"center\">\n \u003Ca href=\"https:\u002F\u002Foclif.io\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fcli-oclif-brightgreen.svg\" alt=\"Oclif\">\u003C\u002Fa>\n \u003Ca href=\"https:\u002F\u002Fnpmjs.org\u002Fpackage\u002F@abhagsain\u002Fai-cli\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fnpm\u002Fv\u002F@abhagsain\u002Fai-cli.svg\" alt=\"npm\">\u003C\u002Fa>\n \u003Ca href=\"https:\u002F\u002Fnpmjs.org\u002Fpackage\u002F@abhagsain\u002Fai-cli\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fnpm\u002Fdw\u002F@abhagsain\u002Fai-cli.svg\" alt=\"npm\">\u003C\u002Fa>\n \u003Ca href=\"https:\u002F\u002Fnews.ycombinator.com\u002Fitem?id=33651326\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002F%233-Hacker%20News%20%7C%20159-FF6600\" alt=\"Hacker News\">\u003C\u002Fa>\n\n\u003C\u002Fp>\n \n\n\n\n\u003C!-- \u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fabhagsain_ai-cli_readme_35056775ac85.gif\" width=\"900\" height=\"600\"\u002F> -->\n![image](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fabhagsain_ai-cli_readme_4704d5cf10a5.png)\n\n\n\n\n### Installation\n\nYou'd need to install it globally\n\n```\nnpm i @abhagsain\u002Fai-cli -g\n```\n\nUsage\n\n```\n$ ai ask \"Check process running on port\"\n```\n\nYou'd need to enter your own OpenAI API key\nHere's how you can get one\n\n1. Go to https:\u002F\u002Fopenai.com\u002Fapi\u002Flogin\n2. Create an account or log into your existing account\n3. Go to https:\u002F\u002Fbeta.openai.com\u002Faccount\u002Fapi-keys or\n   \u003Cimg width=\"1904\" alt=\"image\" src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fabhagsain_ai-cli_readme_2f5ba5399e09.png\">\n4. Run `ai auth`, enter your API KEY and you're good to go!\n\nPricing\n\nThe current prompt length is `~800` tokens and average response length is `~40` tokens. The pricing for [`gpt-3.5-turbo`](https:\u002F\u002Fopenai.com\u002Fapi\u002Fpricing\u002F) is `$0.001` per `1K` input tokens and `$0.002` per `1K` output tokens which is ~`$0.0009\u002Fcommand`. We'll see if we can improve the response as well as reduce the per-command-cost with fine-tuning.\n\n___\n\nAdd autocomplete by running `ai autocomplete` and follow the instructions. It's super easy.\n\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fabhagsain_ai-cli_readme_7a897676b6e8.gif\" width=\"800\">\n\n__\n\n### Liked this project? Checkout my other side project. [SlidesAI.io - AI Presentation Maker](https:\u002F\u002Fslidesai.io\u002F?ref=ai-cli)\n__\n\nAuto generated documentation\n\n\u003C!-- toc -->\n* [Usage](#usage)\n* [Commands](#commands)\n\u003C!-- tocstop -->\n\n# Usage\n\n\u003C!-- usage -->\n```sh-session\n$ npm install -g @abhagsain\u002Fai-cli\n$ ai COMMAND\nrunning command...\n$ ai (--version)\n@abhagsain\u002Fai-cli\u002F1.3.0 darwin-arm64 node-v18.0.0\n$ ai --help [COMMAND]\nUSAGE\n  $ ai COMMAND\n...\n```\n\u003C!-- usagestop -->\n\n# Commands\n\n\u003C!-- commands -->\n* [`ai ask [question]`](#ai-ask-question)\n* [`ai auth`](#ai-auth)\n* [`ai autocomplete [SHELL]`](#ai-autocomplete-shell)\n* [`ai help [COMMAND]`](#ai-help-command)\n* [`ai model`](#ai-model)\n* [`ai update [CHANNEL]`](#ai-update-channel)\n\n## `ai ask [question]`\n\nAsk question to GPT3 from your terminal\n\n```\nUSAGE\n  $ ai ask [question]\n\nARGUMENTS\n  QUESTION  Your question\n\nDESCRIPTION\n  Ask question to GPT3 from your terminal\n\nEXAMPLES\n  $ ai ask \"Check running process on port 3000\"\n```\n\n_See code: [dist\u002Fcommands\u002Fask.ts](https:\u002F\u002Fgithub.com\u002Fabhagsain\u002Fai-cli\u002Fblob\u002Fv1.3.0\u002Fdist\u002Fcommands\u002Fask.ts)_\n\n## `ai auth`\n\nUpdate existing or add new OpenAI API Key\n\n```\nUSAGE\n  $ ai auth\n\nDESCRIPTION\n  Update existing or add new OpenAI API Key\n\nEXAMPLES\n  $ ai auth (Follow the prompt)\n```\n\n_See code: [dist\u002Fcommands\u002Fauth.ts](https:\u002F\u002Fgithub.com\u002Fabhagsain\u002Fai-cli\u002Fblob\u002Fv1.3.0\u002Fdist\u002Fcommands\u002Fauth.ts)_\n\n## `ai autocomplete [SHELL]`\n\ndisplay autocomplete installation instructions\n\n```\nUSAGE\n  $ ai autocomplete [SHELL] [-r]\n\nARGUMENTS\n  SHELL  shell type\n\nFLAGS\n  -r, --refresh-cache  Refresh cache (ignores displaying instructions)\n\nDESCRIPTION\n  display autocomplete installation instructions\n\nEXAMPLES\n  $ ai autocomplete\n\n  $ ai autocomplete bash\n\n  $ ai autocomplete zsh\n\n  $ ai autocomplete --refresh-cache\n```\n\n_See code: [@oclif\u002Fplugin-autocomplete](https:\u002F\u002Fgithub.com\u002Foclif\u002Fplugin-autocomplete\u002Fblob\u002Fv1.3.6\u002Fsrc\u002Fcommands\u002Fautocomplete\u002Findex.ts)_\n\n## `ai help [COMMAND]`\n\nDisplay help for ai.\n\n```\nUSAGE\n  $ ai help [COMMAND] [-n]\n\nARGUMENTS\n  COMMAND  Command to show help for.\n\nFLAGS\n  -n, --nested-commands  Include all nested commands in the output.\n\nDESCRIPTION\n  Display help for ai.\n```\n\n_See code: [@oclif\u002Fplugin-help](https:\u002F\u002Fgithub.com\u002Foclif\u002Fplugin-help\u002Fblob\u002Fv5.1.17\u002Fsrc\u002Fcommands\u002Fhelp.ts)_\n\n## `ai model`\n\nChange model preference (default: gpt-3.5-turbo)\n\n```\nUSAGE\n  $ ai model\n\nDESCRIPTION\n  Change model preference (default: gpt-3.5-turbo)\n\nEXAMPLES\n  $ ai model (Follow the prompt)\n```\n\n_See code: [dist\u002Fcommands\u002Fmodel.ts](https:\u002F\u002Fgithub.com\u002Fabhagsain\u002Fai-cli\u002Fblob\u002Fv1.3.0\u002Fdist\u002Fcommands\u002Fmodel.ts)_\n\n## `ai update [CHANNEL]`\n\nupdate the ai CLI\n\n```\nUSAGE\n  $ ai update [CHANNEL] [-a] [-v \u003Cvalue> | -i] [--force]\n\nFLAGS\n  -a, --available        Install a specific version.\n  -i, --interactive      Interactively select version to install. This is ignored if a channel is provided.\n  -v, --version=\u003Cvalue>  Install a specific version.\n  --force                Force a re-download of the requested version.\n\nDESCRIPTION\n  update the ai CLI\n\nEXAMPLES\n  Update to the stable channel:\n\n    $ ai update stable\n\n  Update to a specific version:\n\n    $ ai update --version 1.0.0\n\n  Interactively select version:\n\n    $ ai update --interactive\n\n  See available versions:\n\n    $ ai update --available\n```\n\n_See code: [@oclif\u002Fplugin-update](https:\u002F\u002Fgithub.com\u002Foclif\u002Fplugin-update\u002Fblob\u002Fv3.0.7\u002Fsrc\u002Fcommands\u002Fupdate.ts)_\n\u003C!-- commandsstop -->\n","\u003Cp align=\"center\">\n\u003Ch1 align=\"center\"> 基于GPT3的命令行工具 \u003C\u002Fh1>\n\n\u003Cp align=\"center\">\n \u003Ca href=\"https:\u002F\u002Foclif.io\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fcli-oclif-brightgreen.svg\" alt=\"Oclif\">\u003C\u002Fa>\n \u003Ca href=\"https:\u002F\u002Fnpmjs.org\u002Fpackage\u002F@abhagsain\u002Fai-cli\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fnpm\u002Fv\u002F@abhagsain\u002Fai-cli.svg\" alt=\"npm\">\u003C\u002Fa>\n \u003Ca href=\"https:\u002F\u002Fnpmjs.org\u002Fpackage\u002F@abhagsain\u002Fai-cli\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fnpm\u002Fdw\u002F@abhagsain\u002Fai-cli.svg\" alt=\"npm\">\u003C\u002Fa>\n \u003Ca href=\"https:\u002F\u002Fnews.ycombinator.com\u002Fitem?id=33651326\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002F%233-Hacker%20News%20%7C%20159-FF6600\" alt=\"Hacker News\">\u003C\u002Fa>\n\n\u003C\u002Fp>\n \n\n\n\n\u003C!-- \u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fabhagsain_ai-cli_readme_35056775ac85.gif\" width=\"900\" height=\"600\"\u002F> -->\n![image](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fabhagsain_ai-cli_readme_4704d5cf10a5.png)\n\n\n\n\n### 安装\n\n你需要全局安装它\n\n```\nnpm i @abhagsain\u002Fai-cli -g\n```\n\n使用方法\n\n```\n$ ai ask \"检查端口上运行的进程\"\n```\n\n你需要输入自己的OpenAI API密钥。以下是获取密钥的方法：\n\n1. 访问 https:\u002F\u002Fopenai.com\u002Fapi\u002Flogin\n2. 创建一个账户或登录现有账户\n3. 转到 https:\u002F\u002Fbeta.openai.com\u002Faccount\u002Fapi-keys 或\n   \u003Cimg width=\"1904\" alt=\"image\" src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fabhagsain_ai-cli_readme_2f5ba5399e09.png\">\n4. 运行 `ai auth`，输入你的API密钥，即可开始使用！\n\n定价\n\n当前提示长度约为800个token，平均响应长度约为40个token。根据 [`gpt-3.5-turbo`](https:\u002F\u002Fopenai.com\u002Fapi\u002Fpricing\u002F) 的定价，每1000个输入token收费0.001美元，每1000个输出token收费0.002美元，即每次命令的成本约为0.0009美元。我们将通过微调来优化响应质量，并进一步降低每次命令的成本。\n\n___\n\n通过运行 `ai autocomplete` 并按照指示操作，即可启用自动补全功能。非常简单。\n\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fabhagsain_ai-cli_readme_7a897676b6e8.gif\" width=\"800\">\n\n__\n\n### 喜欢这个项目吗？来看看我的另一个副业项目吧：[SlidesAI.io - AI演示文稿生成器](https:\u002F\u002Fslidesai.io\u002F?ref=ai-cli)\n__\n\n自动生成的文档\n\n\u003C!-- toc -->\n* [使用方法](#usage)\n* [命令](#commands)\n\u003C!-- tocstop -->\n\n# 使用方法\n\n\u003C!-- usage -->\n```sh-session\n$ npm install -g @abhagsain\u002Fai-cli\n$ ai COMMAND\n正在执行命令...\n$ ai (--version)\n@abhagsain\u002Fai-cli\u002F1.3.0 darwin-arm64 node-v18.0.0\n$ ai --help [COMMAND]\nUSAGE\n  $ ai COMMAND\n...\n```\n\u003C!-- usagestop -->\n\n# 命令\n\n\u003C!-- commands -->\n* [`ai ask [question]`](#ai-ask-question)\n* [`ai auth`](#ai-auth)\n* [`ai autocomplete [SHELL]`](#ai-autocomplete-shell)\n* [`ai help [COMMAND]`](#ai-help-command)\n* [`ai model`](#ai-model)\n* [`ai update [CHANNEL]`](#ai-update-channel)\n\n## `ai ask [question]`\n\n在终端中向GPT3提问\n\n```\nUSAGE\n  $ ai ask [question]\n\nARGUMENTS\n  QUESTION  您的问题\n\nDESCRIPTION\n  在终端中向GPT3提问\n\nEXAMPLES\n  $ ai ask \"检查3000端口上运行的进程\"\n```\n\n_代码来源：[dist\u002Fcommands\u002Fask.ts](https:\u002F\u002Fgithub.com\u002Fabhagsain\u002Fai-cli\u002Fblob\u002Fv1.3.0\u002Fdist\u002Fcommands\u002Fask.ts)_\n\n## `ai auth`\n\n更新现有或添加新的OpenAI API密钥\n\n```\nUSAGE\n  $ ai auth\n\nDESCRIPTION\n  更新现有或添加新的OpenAI API密钥\n\nEXAMPLES\n  $ ai auth (按照提示操作)\n```\n\n_代码来源：[dist\u002Fcommands\u002Fauth.ts](https:\u002F\u002Fgithub.com\u002Fabhagsain\u002Fai-cli\u002Fblob\u002Fv1.3.0\u002Fdist\u002Fcommands\u002Fauth.ts)_\n\n## `ai autocomplete [SHELL]`\n\n显示自动补全的安装说明\n\n```\nUSAGE\n  $ ai autocomplete [SHELL] [-r]\n\nARGUMENTS\n  SHELL  shell类型\n\nFLAGS\n  -r, --refresh-cache  刷新缓存（忽略显示说明）\n\nDESCRIPTION\n  显示自动补全的安装说明\n\nEXAMPLES\n  $ ai autocomplete\n\n  $ ai autocomplete bash\n\n  $ ai autocomplete zsh\n\n  $ ai autocomplete --refresh-cache\n```\n\n_代码来源：[@oclif\u002Fplugin-autocomplete](https:\u002F\u002Fgithub.com\u002Foclif\u002Fplugin-autocomplete\u002Fblob\u002Fv1.3.6\u002Fsrc\u002Fcommands\u002Fautocomplete\u002Findex.ts)_\n\n## `ai help [COMMAND]`\n\n显示ai的帮助信息\n\n```\nUSAGE\n  $ ai help [COMMAND] [-n]\n\nARGUMENTS\n  COMMAND  需要显示帮助的命令\n\nFLAGS\n  -n, --nested-commands  在输出中包含所有嵌套命令\n\nDESCRIPTION\n  显示ai的帮助信息\n```\n\n_代码来源：[@oclif\u002Fplugin-help](https:\u002F\u002Fgithub.com\u002Foclif\u002Fplugin-help\u002Fblob\u002Fv5.1.17\u002Fsrc\u002Fcommands\u002Fhelp.ts)_\n\n## `ai model`\n\n更改模型偏好（默认：gpt-3.5-turbo）\n\n```\nUSAGE\n  $ ai model\n\nDESCRIPTION\n  更改模型偏好（默认：gpt-3.5-turbo）\n\nEXAMPLES\n  $ ai model (按照提示操作)\n```\n\n_代码来源：[dist\u002Fcommands\u002Fmodel.ts](https:\u002F\u002Fgithub.com\u002Fabhagsain\u002Fai-cli\u002Fblob\u002Fv1.3.0\u002Fdist\u002Fcommands\u002Fmodel.ts)_\n\n## `ai update [CHANNEL]`\n\n更新ai CLI\n\n```\nUSAGE\n  $ ai update [CHANNEL] [-a] [-v \u003Cvalue> | -i] [--force]\n\nFLAGS\n  -a, --available        安装特定版本。\n  -i, --interactive      交互式选择要安装的版本。如果指定了频道，则此选项将被忽略。\n  -v, --version=\u003Cvalue>  安装特定版本。\n  --force                强制重新下载请求的版本。\n\nDESCRIPTION\n  更新ai CLI\n\nEXAMPLES\n  更新到稳定频道：\n\n    $ ai update stable\n\n  更新到特定版本：\n\n    $ ai update --version 1.0.0\n\n  交互式选择版本：\n\n    $ ai update --interactive\n\n  查看可用版本：\n\n    $ ai update --available\n```\n\n_代码来源：[@oclif\u002Fplugin-update](https:\u002F\u002Fgithub.com\u002Foclif\u002Fplugin-update\u002Fblob\u002Fv3.0.7\u002Fsrc\u002Fcommands\u002Fupdate.ts)_\n\u003C!-- commandsstop -->","# ai-cli 快速上手指南\n\n## 环境准备\n- 需要 Node.js 18.0.0 或更高版本\n- 推荐使用国内 npm 镜像加速安装（避免网络问题）：\n  ```bash\n  npm config set registry https:\u002F\u002Fregistry.npmmirror.com\n  ```\n\n## 安装步骤\n```bash\nnpm i @abhagsain\u002Fai-cli -g --registry=https:\u002F\u002Fregistry.npmmirror.com\n```\n\n## 基本使用\n1. **配置 OpenAI API Key**（首次使用必需）：\n   ```bash\n   ai auth\n   ```\n   按提示输入你的 OpenAI API Key（[获取方式](https:\u002F\u002Fbeta.openai.com\u002Faccount\u002Fapi-keys)）\n\n2. **最简单提问示例**：\n   ```bash\n   ai ask \"如何查看端口 3000 的进程\"\n   ```","一位后端开发者在部署微服务时，频繁遇到端口冲突问题，需要快速获取Linux命令来检查和终止占用进程。\n\n### 没有 ai-cli 时\n- 需要暂停开发，打开浏览器搜索\"检查端口占用命令\"，在Stack Overflow和文档间反复切换\n- 从搜索结果中复制命令（如`netstat -tuln | grep :8080`），常因系统差异导致执行失败\n- 搜索过程平均耗时5分钟以上，打断编码思维流\n- 依赖网络连接，离线环境完全无法获取帮助\n\n### 使用 ai-cli 后\n- 直接在终端输入 `ai ask \"如何检查端口8080占用情况\"`\n- 立即返回精准命令（如`lsof -i :8080`），并附带系统适配说明\n- 一键复制命令执行，无需切换应用或手动输入\n- 从提问到解决仅需25秒，开发效率提升80%\n\nai-cli将命令查询从碎片化搜索转化为终端内即时响应，让开发者始终专注于核心编码任务。","https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fabhagsain_ai-cli_4704d5cf.png","abhagsain","Anurag Bhagsain","https:\u002F\u002Foss.gittoolsai.com\u002Favatars\u002Fabhagsain_b057f251.jpg","Love to build stuff, Learner & Engineer","SlidesAI","Remote",null,"https:\u002F\u002Fabhagsain.com","https:\u002F\u002Fgithub.com\u002Fabhagsain",[85,89,93],{"name":86,"color":87,"percentage":88},"TypeScript","#3178c6",96.4,{"name":90,"color":91,"percentage":92},"JavaScript","#f1e05a",3.3,{"name":94,"color":95,"percentage":96},"Batchfile","#C1F12E",0.4,1175,61,"2026-04-05T09:25:48","GPL-3.0","未说明","不需要 GPU",{"notes":104,"python":101,"dependencies":105},"需要 Node.js 18.0.0 或更高版本，首次运行需通过 `ai auth` 设置 OpenAI API key。无需本地 GPU 或大内存，模型推理通过 OpenAI API 完成。",[106,107,108,109],"oclif@^1.0.0","@oclif\u002Fplugin-autocomplete@1.3.6","@oclif\u002Fplugin-help@5.1.17","@oclif\u002Fplugin-update@3.0.7",[53,26,14,13,15],[112,113,114,115,116,117],"ai","cli","gpt3","gpt3-cli","openai","chatgpt","2026-03-27T02:49:30.150509","2026-04-06T08:17:44.303879",[121,126,131,136,141],{"id":122,"question_zh":123,"answer_zh":124,"source_url":125},5543,"为什么会出现 429 错误？如何解决？","OpenAI 免费试用账户可能触发请求频率限制。添加支付到 OpenAI 账户后，问题即可解决。","https:\u002F\u002Fgithub.com\u002Fabhagsain\u002Fai-cli\u002Fissues\u002F6",{"id":127,"question_zh":128,"answer_zh":129,"source_url":130},5544,"如何更改默认模型？","升级到最新版本，运行命令 `npm install @abhagsain\u002Fai-cli@latest -g`。升级后默认模型配置已修复。","https:\u002F\u002Fgithub.com\u002Fabhagsain\u002Fai-cli\u002Fissues\u002F8",{"id":132,"question_zh":133,"answer_zh":134,"source_url":135},5545,"为什么会出现 400 错误？如何解决？","默认模型配置问题导致（如缺少 `name` 键）。升级到最新版本（v1.2.3）即可修复。","https:\u002F\u002Fgithub.com\u002Fabhagsain\u002Fai-cli\u002Fissues\u002F20",{"id":137,"question_zh":138,"answer_zh":139,"source_url":140},5546,"是否支持 GPT-4 模型？","是的，支持 GPT-4。升级到最新版本后，使用 `ai model` 命令切换模型即可。","https:\u002F\u002Fgithub.com\u002Fabhagsain\u002Fai-cli\u002Fissues\u002F50",{"id":142,"question_zh":143,"answer_zh":144,"source_url":145},5547,"text-davinci-003 模型已弃用，如何解决？","升级到最新版本，新版本已自动添加支持的模型到模型菜单，无需额外操作。","https:\u002F\u002Fgithub.com\u002Fabhagsain\u002Fai-cli\u002Fissues\u002F52",[147,152,157,162,167,172,177],{"id":148,"version":149,"summary_zh":150,"released_at":151},114760,"v1.3.0","## What's Changed\r\n* Refactor: Use Chat Completions API by @arindamlahiri in https:\u002F\u002Fgithub.com\u002Fabhagsain\u002Fai-cli\u002Fpull\u002F53\r\n\r\n## New Contributors\r\n* @arindamlahiri made their first contribution at https:\u002F\u002Fgithub.com\u002Fabhagsain\u002Fai-cli\u002Fpull\u002F53\r\n\r\n**Full Changelog**: https:\u002F\u002Fgithub.com\u002Fabhagsain\u002Fai-cli\u002Fcompare\u002Fv1.2.3...v1.3.0\r\n\r\nThanks @deivid11 for raising the issue.","2024-01-27T19:08:02",{"id":153,"version":154,"summary_zh":155,"released_at":156},114761,"v1.2.3","- fix: 🐞 undefined model getting passed to API  0072314 closes #20 \r\n- docs: 🗒️ add autocomplete gif & instructions  93e52ec\r\n\r\nhttps:\u002F\u002Fgithub.com\u002Fabhagsain\u002Fai-cli\u002Fcompare\u002Fv1.2.2...v1.2.3","2022-12-09T06:36:35",{"id":158,"version":159,"summary_zh":160,"released_at":161},114762,"v1.2.2","- refactor: ⚒️ add update and autocomplete plugins  ecd2059\r\n- Update README.md  f3c95e6\r\n- Update README.md  de4bdc8\r\n\r\nhttps:\u002F\u002Fgithub.com\u002Fabhagsain\u002Fai-cli\u002Fcompare\u002Fv1.2.1...v1.2.2","2022-12-07T17:15:52",{"id":163,"version":164,"summary_zh":165,"released_at":166},114763,"v1.2.1","-  fix: 🐞 wrong name getting passed  545572c \r\n- #8 feat: ✅ changing default model  b91bab4\r\nhttps:\u002F\u002Fgithub.com\u002Fabhagsain\u002Fai-cli\u002Fcompare\u002Fv1.1.3...v1.2.1","2022-12-04T14:24:31",{"id":168,"version":169,"summary_zh":170,"released_at":171},114764,"v1.1.3","- refactor: ⚒️ using prompt conditionally  360aadc (Thanks @luiz00martins) for the prompt\r\n- chore: 🗒️ add form to README  f45628c\r\n- docs: 🗒️ add pricing info to README  9735a84\r\n- docs: 🗒️ remove URL from OG  f2726b2\r\n- docs: 🗒️ add global installation instructions  3b487f2\r\n\r\nhttps:\u002F\u002Fgithub.com\u002Fabhagsain\u002Fai-cli\u002Fcompare\u002Fv1.1.2...v1.1.3","2022-12-04T12:13:41",{"id":173,"version":174,"summary_zh":175,"released_at":176},114765,"v1.1.2","- docs: 🗒️ update README.md  09b9c44\r\n\r\nhttps:\u002F\u002Fgithub.com\u002Fabhagsain\u002Fai-cli\u002Fcompare\u002Fv1.1.1...v1.1.2","2022-11-16T07:12:47",{"id":178,"version":179,"summary_zh":180,"released_at":181},114766,"v0.0.1-1","- refactor: 🛠️ remove @oclif\u002Fplugins  793edbb\r\n\r\nhttps:\u002F\u002Fgithub.com\u002Fabhagsain\u002Fai-cli\u002Fcompare\u002Fv0.0.1-0...v0.0.1-1\r\n\r\n**Full Changelog**: https:\u002F\u002Fgithub.com\u002Fabhagsain\u002Fai-cli\u002Fcommits\u002Fv0.0.1-1","2022-11-15T20:14:07"]