[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"tool-langchain-ai--langchainjs":3,"similar-langchain-ai--langchainjs":193},{"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":15,"owner_website":20,"owner_url":21,"languages":22,"stars":43,"forks":44,"last_commit_at":45,"license":46,"difficulty_score":47,"env_os":48,"env_gpu":48,"env_ram":48,"env_deps":49,"category_tags":55,"github_topics":18,"view_count":59,"oss_zip_url":18,"oss_zip_packed_at":18,"status":60,"created_at":61,"updated_at":62,"faqs":63,"releases":93},5153,"langchain-ai\u002Flangchainjs","langchainjs","The agent engineering platform","langchainjs 是一个专为 JavaScript 和 TypeScript 开发者打造的智能体工程平台，旨在简化基于大语言模型（LLM）的应用开发。它通过提供标准化的接口，将模型、数据源、向量存储及外部工具等互操作性组件灵活串联，帮助开发者轻松构建功能强大的 AI 应用。\n\n在开发过程中，langchainjs 有效解决了技术迭代快导致的代码耦合度高、模型切换困难以及原型验证周期长等痛点。其模块化架构支持快速原型设计，让团队能迅速测试不同工作流而无需推倒重来；同时，高度的模型抽象层确保了应用的未来适应性，当需要更换底层模型或升级技术栈时，业务逻辑无需大幅修改。此外，它还支持与 LangSmith 和 LangGraph 无缝集成，为应用的监控、评估及复杂智能体编排提供了生产级支持。\n\n这款工具非常适合前端工程师、全栈开发者以及希望利用 Node.js 生态构建 AI 产品的技术团队。无论是需要从实时数据中增强模型能力的场景，还是追求高可控性的智能体工作流，langchainjs 都能提供从高层链式调用到底层精细控制的多层级抽象，助力开发者在活跃的开源生态中高效交付可靠产品。","\u003Cdiv align=\"center\">\n  \u003Ca href=\"https:\u002F\u002Fwww.langchain.com\u002F\">\n    \u003Cpicture>\n      \u003Csource media=\"(prefers-color-scheme: light)\" srcset=\".github\u002Fimages\u002Flogo-light.svg\">\n      \u003Csource media=\"(prefers-color-scheme: dark)\" srcset=\".github\u002Fimages\u002Flogo-dark.svg\">\n      \u003Cimg alt=\"LangChain Logo\" src=\".github\u002Fimages\u002Flogo-dark.svg\" width=\"50%\">\n    \u003C\u002Fpicture>\n  \u003C\u002Fa>\n\u003C\u002Fdiv>\n\n\u003Cdiv align=\"center\">\n  \u003Ch3>The agent engineering platform.\u003C\u002Fh3>\n\u003C\u002Fdiv>\n\n![npm](https:\u002F\u002Fimg.shields.io\u002Fnpm\u002Fdm\u002Flangchain) [![License: MIT](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FLicense-MIT-yellow.svg)](https:\u002F\u002Fopensource.org\u002Flicenses\u002FMIT) [![Twitter](https:\u002F\u002Fimg.shields.io\u002Ftwitter\u002Furl\u002Fhttps\u002Ftwitter.com\u002Flangchain.svg?style=social&label=Follow%20%40LangChain)](https:\u002F\u002Fx.com\u002Flangchain)\n\nLangChain is a framework for building LLM-powered applications. It helps you chain together interoperable components and third-party integrations to simplify AI application development — all while future-proofing decisions as the underlying technology evolves.\n\n**Documentation**: To learn more about LangChain, check out [the docs](https:\u002F\u002Fdocs.langchain.com\u002Foss\u002Fjavascript\u002Flangchain\u002Foverview).\n\nIf you're looking for more advanced customization or agent orchestration, check out [LangGraph.js](https:\u002F\u002Fdocs.langchain.com\u002Foss\u002Fjavascript\u002Flanggraph\u002Foverview). our framework for building agents and controllable workflows.\n\n> [!NOTE]\n> Looking for the Python version? Check out [LangChain](https:\u002F\u002Fgithub.com\u002Flangchain-ai\u002Flangchain).\n\nTo help you ship LangChain apps to production faster, check out [LangSmith](https:\u002F\u002Fsmith.langchain.com).\n[LangSmith](https:\u002F\u002Fsmith.langchain.com) is a unified developer platform for building, testing, and monitoring LLM applications.\n\n## ⚡️ Quick Install\n\nYou can use npm, pnpm, or yarn to install LangChain.js\n\n`npm install -S langchain` or `pnpm install langchain` or `yarn add langchain`\n\n## 🚀 Why use LangChain?\n\nLangChain helps developers build applications powered by LLMs through a standard interface for agents, models, embeddings, vector stores, and more.\n\nUse LangChain for:\n\n- **Real-time data augmentation**. Easily connect LLMs to diverse data sources and external\u002Finternal systems, drawing from LangChain’s vast library of integrations with model providers, tools, vector stores, retrievers, and more.\n- **Model interoperability**. Swap models in and out as your engineering team experiments to find the best choice for your application’s needs. As the industry frontier evolves, adapt quickly — LangChain’s abstractions keep you moving without losing momentum.\n- **Rapid prototyping**. Quickly build and iterate on LLM applications with LangChain's modular, component-based architecture. Test different approaches and workflows without rebuilding from scratch, accelerating your development cycle.\n- **Production-ready features**. Deploy reliable applications with built-in support for monitoring, evaluation, and debugging through integrations like LangSmith. Scale with confidence using battle-tested patterns and best practices.\n- **Vibrant community and ecosystem**. Leverage a rich ecosystem of integrations, templates, and community-contributed components. Benefit from continuous improvements and stay up-to-date with the latest AI developments through an active open-source community.\n- **Flexible abstraction layers**. Work at the level of abstraction that suits your needs - from high-level chains for quick starts to low-level components for fine-grained control. LangChain grows with your application's complexity.\n\n## 📦 LangChain's ecosystem\n\n- [LangSmith](https:\u002F\u002Fwww.langchain.com\u002Flangsmith) - Unified developer platform for building, testing, and monitoring LLM applications. With LangSmith, you can debug poor-performing LLM app runs, evaluate agent trajectories, gain visibility in production, and deploy agents with confidence.\n- [LangGraph](https:\u002F\u002Fdocs.langchain.com\u002Foss\u002Fjavascript\u002Flanggraph\u002Foverview) - Build agents that can reliably handle complex tasks with LangGraph, our low-level agent orchestration framework. LangGraph offers customizable architecture, long-term memory, and human-in-the-loop workflows — and is trusted in production by companies like LinkedIn, Uber, Klarna, and GitLab.\n\n## 🌐 Supported Environments\n\nLangChain.js is written in TypeScript and can be used in:\n\n- Node.js (ESM and CommonJS) - 20.x, 22.x, 24.x\n- Cloudflare Workers\n- Vercel \u002F Next.js (Browser, Serverless and Edge functions)\n- Supabase Edge Functions\n- Browser\n- Deno\n- Bun\n\n## 📖 Additional Resources\n\n- [Getting started](https:\u002F\u002Fdocs.langchain.com\u002Foss\u002Fjavascript\u002Flangchain\u002Foverview): Installation, setting up the environment, simple examples\n- [Learn](https:\u002F\u002Fdocs.langchain.com\u002Foss\u002Fjavascript\u002Flearn): Learn about the core concepts of LangChain.\n- [LangChain Forum](https:\u002F\u002Fforum.langchain.com): Connect with the community and share all of your technical questions, ideas, and feedback.\n- [Chat LangChain](https:\u002F\u002Fchat.langchain.com): Ask questions & chat with our documentation.\n\n## 💁 Contributing\n\nAs an open-source project in a rapidly developing field, we are extremely open to contributions, whether it be in the form of a new feature, improved infrastructure, or better documentation.\n\nFor detailed information on how to contribute, see [`CONTRIBUTING.md`](https:\u002F\u002Fgithub.com\u002Flangchain-ai\u002Flangchainjs\u002Fblob\u002Fmain\u002FCONTRIBUTING.md).\n\nPlease report any security issues or concerns following our [security guidelines](https:\u002F\u002Fgithub.com\u002Flangchain-ai\u002F.github\u002Fblob\u002Fmain\u002FSECURITY.md).\n","\u003Cdiv align=\"center\">\n  \u003Ca href=\"https:\u002F\u002Fwww.langchain.com\u002F\">\n    \u003Cpicture>\n      \u003Csource media=\"(prefers-color-scheme: light)\" srcset=\".github\u002Fimages\u002Flogo-light.svg\">\n      \u003Csource media=\"(prefers-color-scheme: dark)\" srcset=\".github\u002Fimages\u002Flogo-dark.svg\">\n      \u003Cimg alt=\"LangChain Logo\" src=\".github\u002Fimages\u002Flogo-dark.svg\" width=\"50%\">\n    \u003C\u002Fpicture>\n  \u003C\u002Fa>\n\u003C\u002Fdiv>\n\n\u003Cdiv align=\"center\">\n  \u003Ch3>智能体工程平台。\u003C\u002Fh3>\n\u003C\u002Fdiv>\n\n![npm](https:\u002F\u002Fimg.shields.io\u002Fnpm\u002Fdm\u002Flangchain) [![License: MIT](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FLicense-MIT-yellow.svg)](https:\u002F\u002Fopensource.org\u002Flicenses\u002FMIT) [![Twitter](https:\u002F\u002Fimg.shields.io\u002Ftwitter\u002Furl\u002Fhttps\u002Ftwitter.com\u002Flangchain.svg?style=social&label=Follow%20%40LangChain)](https:\u002F\u002Fx.com\u002Flangchain)\n\nLangChain 是一个用于构建由大语言模型驱动的应用程序的框架。它可以帮助您将可互操作的组件和第三方集成串联起来，从而简化 AI 应用开发——同时在底层技术不断演进的过程中，确保您的决策具有前瞻性。\n\n**文档**: 要了解更多关于 LangChain 的信息，请查看 [文档](https:\u002F\u002Fdocs.langchain.com\u002Foss\u002Fjavascript\u002Flangchain\u002Foverview)。\n\n如果您需要更高级的自定义功能或智能体编排，请查看 [LangGraph.js](https:\u002F\u002Fdocs.langchain.com\u002Foss\u002Fjavascript\u002Flanggraph\u002Foverview)，这是我们用于构建智能体和可控工作流的框架。\n\n> [!NOTE]\n> 您在寻找 Python 版本吗？请查看 [LangChain](https:\u002F\u002Fgithub.com\u002Flangchain-ai\u002Flangchain)。\n\n为了帮助您更快地将 LangChain 应用部署到生产环境，您可以使用 [LangSmith](https:\u002F\u002Fsmith.langchain.com)。[LangSmith](https:\u002F\u002Fsmith.langchain.com) 是一个统一的开发者平台，用于构建、测试和监控 LLM 应用程序。\n\n## ⚡️ 快速安装\n\n您可以使用 npm、pnpm 或 yarn 来安装 LangChain.js：\n\n`npm install -S langchain` 或 `pnpm install langchain` 或 `yarn add langchain`\n\n## 🚀 为什么使用 LangChain？\n\nLangChain 通过为智能体、模型、嵌入、向量存储等提供标准接口，帮助开发者构建由 LLM 驱动的应用程序。\n\n使用 LangChain 可以实现以下目标：\n\n- **实时数据增强**。轻松将 LLM 连接到各种数据源以及外部\u002F内部系统，利用 LangChain 丰富的集成库，连接模型提供商、工具、向量存储、检索器等。\n- **模型互操作性**。随着您的工程团队不断尝试，您可以灵活地切换不同的模型，找到最适合您应用需求的方案。随着行业前沿的不断发展，LangChain 的抽象层能够帮助您快速适应变化，而不影响开发进度。\n- **快速原型开发**。借助 LangChain 模块化、基于组件的架构，您可以快速构建和迭代 LLM 应用程序。无需从头开始重建，即可测试不同的方法和工作流，从而加速开发周期。\n- **生产就绪的功能**。通过与 LangSmith 等工具的集成，LangChain 提供了内置的监控、评估和调试支持，帮助您部署可靠的应用程序。借助经过实战检验的模式和最佳实践，您可以自信地扩展规模。\n- **活跃的社区与生态系统**。利用丰富的集成、模板和社区贡献的组件，受益于持续改进，并通过活跃的开源社区及时了解最新的 AI 发展动态。\n- **灵活的抽象层**。您可以根据需求选择合适的抽象层次——从适合快速上手的高层链式结构，到用于精细控制的底层组件。LangChain 随着您的应用复杂度不断增加而成长。\n\n## 📦 LangChain 的生态系统\n\n- [LangSmith](https:\u002F\u002Fwww.langchain.com\u002Flangsmith) —— 用于构建、测试和监控 LLM 应用程序的统一开发者平台。借助 LangSmith，您可以调试性能不佳的 LLM 应用运行情况，评估智能体轨迹，在生产环境中获得可观测性，并自信地部署智能体。\n- [LangGraph](https:\u002F\u002Fdocs.langchain.com\u002Foss\u002Fjavascript\u002Flanggraph\u002Foverview) —— 使用 LangGraph，我们提供的低层智能体编排框架，构建能够可靠处理复杂任务的智能体。LangGraph 提供可定制的架构、长期记忆以及人机协作的工作流，已被 LinkedIn、Uber、Klarna 和 GitLab 等公司广泛应用于生产环境。\n\n## 🌐 支持的环境\n\nLangChain.js 使用 TypeScript 编写，可在以下环境中使用：\n\n- Node.js（ESM 和 CommonJS）：20.x、22.x、24.x\n- Cloudflare Workers\n- Vercel \u002F Next.js（浏览器、无服务器和边缘函数）\n- Supabase Edge Functions\n- 浏览器\n- Deno\n- Bun\n\n## 📖 更多资源\n\n- [入门指南](https:\u002F\u002Fdocs.langchain.com\u002Foss\u002Fjavascript\u002Flangchain\u002Foverview)：安装、环境配置、简单示例\n- [学习](https:\u002F\u002Fdocs.langchain.com\u002Foss\u002Fjavascript\u002Flearn)：了解 LangChain 的核心概念\n- [LangChain 论坛](https:\u002F\u002Fforum.langchain.com)：与社区交流，分享您的技术问题、想法和反馈\n- [Chat LangChain](https:\u002F\u002Fchat.langchain.com)：提问并与我们的文档团队聊天\n\n## 💁 贡献\n\n作为一项处于快速发展领域的开源项目，我们非常欢迎任何形式的贡献，无论是新功能、基础设施改进还是文档优化。\n\n有关如何贡献的详细信息，请参阅 [`CONTRIBUTING.md`](https:\u002F\u002Fgithub.com\u002Flangchain-ai\u002Flangchainjs\u002Fblob\u002Fmain\u002FCONTRIBUTING.md)。\n\n如发现任何安全问题或疑虑，请按照我们的 [安全指南](https:\u002F\u002Fgithub.com\u002Flangchain-ai\u002F.github\u002Fblob\u002Fmain\u002FSECURITY.md) 进行报告。","# LangChain.js 快速上手指南\n\nLangChain.js 是一个用于构建大语言模型（LLM）驱动应用的框架。它通过标准化的接口连接模型、向量存储、工具等组件，帮助开发者快速原型设计并部署生产级 AI 应用。\n\n## 环境准备\n\n**系统要求**\nLangChain.js 基于 TypeScript 编写，支持以下运行环境：\n- **Node.js**: 版本 20.x, 22.x, 24.x (支持 ESM 和 CommonJS)\n- **边缘计算\u002FServerless**: Cloudflare Workers, Vercel (Next.js), Supabase Edge Functions\n- **其他运行时**: Deno, Bun\n- **浏览器**: 可直接在前端环境中使用\n\n**前置依赖**\n- 已安装 Node.js 及包管理器（npm, pnpm 或 yarn）\n- 获取相关 LLM 提供商的 API Key（如 OpenAI, Anthropic 等）\n\n> **国内开发者提示**：如果访问 npm 官方源较慢，建议配置淘宝镜像源：\n> `npm config set registry https:\u002F\u002Fregistry.npmmirror.com`\n\n## 安装步骤\n\n你可以使用 npm、pnpm 或 yarn 进行安装。任选其一即可：\n\n```bash\nnpm install -S langchain\n```\n\n或者\n\n```bash\npnpm install langchain\n```\n\n或者\n\n```bash\nyarn add langchain\n```\n\n*注：根据你使用的具体模型提供商（如 OpenAI），可能还需要安装对应的额外依赖包，例如 `@langchain\u002Fopenai`。*\n\n## 基本使用\n\n以下是一个最简单的示例，展示如何初始化模型并调用 LLM 生成回复。本示例以 OpenAI 模型为例。\n\n1. **设置环境变量**\n   在终端中设置你的 API Key（或在项目根目录创建 `.env` 文件）：\n   ```bash\n   export OPENAI_API_KEY=\"your-api-key-here\"\n   ```\n\n2. **编写代码**\n   创建一个 `index.js` (或 `index.ts`) 文件：\n\n```javascript\nimport { ChatOpenAI } from \"@langchain\u002Fopenai\";\nimport { HumanMessage } from \"@langchain\u002Fcore\u002Fmessages\";\n\n\u002F\u002F 初始化模型\nconst model = new ChatOpenAI({\n  modelName: \"gpt-3.5-turbo\",\n  temperature: 0.7,\n});\n\n\u002F\u002F 定义消息并调用模型\nconst message = new HumanMessage(\"你好，请简单介绍一下 LangChain.js\");\nconst response = await model.invoke([message]);\n\n\u002F\u002F 输出结果\nconsole.log(response.content);\n```\n\n3. **运行程序**\n   确保你的 `package.json` 中设置了 `\"type\": \"module\"` 以支持 ES Modules，然后运行：\n\n```bash\nnode index.js\n```\n\n你将看到模型返回的介绍内容。在此基础上，你可以进一步结合向量存储、链式调用（Chains）或代理（Agents）来构建更复杂的应用。","某电商初创团队急需构建一个能实时查询库存、检索商品知识库并自动处理退换货的智能客服助手。\n\n### 没有 langchainjs 时\n- **数据孤岛严重**：开发者需手动编写大量胶水代码连接数据库、向量库和外部 API，每次新增数据源都要重构底层逻辑，耗时且易出错。\n- **模型切换成本极高**：若要从 OpenAI 切换到本地部署的 Llama 模型，必须重写整个提示词管理和响应解析模块，导致技术选型被单一厂商锁定。\n- **复杂流程难以维护**：处理“先查库存再推荐替代品”的多步推理逻辑时，状态管理混乱，代码嵌套过深，调试极其困难。\n- **缺乏生产级监控**：上线后无法追踪用户提问的完整链路，遇到回答幻觉或超时错误时，只能靠猜测定位问题，排查效率低下。\n\n### 使用 langchainjs 后\n- **集成效率飞跃**：利用 langchainjs 丰富的内置组件，通过几行配置即可串联起 PostgreSQL、Pinecone 和内部订单系统，快速实现数据增强。\n- **模型无缝热插拔**：借助统一的抽象接口，团队可在不改动业务逻辑的前提下，自由对比不同大模型的效果，灵活适配成本与性能需求。\n- **工作流清晰可控**：通过模块化链式调用轻松编排复杂任务，将多步推理转化为可视化的执行序列，显著降低逻辑维护难度。\n- **全链路可观测性**：结合 LangSmith 插件，实时监控每一次调用的延迟、Token 消耗及中间步骤，迅速定位并修复异常，保障服务稳定性。\n\nlangchainjs 让开发团队从繁琐的基础设施搭建中解放出来，专注于核心业务逻辑，将智能应用的交付周期从数周缩短至几天。","https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Flangchain-ai_langchainjs_156e2ce0.png","langchain-ai","LangChain","https:\u002F\u002Foss.gittoolsai.com\u002Favatars\u002Flangchain-ai_8e6aaeef.png","",null,"support@langchain.dev","https:\u002F\u002Fwww.langchain.com","https:\u002F\u002Fgithub.com\u002Flangchain-ai",[23,27,31,35,39],{"name":24,"color":25,"percentage":26},"TypeScript","#3178c6",97.3,{"name":28,"color":29,"percentage":30},"HTML","#e34c26",1.9,{"name":32,"color":33,"percentage":34},"JavaScript","#f1e05a",0.5,{"name":36,"color":37,"percentage":38},"Shell","#89e051",0.2,{"name":40,"color":41,"percentage":42},"CSS","#663399",0.1,17430,3110,"2026-04-07T11:35:09","MIT",1,"未说明",{"notes":50,"python":51,"dependencies":52},"该工具为 LangChain 的 JavaScript\u002FTypeScript 版本，非 Python 项目。支持在 Node.js (ESM 和 CommonJS)、Cloudflare Workers、Vercel\u002FNext.js、Supabase Edge Functions、浏览器、Deno 和 Bun 环境中运行。无需 GPU，具体资源需求取决于所调用的大模型服务或本地运行时环境。","不适用 (基于 JavaScript\u002FTypeScript)",[53,54],"Node.js 20.x\u002F22.x\u002F24.x","npm\u002Fpnpm\u002Fyarn",[56,57,58],"语言模型","开发框架","Agent",2,"ready","2026-03-27T02:49:30.150509","2026-04-08T01:49:47.141618",[64,69,74,79,84,89],{"id":65,"question_zh":66,"answer_zh":67,"source_url":68},23381,"遇到 'ERR_PACKAGE_PATH_NOT_EXPORTED: No exports main defined' 错误怎么办？","该错误通常发生在 langchain 版本 0.0.13 及以上。解决方法是修改导入路径，使用特定的子包路径而不是主包。例如：\n- 将 `import ... from \"langchain\"` 改为 `import ... from \"@langchain\u002Fcore\u002Fprompts\"`、`import ... from \"@langchain\u002Fopenai\"` 等具体子包。\n- 确保在 `package.json` 中设置 `\"type\": \"module\"`。\n- 如果问题依旧，尝试删除 `node_modules` 和 `package-lock.json`，然后重新运行 `npm install`。","https:\u002F\u002Fgithub.com\u002Flangchain-ai\u002Flangchainjs\u002Fissues\u002F185",{"id":70,"question_zh":71,"answer_zh":72,"source_url":73},23382,"如何在 RetrievalQAChain 中获取 Token 使用量统计？","默认情况下，`RetrievalQAChain` 的回调中可能无法直接获取 `tokenUsage`。你需要确保使用的是支持该属性的最新版本，或者检查 LLM 实例（如 ChatOpenAI）是否正确传递了回调。如果 `tokenUsage` 为 undefined，可能是因为链式调用未正确传播输出信息。建议查看官方是否已发布修复补丁，或考虑手动在 LLM 层而非 Chain 层统计 Token。","https:\u002F\u002Fgithub.com\u002Flangchain-ai\u002Flangchainjs\u002Fissues\u002F965",{"id":75,"question_zh":76,"answer_zh":77,"source_url":78},23383,"在使用 ConversationChain 时遇到 Axios 网络错误（Network Error）如何解决？","此问题常见于代理环境或特定网络配置下。从 langchain 0.0.71 版本开始，非流式模式下默认使用 axios 适配器，而流式模式强制使用 fetch 适配器。如果你在使用代理且不需要流式传输，请确保升级到 0.0.71 或更高版本。如果仍需配置代理，可能需要自定义 axios 实例或通过环境变量（如 `HTTP_PROXY`）配置系统级代理。","https:\u002F\u002Fgithub.com\u002Flangchain-ai\u002Flangchainjs\u002Fissues\u002F739",{"id":80,"question_zh":81,"answer_zh":82,"source_url":83},23384,"如何在 Cloudflare Workers 或 Vercel Edge Functions 等边缘环境中运行 LangChain.js？","LangChain.js 已逐步移除对 Node.js 特有 API（如 `fs`, `crypto`, `node-fetch`）的依赖以支持边缘环境。关键步骤包括：\n1. 确保使用最新版本（已移除 WASM tokeniser 依赖）。\n2. 对于 Next.js\u002FVercel 项目，无需特殊配置即可运行；若需使用 tokenizer，需在 `next.config.js` 中启用 WebAssembly 支持。\n3. 避免使用仅支持 Node 的向量存储（如 hnswlib），选择兼容浏览器的实现。","https:\u002F\u002Fgithub.com\u002Flangchain-ai\u002Flangchainjs\u002Fissues\u002F62",{"id":85,"question_zh":86,"answer_zh":87,"source_url":88},23385,"编译时出现 'Cannot find name this' 的 TypeScript 错误如何处理？","该错误通常出现在 TypeScript 编译 `@langchain\u002Fcore` 的类型定义文件时，特别是在 Node 18 环境下。这往往是由于 TypeScript 版本过旧或与 ESM 模块系统不兼容导致的。解决方案包括：\n1. 升级 TypeScript 到最新版本。\n2. 确保 `tsconfig.json` 中设置了 `\"module\": \"ESNext\"` 和 `\"target\": \"ES2020\"` 或更高。\n3. 检查 `package.json` 中是否包含 `\"type\": \"module\"`，并确保所有导入语句使用 ES Module 语法。","https:\u002F\u002Fgithub.com\u002Flangchain-ai\u002Flangchainjs\u002Fissues\u002F4043",{"id":90,"question_zh":91,"answer_zh":92,"source_url":68},23386,"为什么在导入 '@langchain\u002Fcommunity\u002Fdocument_loaders\u002Ffs\u002Fpdf' 时提示子路径未定义？","这是因为新版 LangChain 严格限制了 `exports` 字段，不允许随意导入内部子路径。解决方法是使用官方推荐的公开导出路径。如果必须加载 PDF，请确认使用的导入路径是否在 `package.json` 的 `exports` 中明确列出。通常应使用类似 `import { PDFLoader } from \"@langchain\u002Fcommunity\u002Fdocument_loaders\u002Ffs\u002Fpdf.js\"`（带 `.js` 后缀）或检查文档获取正确的导入方式。同时确保项目配置了 `\"type\": \"module\"`。",[94,99,104,109,114,119,124,129,133,138,143,148,153,158,163,168,173,178,183,188],{"id":95,"version":96,"summary_zh":97,"released_at":98},144880,"@langchain\u002Fgroq@1.2.0","### 小改动\n\n-   [#10603](https:\u002F\u002Fgithub.com\u002Flangchain-ai\u002Flangchainjs\u002Fpull\u002F10603) [`66effb0`](https:\u002F\u002Fgithub.com\u002Flangchain-ai\u002Flangchainjs\u002Fcommit\u002F66effb028baf5c923501801c989c7377efb8b77a) 感谢 [@dependabot](https:\u002F\u002Fgithub.com\u002Fapps\u002Fdependabot)! - chore(deps): 将 groq-sdk 从 0.37.0 升级到 1.1.2\n","2026-04-03T23:12:43",{"id":100,"version":101,"summary_zh":102,"released_at":103},144881,"@langchain\u002Fclassic@1.0.28","### 补丁变更\n\n-   [#10591](https:\u002F\u002Fgithub.com\u002Flangchain-ai\u002Flangchainjs\u002Fpull\u002F10591) [`d7a98cd`](https:\u002F\u002Fgithub.com\u002Flangchain-ai\u002Flangchainjs\u002Fcommit\u002Fd7a98cda1a5d9bf9b93b503fc54374f1aaf1a37e) 感谢 [@christian-bromann](https:\u002F\u002Fgithub.com\u002Fchristian-bromann)! - 功能：添加 @langchain\u002Fperplexity 独立提供者包\n\n-   [#10594](https:\u002F\u002Fgithub.com\u002Flangchain-ai\u002Flangchainjs\u002Fpull\u002F10594) [`884c2d3`](https:\u002F\u002Fgithub.com\u002Flangchain-ai\u002Flangchainjs\u002Fcommit\u002F884c2d3d1b2c49225d73ddec2235ad174db36f86) 感谢 [@christian-bromann](https:\u002F\u002Fgithub.com\u002Fchristian-bromann)! - 功能（fireworks）：提取独立提供者包\n\n-   [#10593](https:\u002F\u002Fgithub.com\u002Flangchain-ai\u002Flangchainjs\u002Fpull\u002F10593) [`0fb6fa4`](https:\u002F\u002Fgithub.com\u002Flangchain-ai\u002Flangchainjs\u002Fcommit\u002F0fb6fa40dcd3a09a4fb91f36c9f2ca869552961e) 感谢 [@christian-bromann](https:\u002F\u002Fgithub.com\u002Fchristian-bromann)! - 功能（together-ai）：将 Together AI 迁移到提供者包中\n\n-   更新了依赖项 \\[[`d6bf4fc`](https:\u002F\u002Fgithub.com\u002Flangchain-ai\u002Flangchainjs\u002Fcommit\u002Fd6bf4fc91b2c2eb931bf3bc7606b1817632bc8c1)]：\n    -   @langchain\u002Fopenai@1.4.2\n","2026-04-03T23:12:40",{"id":105,"version":106,"summary_zh":107,"released_at":108},144882,"@langchain\u002Fxai@1.3.14","### 补丁变更\n\n-   更新了依赖项 \\[[`d6bf4fc`](https:\u002F\u002Fgithub.com\u002Flangchain-ai\u002Flangchainjs\u002Fcommit\u002Fd6bf4fc91b2c2eb931bf3bc7606b1817632bc8c1)]:\n    -   @langchain\u002Fopenai@1.4.2\n","2026-04-03T23:12:37",{"id":110,"version":111,"summary_zh":112,"released_at":113},144883,"@langchain\u002Fopenai@1.4.2","### 补丁变更\n\n-   [#10614](https:\u002F\u002Fgithub.com\u002Flangchain-ai\u002Flangchainjs\u002Fpull\u002F10614) [`d6bf4fc`](https:\u002F\u002Fgithub.com\u002Flangchain-ai\u002Flangchainjs\u002Fcommit\u002Fd6bf4fc91b2c2eb931bf3bc7606b1817632bc8c1) 感谢 [@colifran](https:\u002F\u002Fgithub.com\u002Fcolifran)! - 新增（openai）：为 OpenAI 文件输入添加占位符文件名\n\n-   更新了依赖项 \\[[`d3d0922`](https:\u002F\u002Fgithub.com\u002Flangchain-ai\u002Flangchainjs\u002Fcommit\u002Fd3d0922c24afcd3006fb94dcadd3ebe08fbf2383)]：\n    -   @langchain\u002Fcore@1.1.39\n","2026-04-03T23:12:34",{"id":115,"version":116,"summary_zh":117,"released_at":118},144884,"@langchain\u002Fneo4j@0.1.0","### 小改动\n\n-   [#10590](https:\u002F\u002Fgithub.com\u002Flangchain-ai\u002Flangchainjs\u002Fpull\u002F10590) [`ed8cda6`](https:\u002F\u002Fgithub.com\u002Flangchain-ai\u002Flangchainjs\u002Fcommit\u002Fed8cda659c893219d853a402f0fcd46e06cf7c28) 感谢 [@christian-bromann](https:\u002F\u002Fgithub.com\u002Fchristian-bromann)! - 功能：搭建 @langchain\u002Fneo4j 提供者包\n\n### 补丁更新\n\n-   更新了依赖项 \\[[`d7a98cd`](https:\u002F\u002Fgithub.com\u002Flangchain-ai\u002Flangchainjs\u002Fcommit\u002Fd7a98cda1a5d9bf9b93b503fc54374f1aaf1a37e), [`884c2d3`](https:\u002F\u002Fgithub.com\u002Flangchain-ai\u002Flangchainjs\u002Fcommit\u002F884c2d3d1b2c49225d73ddec2235ad174db36f86), [`0fb6fa4`](https:\u002F\u002Fgithub.com\u002Flangchain-ai\u002Flangchainjs\u002Fcommit\u002F0fb6fa40dcd3a09a4fb91f36c9f2ca869552961e), [`d3d0922`](https:\u002F\u002Fgithub.com\u002Flangchain-ai\u002Flangchainjs\u002Fcommit\u002Fd3d0922c24afcd3006fb94dcadd3ebe08fbf2383)]：\n    -   @langchain\u002Fclassic@1.0.28\n    -   @langchain\u002Fcore@1.1.39","2026-04-03T23:12:31",{"id":120,"version":121,"summary_zh":122,"released_at":123},144885,"@langchain\u002Fopenrouter@0.2.0","### 小改动\n\n-   [#10559](https:\u002F\u002Fgithub.com\u002Flangchain-ai\u002Flangchainjs\u002Fpull\u002F10559) [`17aedaa`](https:\u002F\u002Fgithub.com\u002Flangchain-ai\u002Flangchainjs\u002Fcommit\u002F17aedaabfca680a9f8bb8f858395ee1ee4f152a1) 感谢 [@mdrxy](https:\u002F\u002Fgithub.com\u002Fmdrxy)! - 添加 `appCategories` 字段，用于 OpenRouter 市场的归属标识（`X-OpenRouter-Categories` 头），并更新默认的 `siteUrl` 和 `siteName` 值。归属头现在仅在已设置时才会发送。\n\n### 补丁更新\n\n-   更新了依赖项 \\[[`d6bf4fc`](https:\u002F\u002Fgithub.com\u002Flangchain-ai\u002Flangchainjs\u002Fcommit\u002Fd6bf4fc91b2c2eb931bf3bc7606b1817632bc8c1)]:\n    -   @langchain\u002Fopenai@1.4.2\n","2026-04-03T23:12:28",{"id":125,"version":126,"summary_zh":127,"released_at":128},144886,"@langchain\u002Ffireworks@0.1.0","### 小幅变更\n\n-   [#10594](https:\u002F\u002Fgithub.com\u002Flangchain-ai\u002Flangchainjs\u002Fpull\u002F10594) [`884c2d3`](https:\u002F\u002Fgithub.com\u002Flangchain-ai\u002Flangchainjs\u002Fcommit\u002F884c2d3d1b2c49225d73ddec2235ad174db36f86) 感谢 [@christian-bromann](https:\u002F\u002Fgithub.com\u002Fchristian-bromann)! - 功能（fireworks）：提取独立的提供商包\n\n### 补丁变更\n\n-   更新了依赖项 \\[[`d6bf4fc`](https:\u002F\u002Fgithub.com\u002Flangchain-ai\u002Flangchainjs\u002Fcommit\u002Fd6bf4fc91b2c2eb931bf3bc7606b1817632bc8c1)]：\n    -   @langchain\u002Fopenai@1.4.2\n","2026-04-03T23:12:25",{"id":130,"version":131,"summary_zh":107,"released_at":132},144887,"@langchain\u002Fdeepseek@1.0.22","2026-04-03T23:12:22",{"id":134,"version":135,"summary_zh":136,"released_at":137},144888,"@langchain\u002Fperplexity@0.1.0","### 小幅改动\n\n-   [#10591](https:\u002F\u002Fgithub.com\u002Flangchain-ai\u002Flangchainjs\u002Fpull\u002F10591) [`d7a98cd`](https:\u002F\u002Fgithub.com\u002Flangchain-ai\u002Flangchainjs\u002Fcommit\u002Fd7a98cda1a5d9bf9b93b503fc54374f1aaf1a37e) 感谢 [@christian-bromann](https:\u002F\u002Fgithub.com\u002Fchristian-bromann)! - 功能：添加 @langchain\u002Fperplexity 独立提供商包\n","2026-04-03T23:12:19",{"id":139,"version":140,"summary_zh":141,"released_at":142},144889,"@langchain\u002Ftogether-ai@0.1.0","### 小改动\n\n-   [#10593](https:\u002F\u002Fgithub.com\u002Flangchain-ai\u002Flangchainjs\u002Fpull\u002F10593) [`0fb6fa4`](https:\u002F\u002Fgithub.com\u002Flangchain-ai\u002Flangchainjs\u002Fcommit\u002F0fb6fa40dcd3a09a4fb91f36c9f2ca869552961e) 感谢 [@christian-bromann](https:\u002F\u002Fgithub.com\u002Fchristian-bromann)! - 新增功能（together-ai）：将 Together AI 迁移到 provider 包中\n\n### 修复性更改\n\n-   更新了依赖项 \\[[`d6bf4fc`](https:\u002F\u002Fgithub.com\u002Flangchain-ai\u002Flangchainjs\u002Fcommit\u002Fd6bf4fc91b2c2eb931bf3bc7606b1817632bc8c1)]：\n    -   @langchain\u002Fopenai@1.4.2\n","2026-04-03T23:12:16",{"id":144,"version":145,"summary_zh":146,"released_at":147},144890,"@langchain\u002Fibm@0.1.0","### Minor Changes\n\n-   [#10589](https:\u002F\u002Fgithub.com\u002Flangchain-ai\u002Flangchainjs\u002Fpull\u002F10589) [`ba03669`](https:\u002F\u002Fgithub.com\u002Flangchain-ai\u002Flangchainjs\u002Fcommit\u002Fba0366964ad4e697cba36404ed298c1b04b6f8a9) Thanks [@christian-bromann](https:\u002F\u002Fgithub.com\u002Fchristian-bromann)! - feat: add @langchain\u002Fibm package - IBM watsonx.ai integration\n\n### Patch Changes\n\n-   Updated dependencies \\[[`d3d0922`](https:\u002F\u002Fgithub.com\u002Flangchain-ai\u002Flangchainjs\u002Fcommit\u002Fd3d0922c24afcd3006fb94dcadd3ebe08fbf2383)]:\n    -   @langchain\u002Fcore@1.1.39\n","2026-04-03T23:12:13",{"id":149,"version":150,"summary_zh":151,"released_at":152},144891,"@langchain\u002Fgoogle@0.1.10","### Patch Changes\n\n-   [#10550](https:\u002F\u002Fgithub.com\u002Flangchain-ai\u002Flangchainjs\u002Fpull\u002F10550) [`9781bff`](https:\u002F\u002Fgithub.com\u002Flangchain-ai\u002Flangchainjs\u002Fcommit\u002F9781bff525bffdd3b6a75adfa8a30fdb4bfc505e) Thanks [@muhammadosama984](https:\u002F\u002Fgithub.com\u002Fmuhammadosama984)! - fix(google): align `mediaResolution` with Gemini scalar values and support `detail` alias mapping (`low`\u002F`high`\u002F`auto`) for media prompts.\n","2026-04-03T23:12:10",{"id":154,"version":155,"summary_zh":156,"released_at":157},144892,"@langchain\u002Fpgvector@0.1.0","### Minor Changes\n\n-   [#10592](https:\u002F\u002Fgithub.com\u002Flangchain-ai\u002Flangchainjs\u002Fpull\u002F10592) [`ca0a41d`](https:\u002F\u002Fgithub.com\u002Flangchain-ai\u002Flangchainjs\u002Fcommit\u002Fca0a41d2e043a99eb4db06e641d11fb8d6972f0c) Thanks [@christian-bromann](https:\u002F\u002Fgithub.com\u002Fchristian-bromann)! - feat: add @langchain\u002Fpgvector standalone package\n","2026-04-03T23:12:07",{"id":159,"version":160,"summary_zh":161,"released_at":162},144893,"@langchain\u002Faws@1.3.4","### Patch Changes\n\n-   [#10658](https:\u002F\u002Fgithub.com\u002Flangchain-ai\u002Flangchainjs\u002Fpull\u002F10658) [`793bc69`](https:\u002F\u002Fgithub.com\u002Flangchain-ai\u002Flangchainjs\u002Fcommit\u002F793bc69a8af8198de9d157c21070871660e6bb13) Thanks [@colifran](https:\u002F\u002Fgithub.com\u002Fcolifran)! - feat(aws): impute file name for document content blocks\n","2026-04-03T23:12:04",{"id":164,"version":165,"summary_zh":166,"released_at":167},144894,"@langchain\u002Fcore@1.1.39","### Patch Changes\n\n-   [#10430](https:\u002F\u002Fgithub.com\u002Flangchain-ai\u002Flangchainjs\u002Fpull\u002F10430) [`d3d0922`](https:\u002F\u002Fgithub.com\u002Flangchain-ai\u002Flangchainjs\u002Fcommit\u002Fd3d0922c24afcd3006fb94dcadd3ebe08fbf2383) Thanks [@christian-bromann](https:\u002F\u002Fgithub.com\u002Fchristian-bromann)! - feat(langchain): support for browser tools\n","2026-04-03T23:12:01",{"id":169,"version":170,"summary_zh":171,"released_at":172},144895,"langchain@1.3.0","### Minor Changes\n\n-   [#10430](https:\u002F\u002Fgithub.com\u002Flangchain-ai\u002Flangchainjs\u002Fpull\u002F10430) [`d3d0922`](https:\u002F\u002Fgithub.com\u002Flangchain-ai\u002Flangchainjs\u002Fcommit\u002Fd3d0922c24afcd3006fb94dcadd3ebe08fbf2383) Thanks [@christian-bromann](https:\u002F\u002Fgithub.com\u002Fchristian-bromann)! - feat(langchain): support for browser tools\n\n### Patch Changes\n\n-   [#10591](https:\u002F\u002Fgithub.com\u002Flangchain-ai\u002Flangchainjs\u002Fpull\u002F10591) [`d7a98cd`](https:\u002F\u002Fgithub.com\u002Flangchain-ai\u002Flangchainjs\u002Fcommit\u002Fd7a98cda1a5d9bf9b93b503fc54374f1aaf1a37e) Thanks [@christian-bromann](https:\u002F\u002Fgithub.com\u002Fchristian-bromann)! - feat: add @langchain\u002Fperplexity standalone provider package\n\n-   [#10594](https:\u002F\u002Fgithub.com\u002Flangchain-ai\u002Flangchainjs\u002Fpull\u002F10594) [`884c2d3`](https:\u002F\u002Fgithub.com\u002Flangchain-ai\u002Flangchainjs\u002Fcommit\u002F884c2d3d1b2c49225d73ddec2235ad174db36f86) Thanks [@christian-bromann](https:\u002F\u002Fgithub.com\u002Fchristian-bromann)! - feat(fireworks): extract standalone provider package\n\n-   [#10593](https:\u002F\u002Fgithub.com\u002Flangchain-ai\u002Flangchainjs\u002Fpull\u002F10593) [`0fb6fa4`](https:\u002F\u002Fgithub.com\u002Flangchain-ai\u002Flangchainjs\u002Fcommit\u002F0fb6fa40dcd3a09a4fb91f36c9f2ca869552961e) Thanks [@christian-bromann](https:\u002F\u002Fgithub.com\u002Fchristian-bromann)! - feat(together-ai): migrate Together AI into provider package\n\n-   [#10654](https:\u002F\u002Fgithub.com\u002Flangchain-ai\u002Flangchainjs\u002Fpull\u002F10654) [`3bd85c1`](https:\u002F\u002Fgithub.com\u002Flangchain-ai\u002Flangchainjs\u002Fcommit\u002F3bd85c17869e95d5d1a67c5fccc0c4cab2646616) Thanks [@jabiinfante](https:\u002F\u002Fgithub.com\u002Fjabiinfante)! - feat(langchain): add ChatGoogle support to initChatModel\n\n-   Updated dependencies \\[[`d3d0922`](https:\u002F\u002Fgithub.com\u002Flangchain-ai\u002Flangchainjs\u002Fcommit\u002Fd3d0922c24afcd3006fb94dcadd3ebe08fbf2383)]:\n    -   @langchain\u002Fcore@1.1.39\n","2026-04-03T23:11:58",{"id":174,"version":175,"summary_zh":176,"released_at":177},144896,"@langchain\u002Fopenai@1.4.1","### Patch Changes\n\n-   [#10551](https:\u002F\u002Fgithub.com\u002Flangchain-ai\u002Flangchainjs\u002Fpull\u002F10551) [`9270c48`](https:\u002F\u002Fgithub.com\u002Flangchain-ai\u002Flangchainjs\u002Fcommit\u002F9270c48d7a95db6e7e2570a7e681c94479a673d0) Thanks [@muhammadosama984](https:\u002F\u002Fgithub.com\u002Fmuhammadosama984)! - fix(openai): preserve reasoning_content in ChatOpenAICompletions\n\n-   Updated dependencies \\[[`589ab9b`](https:\u002F\u002Fgithub.com\u002Flangchain-ai\u002Flangchainjs\u002Fcommit\u002F589ab9be391a5d6c104f34877fc1b3e2a32fa449)]:\n    -   @langchain\u002Fcore@1.1.38\n","2026-03-31T01:11:14",{"id":179,"version":180,"summary_zh":181,"released_at":182},144897,"langchain@1.2.39","### Patch Changes\n\n-   [#10543](https:\u002F\u002Fgithub.com\u002Flangchain-ai\u002Flangchainjs\u002Fpull\u002F10543) [`7ed93b8`](https:\u002F\u002Fgithub.com\u002Flangchain-ai\u002Flangchainjs\u002Fcommit\u002F7ed93b8b8a6e9eb0da3e103d74087c692fee2773) Thanks [@pawel-twardziak](https:\u002F\u002Fgithub.com\u002Fpawel-twardziak)! - fix(langchain): allow dynamic tools in wrapModelCall with wrapToolCall\n\n-   [#10554](https:\u002F\u002Fgithub.com\u002Flangchain-ai\u002Flangchainjs\u002Fpull\u002F10554) [`11a295f`](https:\u002F\u002Fgithub.com\u002Flangchain-ai\u002Flangchainjs\u002Fcommit\u002F11a295fdadec3809f40c10492e3fd474e832c468) Thanks [@christian-bromann](https:\u002F\u002Fgithub.com\u002Fchristian-bromann)! - fix(langchain): add support for dynamic structured output\n\n-   [#10555](https:\u002F\u002Fgithub.com\u002Flangchain-ai\u002Flangchainjs\u002Fpull\u002F10555) [`f548053`](https:\u002F\u002Fgithub.com\u002Flangchain-ai\u002Flangchainjs\u002Fcommit\u002Ff54805305787fa383c3ce1e287daafdb5464a98b) Thanks [@christian-bromann](https:\u002F\u002Fgithub.com\u002Fchristian-bromann)! - fix(langchain): bump langgraph dep\n\n-   [#10552](https:\u002F\u002Fgithub.com\u002Flangchain-ai\u002Flangchainjs\u002Fpull\u002F10552) [`589ab9b`](https:\u002F\u002Fgithub.com\u002Flangchain-ai\u002Flangchainjs\u002Fcommit\u002F589ab9be391a5d6c104f34877fc1b3e2a32fa449) Thanks [@christian-bromann](https:\u002F\u002Fgithub.com\u002Fchristian-bromann)! - fix(langchain): accept cross-version runnable models in createAgent\n\n-   Updated dependencies \\[[`589ab9b`](https:\u002F\u002Fgithub.com\u002Flangchain-ai\u002Flangchainjs\u002Fcommit\u002F589ab9be391a5d6c104f34877fc1b3e2a32fa449)]:\n    -   @langchain\u002Fcore@1.1.38\n","2026-03-31T01:11:11",{"id":184,"version":185,"summary_zh":186,"released_at":187},144898,"@langchain\u002Fxai@1.3.13","### Patch Changes\n\n-   Updated dependencies \\[[`9270c48`](https:\u002F\u002Fgithub.com\u002Flangchain-ai\u002Flangchainjs\u002Fcommit\u002F9270c48d7a95db6e7e2570a7e681c94479a673d0)]:\n    -   @langchain\u002Fopenai@1.4.1\n","2026-03-31T01:11:08",{"id":189,"version":190,"summary_zh":191,"released_at":192},144899,"@langchain\u002Fcommunity@1.1.27","### Patch Changes\n\n-   Updated dependencies \\[[`9270c48`](https:\u002F\u002Fgithub.com\u002Flangchain-ai\u002Flangchainjs\u002Fcommit\u002F9270c48d7a95db6e7e2570a7e681c94479a673d0), [`589ab9b`](https:\u002F\u002Fgithub.com\u002Flangchain-ai\u002Flangchainjs\u002Fcommit\u002F589ab9be391a5d6c104f34877fc1b3e2a32fa449)]:\n    -   @langchain\u002Fopenai@1.4.1\n    -   @langchain\u002Fcore@1.1.38\n    -   @langchain\u002Fclassic@1.0.27\n","2026-03-31T01:11:05",[194,205,213,221,229,238],{"id":195,"name":196,"github_repo":197,"description_zh":198,"stars":199,"difficulty_score":200,"last_commit_at":201,"category_tags":202,"status":60},4358,"openclaw","openclaw\u002Fopenclaw","OpenClaw 是一款专为个人打造的本地化 AI 助手，旨在让你在自己的设备上拥有完全可控的智能伙伴。它打破了传统 AI 助手局限于特定网页或应用的束缚，能够直接接入你日常使用的各类通讯渠道，包括微信、WhatsApp、Telegram、Discord、iMessage 等数十种平台。无论你在哪个聊天软件中发送消息，OpenClaw 都能即时响应，甚至支持在 macOS、iOS 和 Android 设备上进行语音交互，并提供实时的画布渲染功能供你操控。\n\n这款工具主要解决了用户对数据隐私、响应速度以及“始终在线”体验的需求。通过将 AI 部署在本地，用户无需依赖云端服务即可享受快速、私密的智能辅助，真正实现了“你的数据，你做主”。其独特的技术亮点在于强大的网关架构，将控制平面与核心助手分离，确保跨平台通信的流畅性与扩展性。\n\nOpenClaw 非常适合希望构建个性化工作流的技术爱好者、开发者，以及注重隐私保护且不愿被单一生态绑定的普通用户。只要具备基础的终端操作能力（支持 macOS、Linux 及 Windows WSL2），即可通过简单的命令行引导完成部署。如果你渴望拥有一个懂你",349277,3,"2026-04-06T06:32:30",[58,57,203,204],"图像","数据工具",{"id":206,"name":207,"github_repo":208,"description_zh":209,"stars":210,"difficulty_score":200,"last_commit_at":211,"category_tags":212,"status":60},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",[57,203,58],{"id":214,"name":215,"github_repo":216,"description_zh":217,"stars":218,"difficulty_score":59,"last_commit_at":219,"category_tags":220,"status":60},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",143909,"2026-04-07T11:33:18",[57,58,56],{"id":222,"name":223,"github_repo":224,"description_zh":225,"stars":226,"difficulty_score":59,"last_commit_at":227,"category_tags":228,"status":60},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。",107888,"2026-04-06T11:32:50",[57,203,58],{"id":230,"name":231,"github_repo":232,"description_zh":233,"stars":234,"difficulty_score":59,"last_commit_at":235,"category_tags":236,"status":60},4721,"markitdown","microsoft\u002Fmarkitdown","MarkItDown 是一款由微软 AutoGen 团队打造的轻量级 Python 工具，专为将各类文件高效转换为 Markdown 格式而设计。它支持 PDF、Word、Excel、PPT、图片（含 OCR）、音频（含语音转录）、HTML 乃至 YouTube 链接等多种格式的解析，能够精准提取文档中的标题、列表、表格和链接等关键结构信息。\n\n在人工智能应用日益普及的今天，大语言模型（LLM）虽擅长处理文本，却难以直接读取复杂的二进制办公文档。MarkItDown 恰好解决了这一痛点，它将非结构化或半结构化的文件转化为模型“原生理解”且 Token 效率极高的 Markdown 格式，成为连接本地文件与 AI 分析 pipeline 的理想桥梁。此外，它还提供了 MCP（模型上下文协议）服务器，可无缝集成到 Claude Desktop 等 LLM 应用中。\n\n这款工具特别适合开发者、数据科学家及 AI 研究人员使用，尤其是那些需要构建文档检索增强生成（RAG）系统、进行批量文本分析或希望让 AI 助手直接“阅读”本地文件的用户。虽然生成的内容也具备一定可读性，但其核心优势在于为机器",93400,"2026-04-06T19:52:38",[237,57],"插件",{"id":239,"name":240,"github_repo":241,"description_zh":242,"stars":243,"difficulty_score":200,"last_commit_at":244,"category_tags":245,"status":60},4487,"LLMs-from-scratch","rasbt\u002FLLMs-from-scratch","LLMs-from-scratch 是一个基于 PyTorch 的开源教育项目，旨在引导用户从零开始一步步构建一个类似 ChatGPT 的大型语言模型（LLM）。它不仅是同名技术著作的官方代码库，更提供了一套完整的实践方案，涵盖模型开发、预训练及微调的全过程。\n\n该项目主要解决了大模型领域“黑盒化”的学习痛点。许多开发者虽能调用现成模型，却难以深入理解其内部架构与训练机制。通过亲手编写每一行核心代码，用户能够透彻掌握 Transformer 架构、注意力机制等关键原理，从而真正理解大模型是如何“思考”的。此外，项目还包含了加载大型预训练权重进行微调的代码，帮助用户将理论知识延伸至实际应用。\n\nLLMs-from-scratch 特别适合希望深入底层原理的 AI 开发者、研究人员以及计算机专业的学生。对于不满足于仅使用 API，而是渴望探究模型构建细节的技术人员而言，这是极佳的学习资源。其独特的技术亮点在于“循序渐进”的教学设计：将复杂的系统工程拆解为清晰的步骤，配合详细的图表与示例，让构建一个虽小但功能完备的大模型变得触手可及。无论你是想夯实理论基础，还是为未来研发更大规模的模型做准备",90106,"2026-04-06T11:19:32",[56,203,58,57]]