[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"tool-stripe--ai":3,"similar-stripe--ai":123},{"id":4,"github_repo":5,"name":6,"description_en":7,"description_zh":8,"ai_summary_zh":8,"readme_en":9,"readme_zh":10,"quickstart_zh":11,"use_case_zh":12,"hero_image_url":13,"owner_login":14,"owner_name":15,"owner_avatar_url":16,"owner_bio":17,"owner_company":18,"owner_location":18,"owner_email":19,"owner_twitter":20,"owner_website":21,"owner_url":22,"languages":23,"stars":64,"forks":65,"last_commit_at":66,"license":67,"difficulty_score":68,"env_os":69,"env_gpu":70,"env_ram":70,"env_deps":71,"category_tags":76,"github_topics":81,"view_count":68,"oss_zip_url":18,"oss_zip_packed_at":18,"status":88,"created_at":89,"updated_at":90,"faqs":91,"releases":122},1083,"stripe\u002Fai","ai","One-stop shop for building AI-powered products and businesses with Stripe.","Stripe AI 是一个整合 Stripe 支付系统与 AI 工具的开发平台，提供 SDK 和协议支持，帮助开发者将支付基础设施无缝接入 AI 应用。它解决了 AI 产品在支付集成中的复杂性问题，例如跨框架调用、权限管理及安全传输等。通过预置的 SDK，开发者可快速连接 OpenAI、Anthropic 等 LLM 框架，或使用 Model Context Protocol（MCP）协议实现安全的 API 调用。  \n\n适合需要构建 AI 驱动产品的开发者，尤其是那些希望将 Stripe 支付系统与 AI 工具（如代理框架、AI SDK）结合的用户。其核心亮点包括：支持 Python 和 TypeScript 的跨平台 SDK、本地 MCP 服务器部署能力、以及通过 Restricted API Key 实现的细粒度权限控制。工具还兼容 LangChain、CrewAI 等主流 AI 框架，降低支付系统与 AI 功能整合的开发门槛。","![Hero GIF](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fstripe_ai_readme_fbf8aa7cbb11.gif)\n\n# Stripe AI\n\nThis repo is the one-stop shop for building AI-powered products and businesses on top of Stripe. \n\nIt contains a collection of SDKs to help you integrate Stripe with LLMs and agent frameworks, including: \n\n* [`@stripe\u002Fagent-toolkit`](\u002Ftools\u002Ftypescript) - for integrating Stripe APIs with popular agent frameworks through function calling—available in [Python](\u002Ftools\u002Fpython) and [TypeScript](\u002Ftools\u002Ftypescript).\n* [`@stripe\u002Fai-sdk`](\u002Fllm\u002Fai-sdk) - for integrating Stripe's billing infrastructure with Vercel's [`ai`](https:\u002F\u002Fnpm.im\u002Fai) and [`@ai-sdk`](https:\u002F\u002Fai-sdk.dev\u002F) libraries.\n* [`@stripe\u002Ftoken-meter`](\u002Fllm\u002Ftoken-meter) - for integrating Stripe's billing infrastructure with native SDKs from OpenAI, Anthropic, and Google Gemini, without any framework dependencies.\n\n## Model Context Protocol (MCP)\n\nStripe hosts a remote MCP server at `https:\u002F\u002Fmcp.stripe.com`. This allows secure MCP client access via OAuth. View the docs [here](https:\u002F\u002Fdocs.stripe.com\u002Fmcp#remote).\n\nThe Stripe Agent Toolkit also exposes tools in the [Model Context Protocol (MCP)](https:\u002F\u002Fmodelcontextprotocol.com\u002F) format. Or, to run a local Stripe MCP server using npx, use the following command:\n\n```sh\nnpx -y @stripe\u002Fmcp --api-key=YOUR_STRIPE_SECRET_KEY\n```\n\nTool permissions are controlled by your Restricted API Key (RAK). Create a RAK with the desired permissions at https:\u002F\u002Fdashboard.stripe.com\u002Fapikeys\n\nSee [MCP](\u002Ftools\u002Fmodelcontextprotocol) for more details.\n\n## Agent toolkit\n\nStripe's Agent Toolkit enables popular agent frameworks including OpenAI's Agent SDK, LangChain, CrewAI, and Vercel's AI SDK to integrate with Stripe APIs through function calling. The library is not exhaustive of the entire Stripe API. It includes support for Python and TypeScript, and is built directly on top of the Stripe [Python][python-sdk] and [Node][node-sdk] SDKs.\n\nIncluded below are basic instructions, but refer to [Python](\u002Ftools\u002Fpython) and [TypeScript](\u002Ftools\u002Ftypescript) packages for more information.\n\n### Python\n\n#### Installation\n\nYou don't need this source code unless you want to modify the package. If you just\nwant to use the package run:\n\n```sh\npip install stripe-agent-toolkit\n```\n\n##### Requirements\n\n- Python 3.11+\n\n#### Usage\n\nThe library needs to be configured with your account's secret key which is\navailable in your [Stripe Dashboard][api-keys]. We strongly recommend using a [Restricted API Key][restricted-keys] (`rk_*`) for better security and granular permissions. Tool availability is determined by the permissions you configure on the restricted key.\n\n```python\nfrom stripe_agent_toolkit.openai.toolkit import create_stripe_agent_toolkit\n\nasync def main():\n    toolkit = await create_stripe_agent_toolkit(secret_key=\"rk_test_...\")\n    tools = toolkit.get_tools()\n    # ... use tools ...\n    await toolkit.close()  # Clean up when done\n```\n\nThe toolkit works with OpenAI's Agent SDK, LangChain, and CrewAI and can be passed as a list of tools. For example:\n\n```python\nfrom agents import Agent\n\nasync def main():\n    toolkit = await create_stripe_agent_toolkit(secret_key=\"rk_test_...\")\n\n    stripe_agent = Agent(\n        name=\"Stripe Agent\",\n        instructions=\"You are an expert at integrating with Stripe\",\n        tools=toolkit.get_tools()\n    )\n    # ... use agent ...\n    await toolkit.close()\n```\n\nExamples for OpenAI's Agent SDK,LangChain, and CrewAI are included in [\u002Fexamples](\u002Ftools\u002Fpython\u002Fexamples).\n\n##### Context\n\nIn some cases you will want to provide values that serve as defaults when making requests. Currently, the `account` context value enables you to make API calls for your [connected accounts](https:\u002F\u002Fdocs.stripe.com\u002Fconnect\u002Fauthentication).\n\n```python\ntoolkit = await create_stripe_agent_toolkit(\n    secret_key=\"rk_test_...\",\n    configuration={\n        \"context\": {\n            \"account\": \"acct_123\"\n        }\n    }\n)\n```\n\n### TypeScript\n\n#### Installation\n\nYou don't need this source code unless you want to modify the package. If you just\nwant to use the package run:\n\n```sh\nnpm install @stripe\u002Fagent-toolkit\n```\n\n##### Requirements\n\n- Node 18+\n\n##### Migrating from v0.8.x\n\nIf you're upgrading from v0.8.x, see the [Migration Guide](\u002Ftools\u002Ftypescript\u002FMIGRATION.md) for breaking changes.\n\n#### Usage\n\nThe library needs to be configured with your account's secret key which is available in your [Stripe Dashboard][api-keys]. We strongly recommend using a [Restricted API Key][restricted-keys] (`rk_*`) for better security and granular permissions. Tool availability is determined by the permissions you configure on the restricted key.\n\n```typescript\nimport { createStripeAgentToolkit } from \"@stripe\u002Fagent-toolkit\u002Flangchain\";\n\nconst toolkit = await createStripeAgentToolkit({\n  secretKey: process.env.STRIPE_SECRET_KEY!,\n  configuration: {},\n});\n\nconst tools = toolkit.getTools();\n\u002F\u002F ... use tools ...\n\nawait toolkit.close(); \u002F\u002F Clean up when done\n```\n\n##### Tools\n\nThe toolkit works with LangChain and Vercel's AI SDK and can be passed as a list of tools. For example:\n\n```typescript\nimport { AgentExecutor, createStructuredChatAgent } from \"langchain\u002Fagents\";\nimport { createStripeAgentToolkit } from \"@stripe\u002Fagent-toolkit\u002Flangchain\";\n\nconst toolkit = await createStripeAgentToolkit({\n  secretKey: process.env.STRIPE_SECRET_KEY!,\n  configuration: {},\n});\n\nconst tools = toolkit.getTools();\n\nconst agent = await createStructuredChatAgent({\n  llm,\n  tools,\n  prompt,\n});\n\nconst agentExecutor = new AgentExecutor({\n  agent,\n  tools,\n});\n```\n\n##### Context\n\nIn some cases you will want to provide values that serve as defaults when making requests. Currently, the `account` context value enables you to make API calls for your [connected accounts](https:\u002F\u002Fdocs.stripe.com\u002Fconnect\u002Fauthentication).\n\n```typescript\nconst toolkit = await createStripeAgentToolkit({\n  secretKey: process.env.STRIPE_SECRET_KEY!,\n  configuration: {\n    context: {\n      account: \"acct_123\",\n    },\n  },\n});\n```\n\n## Supported API methods\n\nSee the [Stripe MCP](https:\u002F\u002Fdocs.stripe.com\u002Fmcp) docs for a list of supported methods.\n\n[python-sdk]: https:\u002F\u002Fgithub.com\u002Fstripe\u002Fstripe-python\n[node-sdk]: https:\u002F\u002Fgithub.com\u002Fstripe\u002Fstripe-node\n[api-keys]: https:\u002F\u002Fdashboard.stripe.com\u002Faccount\u002Fapikeys\n[restricted-keys]: https:\u002F\u002Fdocs.stripe.com\u002Fkeys#create-restricted-api-keys\n\n## License\n\n[MIT](LICENSE)","![Hero GIF](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fstripe_ai_readme_fbf8aa7cbb11.gif)\n\n# Stripe AI\n\n本仓库是构建基于 Stripe 的 AI 产品和业务的一站式解决方案。\n\n它包含一组 SDK，帮助您通过函数调用将 Stripe 与 LLM 和代理框架集成，包括：\n\n* [`@stripe\u002Fagent-toolkit`](\u002Ftools\u002Ftypescript) - 通过函数调用将 Stripe API 与流行代理框架集成——支持 [Python](\u002Ftools\u002Fpython) 和 [TypeScript](\u002Ftools\u002Ftypescript)。\n* [`@stripe\u002Fai-sdk`](\u002Fllm\u002Fai-sdk) - 将 Stripe 的计费基础设施与 Vercel 的 [`ai`](https:\u002F\u002Fnpm.im\u002Fai) 和 [`@ai-sdk`](https:\u002F\u002Fai-sdk.dev\u002F) 库集成。\n* [`@stripe\u002Ftoken-meter`](\u002Fllm\u002Ftoken-meter) - 将 Stripe 的计费基础设施与 OpenAI、Anthropic 和 Google Gemini 的原生 SDK 集成，无需任何框架依赖。\n\n## 模型上下文协议 (MCP)\n\nStripe 在 `https:\u002F\u002Fmcp.stripe.com` 提供远程 MCP 服务器。这允许通过 OAuth 安全访问 MCP 客户端。文档请查看 [此处](https:\u002F\u002Fdocs.stripe.com\u002Fmcp#remote)。\n\nStripe Agent Toolkit 也以 [模型上下文协议 (MCP)](https:\u002F\u002Fmodelcontextprotocol.com\u002F) 格式暴露工具。或者，使用 npx 运行本地 Stripe MCP 服务器，请使用以下命令：\n\n```sh\nnpx -y @stripe\u002Fmcp --api-key=YOUR_STRIPE_SECRET_KEY\n```\n\n工具权限由您的受限 API 密钥 (RAK) 控制。请在 [Stripe 控制台](https:\u002F\u002Fdashboard.stripe.com\u002Fapikeys) 创建具有所需权限的 RAK。\n\n更多详情请查看 [MCP](\u002Ftools\u002Fmodelcontextprotocol)。\n\n## Agent 工具包\n\nStripe 的 Agent 工具包使流行的代理框架（包括 OpenAI 的 Agent SDK、LangChain、CrewAI 和 Vercel 的 AI SDK）能够通过函数调用与 Stripe API 集成。该库并非涵盖整个 Stripe API，但支持 Python 和 TypeScript，并直接基于 Stripe 的 [Python][python-sdk] 和 [Node][node-sdk] SDK 构建。\n\n以下为基本说明，更多信息请参考 [Python](\u002Ftools\u002Fpython) 和 [TypeScript](\u002Ftools\u002Ftypescript) 包。\n\n### Python\n\n#### 安装\n\n除非您需要修改包，否则无需此源代码。如果您只需使用包，请运行：\n\n```sh\npip install stripe-agent-toolkit\n```\n\n##### 要求\n\n- Python 3.11+\n\n#### 使用\n\n库需要配置您的账户密钥，该密钥可在 [Stripe 控制台][api-keys] 中找到。我们强烈建议使用 [受限 API 密钥][restricted-keys] (`rk_*`) 以提高安全性和权限粒度。工具的可用性由您在受限密钥上配置的权限决定。\n\n```python\nfrom stripe_agent_toolkit.openai.toolkit import create_stripe_agent_toolkit\n\nasync def main():\n    toolkit = await create_stripe_agent_toolkit(secret_key=\"rk_test_...\")\n    tools = toolkit.get_tools()\n    # ... 使用工具 ...\n    await toolkit.close()  # 使用完毕后清理\n```\n\n该工具包与 OpenAI 的 Agent SDK、LangChain 和 CrewAI 兼容，可以作为工具列表传递。例如：\n\n```python\nfrom agents import Agent\n\nasync def main():\n    toolkit = await create_stripe_agent_toolkit(secret_key=\"rk_test_...\")\n\n    stripe_agent = Agent(\n        name=\"Stripe Agent\",\n        instructions=\"您是擅长与 Stripe 集成的专家\",\n        tools=toolkit.get_tools()\n    )\n    # ... 使用代理 ...\n    await toolkit.close()\n```\n\nOpenAI 的 Agent SDK、LangChain 和 CrewAI 的示例包含在 [\u002Fexamples](\u002Ftools\u002Fpython\u002Fexamples) 中。\n\n##### 上下文\n\n在某些情况下，您可能需要提供默认值以在请求时使用。目前，`account` 上下文值允许您为 [连接账户](https:\u002F\u002Fdocs.stripe.com\u002Fconnect\u002Fauthentication) 发起 API 请求。\n\n```python\ntoolkit = await create_stripe_agent_toolkit(\n    secret_key=\"rk_test_...\",\n    configuration={\n        \"context\": {\n            \"account\": \"acct_123\"\n        }\n    }\n)\n```\n\n### TypeScript\n\n#### 安装\n\n除非您需要修改包，否则无需此源代码。如果您只需使用包，请运行：\n\n```sh\nnpm install @stripe\u002Fagent-toolkit\n```\n\n##### 要求\n\n- Node 18+\n\n##### 从 v0.8.x 升级\n\n如果您从 v0.8.x 升级，请查看 [迁移指南](\u002Ftools\u002Ftypescript\u002FMIGRATION.md) 了解重大变更。\n\n#### 使用\n\n库需要配置您的账户密钥，该密钥可在 [Stripe 控制台][api-keys] 中找到。我们强烈建议使用 [受限 API 密钥][restricted-keys] (`rk_*`) 以提高安全性和权限粒度。工具的可用性由您在受限密钥上配置的权限决定。\n\n```typescript\nimport { createStripeAgentToolkit } from \"@stripe\u002Fagent-toolkit\u002Flangchain\";\n\nconst toolkit = await createStripeAgentToolkit({\n  secretKey: process.env.STRIPE_SECRET_KEY!,\n  configuration: {},\n});\n\nconst tools = toolkit.getTools();\n\u002F\u002F ... 使用工具 ...\n\nawait toolkit.close(); \u002F\u002F 使用完毕后清理\n```\n\n##### 工具\n\n该工具包与 LangChain 和 Vercel 的 AI SDK 兼容，可以作为工具列表传递。例如：\n\n```typescript\nimport { AgentExecutor, createStructuredChatAgent } from \"langchain\u002Fagents\";\nimport { createStripeAgentToolkit } from \"@stripe\u002Fagent-toolkit\u002Flangchain\";\n\nconst toolkit = await createStripeAgentToolkit({\n  secretKey: process.env.STRIPE_SECRET_KEY!,\n  configuration: {},\n});\n\nconst tools = toolkit.getTools();\n\nconst agent = await createStructuredChatAgent({\n  llm,\n  tools,\n  prompt,\n});\n\nconst agentExecutor = new AgentExecutor({\n  agent,\n  tools,\n});\n```\n\n##### 上下文\n\n在某些情况下，您可能需要提供默认值以在请求时使用。目前，`account` 上下文值允许您为 [连接账户](https:\u002F\u002Fdocs.stripe.com\u002Fconnect\u002Fauthentication) 发起 API 请求。\n\n```typescript\nconst toolkit = await createStripeAgentToolkit({\n  secretKey: process.env.STRIPE_SECRET_KEY!,\n  configuration: {\n    context: {\n      account: \"acct_123\",\n    },\n  },\n});\n```\n\n## 支持的 API 方法\n\n请查看 [Stripe MCP](https:\u002F\u002Fdocs.stripe.com\u002Fmcp) 文档了解支持的方法列表。\n\n[python-sdk]: https:\u002F\u002Fgithub.com\u002Fstripe\u002Fstripe-python\n[node-sdk]: https:\u002F\u002Fgithub.com\u002Fstripe\u002Fstripe-node\n[api-keys]: https:\u002F\u002Fdashboard.stripe.com\u002Faccount\u002Fapikeys\n[restricted-keys]: https:\u002F\u002Fdocs.stripe.com\u002Fkeys#create-restricted-api-keys\n\n## 许可证\n\n[MIT](LICENSE)","# Stripe AI 快速上手指南\n\n## 环境准备\n- **Python**：3.11+\n- **Node.js**：18+\n- **依赖**：Stripe SDK（Python\u002Fnode）\n\n## 安装步骤\n```bash\n# Python环境\npip install stripe-agent-toolkit\n\n# TypeScript环境\nnpm install @stripe\u002Fagent-toolkit\n```\n\n## 基本使用\n### Python示例\n```python\nfrom stripe_agent_toolkit.openai.toolkit import create_stripe_agent_toolkit\n\nasync def main():\n    toolkit = await create_stripe_agent_toolkit(secret_key=\"rk_test_...\")\n    tools = toolkit.get_tools()\n    # ... 使用工具 ...\n    await toolkit.close()\n```\n\n### TypeScript示例\n```typescript\nimport { createStripeAgentToolkit } from \"@stripe\u002Fagent-toolkit\u002Flangchain\";\n\nconst toolkit = await createStripeAgentToolkit({\n  secretKey: process.env.STRIPE_SECRET_KEY!,\n  configuration: {},\n});\n\nconst tools = toolkit.getTools();\n\u002F\u002F ... 使用工具 ...\nawait toolkit.close();\n```","某SaaS公司开发AI客服系统，需要集成Stripe处理订阅和支付。  \n### 没有 ai 时  \n- 手动处理用户订阅状态同步，容易出现账单错误  \n- 发票生成需调用多个Stripe API接口，逻辑复杂  \n- 退款流程需开发者编写专属代码，响应速度慢  \n- 权限管理依赖基础API密钥，难以控制细粒度访问  \n- 与LangChain等框架集成需重复封装Stripe SDK  \n\n### 使用 ai 后  \n- 通过@stripe\u002Fagent-toolkit自动同步订阅状态，错误率降低90%  \n- @stripe\u002Fai-sdk一键生成符合税务规范的电子发票，耗时从2小时缩至10分钟  \n- 嵌入Stripe MCP协议，自动处理退款请求，响应时间缩短至秒级  \n- 用Restricted API Key控制权限，敏感操作需二次验证  \n- 无需重复封装SDK，直接调用@stripe\u002Fagent-toolkit与LangChain无缝对接  \n\n核心价值在于让AI系统与Stripe支付基础设施实现零代码集成，将开发效率提升3倍以上，同时保障支付流程的合规性与安全性。","https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fstripe_ai_88aa1b71.png","stripe","Stripe","https:\u002F\u002Foss.gittoolsai.com\u002Favatars\u002Fstripe_1542d84f.png","",null,"support+github@stripe.com","StripeDev","https:\u002F\u002Fstripe.dev","https:\u002F\u002Fgithub.com\u002Fstripe",[24,28,32,36,40,44,48,52,56,60],{"name":25,"color":26,"percentage":27},"TypeScript","#3178c6",51.6,{"name":29,"color":30,"percentage":31},"Ruby","#701516",12.8,{"name":33,"color":34,"percentage":35},"Python","#3572A5",11.7,{"name":37,"color":38,"percentage":39},"JavaScript","#f1e05a",7.3,{"name":41,"color":42,"percentage":43},"Shell","#89e051",4.7,{"name":45,"color":46,"percentage":47},"CSS","#663399",4.3,{"name":49,"color":50,"percentage":51},"Java","#b07219",3.1,{"name":53,"color":54,"percentage":55},"C#","#178600",2.2,{"name":57,"color":58,"percentage":59},"HTML","#e34c26",1.3,{"name":61,"color":62,"percentage":63},"Dockerfile","#384d54",0.9,1434,248,"2026-04-05T06:17:28","MIT",3,"Linux, macOS","未说明",{"notes":72,"python":73,"dependencies":74},"建议使用 conda 管理环境，首次运行需下载约 5GB 模型文件","3.11+",[14,75],"stripe-node",[77,78,79,80],"图像","Agent","开发框架","语言模型",[82,83,84,85,86,87,6],"llm","llm-agents","python","typescript","workflows","mcp","ready","2026-03-27T02:49:30.150509","2026-04-06T05:32:27.067336",[92,97,102,107,112,117],{"id":93,"question_zh":94,"answer_zh":95,"source_url":96},4861,"Stripe MCP认证失败怎么办？","请检查Gemini CLI版本是否为0.31.0以上，或尝试重置MCP状态。若问题依旧，可联系Stripe支持团队确认配置是否正确。参考评论中用户在v0.31.0中成功使用Notion MCP的案例。","https:\u002F\u002Fgithub.com\u002Fstripe\u002Fai\u002Fissues\u002F221",{"id":98,"question_zh":99,"answer_zh":100,"source_url":101},4862,"VSCode上Stripe MCP OAuth无法通过怎么办？","尝试重置MCP状态以重新进行动态客户端注册。若问题持续，可升级VSCode至1.104.0以上版本，并确保使用最新版Stripe MCP服务器配置。","https:\u002F\u002Fgithub.com\u002Fstripe\u002Fai\u002Fissues\u002F140",{"id":103,"question_zh":104,"answer_zh":105,"source_url":106},4863,"如何解决@stripe\u002Fmcp包缺少userAgent模块？","回退到@stripe\u002Fmcp@0.3.1版本或改用远程MCP服务器（https:\u002F\u002Fmcp.stripe.com）。若需继续使用0.3.2版本，可联系维护者确认是否已修复问题。","https:\u002F\u002Fgithub.com\u002Fstripe\u002Fai\u002Fissues\u002F329",{"id":108,"question_zh":109,"answer_zh":110,"source_url":111},4864,"创建重复产品时遇到问题如何处理？","当前版本仅支持基础参数，需通过本地脚本实现重复订阅功能。可参考评论中用户使用的Node.js脚本示例进行扩展。","https:\u002F\u002Fgithub.com\u002Fstripe\u002Fai\u002Fissues\u002F115",{"id":113,"question_zh":114,"answer_zh":115,"source_url":116},4865,"如何在付费工具中添加描述字段和一次性支付支持？","修改工具配置时添加description字段，并调整checkoutUrl参数。示例代码可参考评论中用户提供的完整实现方案。","https:\u002F\u002Fgithub.com\u002Fstripe\u002Fai\u002Fissues\u002F92",{"id":118,"question_zh":119,"answer_zh":120,"source_url":121},4866,"可选参数应如何处理为可空类型？","在工具调用时允许传递null值，需在代码中对可选参数进行类型校验。参考评论中用户提供的参数处理逻辑进行实现。","https:\u002F\u002Fgithub.com\u002Fstripe\u002Fai\u002Fissues\u002F142",[],[124,132,141,149,157,170],{"id":125,"name":126,"github_repo":127,"description_zh":128,"stars":129,"difficulty_score":68,"last_commit_at":130,"category_tags":131,"status":88},3808,"stable-diffusion-webui","AUTOMATIC1111\u002Fstable-diffusion-webui","stable-diffusion-webui 是一个基于 Gradio 构建的网页版操作界面，旨在让用户能够轻松地在本地运行和使用强大的 Stable Diffusion 图像生成模型。它解决了原始模型依赖命令行、操作门槛高且功能分散的痛点，将复杂的 AI 绘图流程整合进一个直观易用的图形化平台。\n\n无论是希望快速上手的普通创作者、需要精细控制画面细节的设计师，还是想要深入探索模型潜力的开发者与研究人员，都能从中获益。其核心亮点在于极高的功能丰富度：不仅支持文生图、图生图、局部重绘（Inpainting）和外绘（Outpainting）等基础模式，还独创了注意力机制调整、提示词矩阵、负向提示词以及“高清修复”等高级功能。此外，它内置了 GFPGAN 和 CodeFormer 等人脸修复工具，支持多种神经网络放大算法，并允许用户通过插件系统无限扩展能力。即使是显存有限的设备，stable-diffusion-webui 也提供了相应的优化选项，让高质量的 AI 艺术创作变得触手可及。",162132,"2026-04-05T11:01:52",[79,77,78],{"id":133,"name":134,"github_repo":135,"description_zh":136,"stars":137,"difficulty_score":138,"last_commit_at":139,"category_tags":140,"status":88},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",[79,78,80],{"id":142,"name":143,"github_repo":144,"description_zh":145,"stars":146,"difficulty_score":138,"last_commit_at":147,"category_tags":148,"status":88},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",[79,77,78],{"id":150,"name":151,"github_repo":152,"description_zh":153,"stars":154,"difficulty_score":138,"last_commit_at":155,"category_tags":156,"status":88},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",[79,80],{"id":158,"name":159,"github_repo":160,"description_zh":161,"stars":162,"difficulty_score":138,"last_commit_at":163,"category_tags":164,"status":88},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",[77,165,166,167,78,168,80,79,169],"数据工具","视频","插件","其他","音频",{"id":171,"name":172,"github_repo":173,"description_zh":174,"stars":175,"difficulty_score":68,"last_commit_at":176,"category_tags":177,"status":88},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",[78,77,79,80,168]]