[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"similar-rocketride-org--rocketride-server":3,"tool-rocketride-org--rocketride-server":61},[4,18,26,36,44,53],{"id":5,"name":6,"github_repo":7,"description_zh":8,"stars":9,"difficulty_score":10,"last_commit_at":11,"category_tags":12,"status":17},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",[13,14,15,16],"Agent","开发框架","图像","数据工具","ready",{"id":19,"name":20,"github_repo":21,"description_zh":22,"stars":23,"difficulty_score":10,"last_commit_at":24,"category_tags":25,"status":17},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",[14,15,13],{"id":27,"name":28,"github_repo":29,"description_zh":30,"stars":31,"difficulty_score":32,"last_commit_at":33,"category_tags":34,"status":17},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",148568,2,"2026-04-09T23:34:24",[14,13,35],"语言模型",{"id":37,"name":38,"github_repo":39,"description_zh":40,"stars":41,"difficulty_score":32,"last_commit_at":42,"category_tags":43,"status":17},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。",108111,"2026-04-08T11:23:26",[14,15,13],{"id":45,"name":46,"github_repo":47,"description_zh":48,"stars":49,"difficulty_score":32,"last_commit_at":50,"category_tags":51,"status":17},6121,"gemini-cli","google-gemini\u002Fgemini-cli","gemini-cli 是一款由谷歌推出的开源 AI 命令行工具，它将强大的 Gemini 大模型能力直接集成到用户的终端环境中。对于习惯在命令行工作的开发者而言，它提供了一条从输入提示词到获取模型响应的最短路径，无需切换窗口即可享受智能辅助。\n\n这款工具主要解决了开发过程中频繁上下文切换的痛点，让用户能在熟悉的终端界面内直接完成代码理解、生成、调试以及自动化运维任务。无论是查询大型代码库、根据草图生成应用，还是执行复杂的 Git 操作，gemini-cli 都能通过自然语言指令高效处理。\n\n它特别适合广大软件工程师、DevOps 人员及技术研究人员使用。其核心亮点包括支持高达 100 万 token 的超长上下文窗口，具备出色的逻辑推理能力；内置 Google 搜索、文件操作及 Shell 命令执行等实用工具；更独特的是，它支持 MCP（模型上下文协议），允许用户灵活扩展自定义集成，连接如图像生成等外部能力。此外，个人谷歌账号即可享受免费的额度支持，且项目基于 Apache 2.0 协议完全开源，是提升终端工作效率的理想助手。",100752,"2026-04-10T01:20:03",[52,13,15,14],"插件",{"id":54,"name":55,"github_repo":56,"description_zh":57,"stars":58,"difficulty_score":32,"last_commit_at":59,"category_tags":60,"status":17},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",[52,14],{"id":62,"github_repo":63,"name":64,"description_en":65,"description_zh":66,"ai_summary_zh":66,"readme_en":67,"readme_zh":68,"quickstart_zh":69,"use_case_zh":70,"hero_image_url":71,"owner_login":72,"owner_name":73,"owner_avatar_url":74,"owner_bio":75,"owner_company":76,"owner_location":76,"owner_email":76,"owner_twitter":76,"owner_website":77,"owner_url":78,"languages":79,"stars":120,"forks":121,"last_commit_at":122,"license":123,"difficulty_score":32,"env_os":124,"env_gpu":125,"env_ram":125,"env_deps":126,"category_tags":131,"github_topics":132,"view_count":32,"oss_zip_url":76,"oss_zip_packed_at":76,"status":17,"created_at":143,"updated_at":144,"faqs":145,"releases":174},6063,"rocketride-org\u002Frocketride-server","rocketride-server","High-performance AI pipeline engine with a C++ core and 50+ Python-extensible nodes. Build, debug, and scale LLM workflows with 13+ model providers, 8+ vector databases, and agent orchestration, all from your IDE. Includes VS Code extension, TypeScript\u002FPython SDKs, and Docker deployment.","RocketRide 是一款专为开发者打造的开源 AI 工作流引擎，旨在让你无需离开集成开发环境（IDE），即可轻松构建、调试并部署生产级的 AI 应用。它有效解决了传统 AI 开发中流程割裂、调试困难以及高性能部署复杂等痛点，将复杂的模型调用与数据处理串联成可视化的流水线。\n\n这款工具特别适合需要构建复杂大语言模型（LLM）应用、智能体编排或多模态搜索系统的软件工程师与算法研究人员。其核心亮点在于采用了 C++ 编写的高性能运行时引擎，确保了多线程执行下的高效与稳定，同时提供了超过 50 个可灵活扩展的 Python 节点。用户不仅能通过 VS Code 插件以可视化方式设计流程，还能利用 TypeScript 或 Python SDK 进行深度定制。RocketRide 原生支持 13 家主流大模型提供商和 8 种向量数据库，涵盖 OCR、实体识别等多种功能，所有工作流均定义为可移植的 JSON 文件，既方便版本管理，又能直接通过 Docker 部署到你自己的基础设施上，真正实现从代码到生产的一站式闭环。","\u003Cdiv align=\"center\">\n\n\u003Ca href=\"https:\u002F\u002Frocketride.org\">\n  \u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Frocketride-org_rocketride-server_readme_7ad3ae61e8ca.png\" alt=\"RocketRide\" width=\"100%\">\n\u003C\u002Fa>\n\n\u003Cp>\n  Open-source, developer-native AI pipeline tool.\u003Cbr\u002F>\n  Build, debug, and deploy production AI workflows - without leaving your IDE.\n\u003C\u002Fp>\n\n\u003Cp>\n\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Frocketride-org_rocketride-server_readme_1edad045b61c.png\" alt=\"C++\" \u002F>  \n\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Frocketride-org_rocketride-server_readme_7546c6f14134.png\" alt=\"Python\" \u002F>  \n\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Frocketride-org_rocketride-server_readme_c4ac40323ff7.png\" alt=\"TypeScript\" \u002F>\n\u003C\u002Fp>\n\n\u003Cp>\n RocketRide is an open-source data pipeline builder and runtime built for AI and ML workloads. With 50+ pipeline nodes spanning 13 LLM providers, 8 vector databases, OCR, NER, and more — pipelines are defined as portable JSON, built visually in VS Code, and executed by a multithreaded C++ runtime. From real-time data processing to multimodal AI search, RocketRide runs entirely on your own infrastructure.\n\u003C\u002Fp>\n\n\u003Cp>\n  \u003Ca href=\"https:\u002F\u002Frocketride.org\">Home\u003C\u002Fa> |\n  \u003Ca href=\"https:\u002F\u002Fdocs.rocketride.org\u002F\">Documentation\u003C\u002Fa> |\n  \u003Ca href=\"https:\u002F\u002Fpypi.org\u002Fproject\u002Frocketride\u002F\">Python SDK\u003C\u002Fa> |\n  \u003Ca href=\"https:\u002F\u002Fwww.npmjs.com\u002Fpackage\u002Frocketride\">TypeScript SDK\u003C\u002Fa> |\n  \u003Ca href=\"https:\u002F\u002Fpypi.org\u002Fproject\u002Frocketride-mcp\u002F\">MCP Server\u003C\u002Fa>\n\u003C\u002Fp>\n\n\u003Cp>\n  \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Frocketride-org\u002Frocketride-server\u002Factions\u002Fworkflows\u002Fci.yml\">\u003Cimg src=\"https:\u002F\u002Fgithub.com\u002Frocketride-org\u002Frocketride-server\u002Factions\u002Fworkflows\u002Fci.yml\u002Fbadge.svg\" alt=\"CI\">\u003C\u002Fa>\n  \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Frocketride-org\u002Frocketride-server\u002Freleases\u002Ftag\u002Fserver-v3.1.0\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FRuntime-v3.1.0-5f2167?logo=data:image\u002Fsvg%2bxml;base64,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\" alt=\"Engine v3.1.0\">\u003C\u002Fa>\n  \u003Ca href=\"https:\u002F\u002Fdiscord.gg\u002F9hr3tdZmEG\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FDiscord-Join-370b7a?logo=discord&logoColor=white\" alt=\"Discord\">\u003C\u002Fa>\n  \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Frocketride-org\u002Frocketride-server\u002Fblob\u002Fdevelop\u002FLICENSE\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FLicense-MIT-41b6e6\" alt=\"MIT License\">\u003C\u002Fa>\n\u003C\u002Fp>\n\n\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Frocketride-org_rocketride-server_readme_b4e3a8189f32.png\" alt=\"Build and run AI pipelines inside your IDE\" width=\"100%\">\n\n_Design, test, and ship complex AI workflows from a visual canvas, right where you write code._\n\n\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Frocketride-org_rocketride-server_readme_29aae08e277a.png\" alt=\"Integrate real AI solutions using a simple SDK\" width=\"100%\">\n\n_Drop pipelines into any Python or TypeScript app with a few lines of code, no infrastructure glue required._\n\n\u003C\u002Fdiv>\n\n## Features\n\n| Feature                           | Description                                                                                                                                                                                                                          |\n| :-------------------------------- | :----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |\n| **Visual Pipeline Builder**       | Drag, connect, and configure nodes in VS Code — no boilerplate. Real-time observability tracks token usage, LLM calls, latency, and execution. Pipelines are portable JSON — version-controllable, shareable, and runnable anywhere. |\n| **High-Performance C++ Runtime**  | Native multithreading purpose-built for the throughput demands of AI and data workloads. No bottlenecks, no compromises for production scale.                                                                                        |\n| **50+ Pipeline Nodes**            | 13 LLM providers, 8 vector databases, OCR, NER, PII anonymization, chunking strategies, embedding models, and more. All nodes are Python-extensible — build and publish your own.                                                    |\n| **Multi-Agent Workflows**         | Built-in CrewAI and LangChain support. Chain agents, share memory across pipeline runs, and manage multi-step reasoning at scale.                                                                                                    |\n| **Coding Agent Ready**            | RocketRide auto-detects your coding agent — Claude, Cursor, and more. Build, modify, and deploy pipelines through natural language.                                                                                                  |\n| **TypeScript, Python & MCP SDKs** | Integrate pipelines into native apps, expose them as callable tools for AI assistants, or build programmatic workflows into your existing codebase.                                                                                  |\n| **Zero Dependency Headaches**     | Python environments, C++ toolchains, Java\u002FTika, and all node dependencies managed automatically. Clone, build, run — no manual setup.                                                                                                |\n| **One-Click Deploy**              | Run on Docker, on-prem, or RocketRide Cloud (coming soon). Production-ready architecture from day one — not retrofitted from a demo.                                                                                                 |\n\n## Quick Start\n\n1. Install the extension for your IDE. Search for RocketRide in the extension marketplace:\n\n   \u003Cp align=\"center\">\n     \u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Frocketride-org_rocketride-server_readme_67d8573689f9.png\" alt=\"Install RocketRide extension\">\n   \u003C\u002Fp>\n\n   \u003Csub>[Not seeing your IDE? Open an issue](https:\u002F\u002Fgithub.com\u002Frocketride-org\u002Frocketride-server\u002Fissues\u002Fnew) · [Download directly](https:\u002F\u002Fopen-vsx.org\u002Fextension\u002FRocketRide\u002Frocketride)\u003C\u002Fsub>\n\n2. Click the RocketRide extension in your IDE\n\n3. Deploy a server - you'll be prompted on how you want to run the server. Choose the option that fits your setup:\n\n   - **Local (Recommended)** - This pulls the server directly into your IDE without any additional setup.\n   - **On-Premises** - Run the server on your own hardware for full control and data residency. Pull the image and deploy to Docker or clone this repo and [build from source](CONTRIBUTING.md#getting-started).\n\n## Building Your First Pipe\n\n1. All pipelines are recognized with the `*.pipe` format. Each pipeline and configuration is a JSON object - but the extension in your IDE will render within our visual builder canvas.\n\n2. All pipelines begin with source node: _webhook_, _chat_, or _dropper_. For specific usage, examples, and inspiration on how to build pipelines, check out our [guides and documentation](https:\u002F\u002Fdocs.rocketride.org\u002F).\n\n3. Connect input lanes and output lanes by type to properly wire your pipeline. Some nodes like agents or LLMs can be invoked as tools for use by a parent node as shown below:\n\n\u003Cp align=\"center\">\n  \u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Frocketride-org_rocketride-server_readme_87deec58ad36.gif\" alt=\"Pipeline canvas example\" width=\"100%\">\n\u003C\u002Fp>\n\n4. You can run a pipeline from the canvas by pressing the ▶ button on the source node or from the `Connection Manager` directly.\n\n5. Deploy your pipelines on your own infrastructure.\n\n   - **Docker** - Download the RocketRide server image and create a container. Requires [Docker](https:\u002F\u002Fdocs.docker.com\u002Fget-docker\u002F) to be installed.\n\n     ```bash\n     docker pull ghcr.io\u002Frocketride-org\u002Frocketride-engine:latest\n     docker create --name rocketride-engine -p 5565:5565 ghcr.io\u002Frocketride-org\u002Frocketride-engine:latest\n     ```\n\n   - **Local deployment** - Download the runtime of your choice as a standalone process in the 'Deploy' page of the `Connection Manager`\n\n6. Run your pipelines as standalone processes or integrate them into your existing [Python](https:\u002F\u002Fdocs.rocketride.org\u002Fsdk\u002Fpython-sdk) and [TypeScript\u002FJS](https:\u002F\u002Fdocs.rocketride.org\u002Fsdk\u002Fnode-sdk) applications utilizing our SDK.\n\n## Observability\n\nSelecting running pipelines allows for in-depth analytics. Trace call trees, token usage, memory consumption, and more to optimize your pipelines before scaling and deploying. Find the models, agents, and tools best fit for your task.\n\n\u003Cp align=\"center\">\n  \u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Frocketride-org_rocketride-server_readme_06aa353a923b.gif\" alt=\"Pipeline observability and tracing\">\n\u003C\u002Fp>\n\n## Contributors\n\nRocketRide is built by a growing community of contributors. Whether you've fixed a bug, added a node, improved docs, or helped someone on Discord, thank you. New contributions are always welcome - check out our [contributing guide](CONTRIBUTING.md) to get started.\n\n\u003Ca href=\"https:\u002F\u002Fgithub.com\u002Frocketride-org\u002Frocketride-server\u002Fgraphs\u002Fcontributors\">\n  \u003Cimg alt=\"contributors\" src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Frocketride-org_rocketride-server_readme_67ca3ea1ef56.png\" width=\"100%\" \u002F>\n\u003C\u002Fa>\n\n---\n\n\u003Cp align=\"center\">Made with ♥ in SF & EU\u003C\u002Fp>\n","\u003Cdiv align=\"center\">\n\n\u003Ca href=\"https:\u002F\u002Frocketride.org\">\n  \u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Frocketride-org_rocketride-server_readme_7ad3ae61e8ca.png\" alt=\"RocketRide\" width=\"100%\">\n\u003C\u002Fa>\n\n\u003Cp>\n  开源、开发者友好的AI流水线工具。\u003Cbr\u002F>\n  在不离开你的IDE的情况下，构建、调试并部署生产级AI工作流。\n\u003C\u002Fp>\n\n\u003Cp>\n\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Frocketride-org_rocketride-server_readme_1edad045b61c.png\" alt=\"C++\" \u002F>  \n\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Frocketride-org_rocketride-server_readme_7546c6f14134.png\" alt=\"Python\" \u002F>  \n\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Frocketride-org_rocketride-server_readme_c4ac40323ff7.png\" alt=\"TypeScript\" \u002F>\n\u003C\u002Fp>\n\n\u003Cp>\n  RocketRide是一款专为AI和ML工作负载打造的开源数据流水线构建工具及运行时。它拥有50多个流水线节点，覆盖13家大语言模型提供商、8家向量数据库、OCR、NER等功能——流水线以可移植的JSON格式定义，在VS Code中通过可视化界面构建，并由多线程C++运行时执行。无论是实时数据处理还是多模态AI搜索，RocketRide均可完全在您自己的基础设施上运行。\n\u003C\u002Fp>\n\n\u003Cp>\n  \u003Ca href=\"https:\u002F\u002Frocketride.org\">首页\u003C\u002Fa> |\n  \u003Ca href=\"https:\u002F\u002Fdocs.rocketride.org\u002F\">文档\u003C\u002Fa> |\n  \u003Ca href=\"https:\u002F\u002Fpypi.org\u002Fproject\u002Frocketride\u002F\">Python SDK\u003C\u002Fa> |\n  \u003Ca href=\"https:\u002F\u002Fwww.npmjs.com\u002Fpackage\u002Frocketride\">TypeScript SDK\u003C\u002Fa> |\n  \u003Ca href=\"https:\u002F\u002Fpypi.org\u002Fproject\u002Frocketride-mcp\u002F\">MCP服务器\u003C\u002Fa>\n\u003C\u002Fp>\n\n\u003Cp>\n  \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Frocketride-org\u002Frocketride-server\u002Factions\u002Fworkflows\u002Fci.yml\">\u003Cimg src=\"https:\u002F\u002Fgithub.com\u002Frocketride-org\u002Frocketride-server\u002Factions\u002Fworkflows\u002Fci.yml\u002Fbadge.svg\" alt=\"CI\">\u003C\u002Fa>\n  \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Frocketride-org\u002Frocketride-server\u002Freleases\u002Ftag\u002Fserver-v3.1.0\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FRuntime-v3.1.0-5f2167?logo=data:image\u002Fsvg%2bxml;base64,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......\u003Cdiv align=\"center\">\n\n\u003Ca href=\"https:\u002F\u002Frocketride.org\">\n  \u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Frocketride-org_rocketride-server_readme_7ad3ae61e8ca.png\" alt=\"RocketRide\" width=\"100%\">\n\u003C\u002Fa>\n\n\u003Cp>\n  开源、开发者友好的AI流水线工具。\u003Cbr\u002F>\n  在不离开你的IDE的情况下，构建、调试并部署生产级AI工作流。\n\u003C\u002Fp>\n\n\u003Cp>\n\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Frocketride-org_rocketride-server_readme_1edad045b61c.png\" alt=\"C++\" \u002F>  \n\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Frocketride-org_rocketride-server_readme_7546c6f14134.png\" alt=\"Python\" \u002F>  \n\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Frocketride-org_rocketride-server_readme_c4ac40323ff7.png\" alt=\"TypeScript\" \u002F>\n\u003C\u002Fp>\n\n\u003Cp>\n  RocketRide是一款专为AI和ML工作负载打造的开源数据流水线构建工具及运行时。它提供50多个流水线节点，覆盖13家大模型提供商、8个向量数据库、OCR、NER等功能——流水线以可移植的JSON格式定义，在VS Code中进行可视化构建，并由多线程C++运行时执行。无论是实时数据处理还是多模态AI搜索，RocketRide均可完全在您自己的基础设施上运行。\n\u003C\u002Fp>\n\n\u003Cp>\n  \u003Ca href=\"https:\u002F\u002Frocketride.org\">首页\u003C\u002Fa> |\n  \u003Ca href=\"https:\u002F\u002Fdocs.rocketride.org\u002F\">文档\u003C\u002Fa> |\n  \u003Ca href=\"https:\u002F\u002Fpypi.org\u002Fproject\u002Frocketride\u002F\">Python SDK\u003C\u002Fa> |\n  \u003Ca href=\"https:\u002F\u002Fwww.npmjs.com\u002Fpackage\u002Frocketride\">TypeScript SDK\u003C\u002Fa> |\n  \u003Ca href=\"https:\u002F\u002Fpypi.org\u002Fproject\u002Frocketride-mcp\u002F\">MCP服务器\u003C\u002Fa>\n\u003C\u002Fp>\n\n\u003Cp>\n  \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Frocketride-org\u002Frocketride-server\u002Factions\u002Fworkflows\u002Fci.yml\">\u003Cimg src=\"https:\u002F\u002Fgithub.com\u002Frocketride-org\u002Frocketride-server\u002Factions\u002Fworkflows\u002Fci.yml\u002Fbadge.svg\" alt=\"CI\">\u003C\u002Fa>\n  \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Frocketride-org\u002Frocketride-server\u002Freleases\u002Ftag\u002Fserver-v3.1.0\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FRuntime-v3.1.0-5f2167?logo=data:image\u002Fsvg%2bxml;base64,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.4SC.4SC.4SC.4SC.4SC.4SC.4SC.4SC.4SC.4SC.4SC.4SC.4SC.4SC.4SC.4SC.4SC.4SC.4SC.4SC.4SC.4SC.4SC.4SC.4SC.4SC.4SC.4SC.4SC.4SC.4SC.4SC.4SC.4SC.4SC.4SC.4SC.4SC.4SC.4SC.4SC.4SC.4SC.4SC.4SC.4SC.4SC.4SC.4SC.4SC.4SC.4SC.4SC.4SC.4SC.4SC.4SC.4SC.4SC.4SC.4SC.4SC.4SC.4SC.4SC.4SC.4SC.4SC.4SC.4SC.4SC.4SC.4SC.4SC.4SC.4SC.4SC.4SC.4SC.4SC......\n\n## 功能\n\n| 功能                           | 描述                                                                                                                                                                                                                          |\n| :-------------------------------- | :----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |\n| **可视化管道构建器**       | 在 VS Code 中拖拽、连接并配置节点——无需样板代码。实时可观测性可跟踪令牌使用量、LLM 调用、延迟和执行情况。管道是可移植的 JSON 格式——可版本控制、共享，并在任何地方运行。 |\n| **高性能 C++ 运行时**  | 原生多线程设计，专为 AI 和数据工作负载的吞吐量需求而打造。无瓶颈，无需在生产规模下做出妥协。                                                                                        |\n| **50 多种管道节点**            | 包括 13 家 LLM 提供商、8 种向量数据库、OCR、NER、PII 匿名化、分块策略、嵌入模型等。所有节点均可通过 Python 扩展——您可以构建并发布自己的节点。                                                    |\n| **多智能体工作流**         | 内置 CrewAI 和 LangChain 支持。串联智能体，在多个管道运行之间共享内存，并大规模管理多步推理。                                                                                                    |\n| **编码智能体就绪**            | RocketRide 可自动检测您的编码智能体——Claude、Cursor 等。通过自然语言构建、修改和部署管道。                                                                                                  |\n| **TypeScript、Python 和 MCP SDK** | 将管道集成到原生应用中，将其作为可调用工具暴露给 AI 助手，或在现有代码库中构建程序化工作流。                                                                                  |\n| **零依赖烦恼**     | 自动管理 Python 环境、C++ 工具链、Java\u002FTika 以及所有节点依赖项。克隆、构建、运行——无需手动设置。                                                                                                |\n| **一键部署**              | 可在 Docker、本地部署或 RocketRide Cloud（即将推出）上运行。从第一天起即具备生产就绪的架构——而非基于演示环境改造而来。                                                                                                 |\n\n## 快速入门\n\n1. 为您的 IDE 安装扩展。在扩展市场中搜索 RocketRide：\n\n   \u003Cp align=\"center\">\n     \u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Frocketride-org_rocketride-server_readme_67d8573689f9.png\" alt=\"安装 RocketRide 扩展\">\n   \u003C\u002Fp>\n\n   \u003Csub>[未找到您的 IDE？请提交问题](https:\u002F\u002Fgithub.com\u002Frocketride-org\u002Frocketride-server\u002Fissues\u002Fnew) · [直接下载](https:\u002F\u002Fopen-vsx.org\u002Fextension\u002FRocketRide\u002Frocketride)\u003C\u002Fsub>\n\n2. 在您的 IDE 中点击 RocketRide 扩展\n\n3. 部署服务器——系统会提示您希望如何运行服务器。选择适合您设置的选项：\n\n   - **本地（推荐）**——这会将服务器直接拉入您的 IDE，无需额外设置。\n   - **本地部署**——在您自己的硬件上运行服务器，以实现完全控制和数据驻留。拉取镜像并部署到 Docker，或克隆此仓库并按照 [贡献指南](CONTRIBUTING.md#getting-started) 从源码构建。\n\n## 构建您的第一个管道\n\n1. 所有管道都以 `*.pipe` 格式识别。每个管道和配置都是一个 JSON 对象——但您 IDE 中的扩展会在我们的可视化构建画布中呈现。\n\n2. 所有管道都从源节点开始：_webhook_、_chat_ 或 _dropper_。有关具体用法、示例和构建管道的灵感，请查看我们的 [指南和文档](https:\u002F\u002Fdocs.rocketride.org\u002F)。\n\n3. 按类型连接输入和输出通道，以正确地连接您的管道。某些节点，如智能体或 LLM，可以作为工具被父节点调用，如下所示：\n\n\u003Cp align=\"center\">\n  \u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Frocketride-org_rocketride-server_readme_87deec58ad36.gif\" alt=\"管道画布示例\" width=\"100%\">\n\u003C\u002Fp>\n\n4. 您可以通过按源节点上的 ▶ 按钮，或直接从“连接管理器”运行管道。\n\n5. 将您的管道部署到您自己的基础设施上。\n\n   - **Docker**——下载 RocketRide 服务器镜像并创建容器。需要先安装 [Docker](https:\u002F\u002Fdocs.docker.com\u002Fget-docker\u002F)。\n\n     ```bash\n     docker pull ghcr.io\u002Frocketride-org\u002Frocketride-engine:latest\n     docker create --name rocketride-engine -p 5565:5565 ghcr.io\u002Frocketride-org\u002Frocketride-engine:latest\n     ```\n\n   - **本地部署**——在“连接管理器”的“部署”页面中，将您选择的运行时作为独立进程下载。\n\n6. 将您的管道作为独立进程运行，或利用我们的 SDK 将其集成到您现有的 [Python](https:\u002F\u002Fdocs.rocketride.org\u002Fsdk\u002Fpython-sdk) 和 [TypeScript\u002FJS](https:\u002F\u002Fdocs.rocketride.org\u002Fsdk\u002Fnode-sdk) 应用程序中。\n\n## 可观测性\n\n选择正在运行的管道可进行深入分析。追踪调用树、令牌使用量、内存消耗等，以便在扩展和部署之前优化您的管道。找到最适合您任务的模型、智能体和工具。\n\n\u003Cp align=\"center\">\n  \u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Frocketride-org_rocketride-server_readme_06aa353a923b.gif\" alt=\"管道可观性和追踪\">\n\u003C\u002Fp>\n\n## 贡献者\n\nRocketRide 由不断壮大的贡献者社区构建而成。无论您是修复了错误、添加了节点、改进了文档，还是在 Discord 上帮助了他人，我们都感谢您的付出。我们始终欢迎新的贡献——请查看我们的 [贡献指南](CONTRIBUTING.md) 以开始参与。\n\n\u003Ca href=\"https:\u002F\u002Fgithub.com\u002Frocketride-org\u002Frocketride-server\u002Fgraphs\u002Fcontributors\">\n  \u003Cimg alt=\"贡献者\" src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Frocketride-org_rocketride-server_readme_67ca3ea1ef56.png\" width=\"100%\" \u002F>\n\u003C\u002Fa>\n\n---\n\n\u003Cp align=\"center\">用心制作于旧金山与欧洲\u003C\u002Fp>","# RocketRide Server 快速上手指南\n\nRocketRide 是一款开源的、开发者原生的 AI 流水线工具。它允许你在 IDE（如 VS Code）中可视化地构建、调试和部署生产级 AI 工作流，无需离开代码编辑器。其核心由高性能 C++ 运行时驱动，支持 50+ 种节点（涵盖 13 家大模型提供商、8 种向量数据库等）。\n\n## 环境准备\n\n在开始之前，请确保你的开发环境满足以下要求：\n\n*   **操作系统**: Windows, macOS, 或 Linux。\n*   **IDE**: 推荐安装 **Visual Studio Code (VS Code)**。\n*   **容器运行时 (可选但推荐)**: 若需通过 Docker 部署服务端，请安装 [Docker](https:\u002F\u002Fdocs.docker.com\u002Fget-docker\u002F)。\n*   **网络环境**: 确保能访问 GitHub 及对应的包仓库（如无法直接访问，建议配置代理或使用国内镜像源拉取 Docker 镜像）。\n\n## 安装步骤\n\n### 1. 安装 VS Code 扩展\n\nRocketRide 的核心体验集成在 VS Code 扩展中：\n\n1.  打开 VS Code，进入扩展市场（Extensions Marketplace）。\n2.  搜索 `RocketRide`。\n3.  点击 **Install** 安装插件。\n    *   *备选方案*: 如果市场加载缓慢，可访问 [Open VSX Registry](https:\u002F\u002Fopen-vsx.org\u002Fextension\u002FRocketRide\u002Frocketride) 下载 `.vsix` 文件手动安装。\n\n### 2. 启动服务\n\n安装完成后，在 VS Code 侧边栏点击 RocketRide 图标，根据提示选择服务器运行模式：\n\n*   **Local (推荐)**: 自动将服务器拉取到 IDE 本地运行，无需额外配置。\n*   **On-Premises (自托管)**: 适用于需要完全控制数据驻留的场景。你可以选择使用 Docker 部署或从源码构建。\n\n**使用 Docker 快速部署服务端：**\n\n```bash\n# 拉取最新镜像\ndocker pull ghcr.io\u002Frocketride-org\u002Frocketride-engine:latest\n\n# 创建并启动容器，映射端口 5565\ndocker create --name rocketride-engine -p 5565:5565 ghcr.io\u002Frocketride-org\u002Frocketride-engine:latest\ndocker start rocketride-engine\n```\n\n## 基本使用\n\n### 1. 创建第一个流水线 (Pipeline)\n\nRocketRide 的流水线文件以 `*.pipe` 为后缀，本质是 JSON 格式，但在 IDE 中会以可视化画布形式呈现。\n\n1.  在 VS Code 中新建一个文件，命名为 `my_first_flow.pipe`。\n2.  插件会自动识别并打开可视化编辑器。\n\n### 2. 构建工作流\n\n所有流水线必须以一个**源节点 (Source Node)** 开始：\n\n*   **Webhook**: 用于接收外部 HTTP 请求。\n*   **Chat**: 用于交互式对话场景。\n*   **Dropper**: 用于直接输入数据测试。\n\n**操作步骤：**\n1.  从左侧组件栏拖入一个源节点（例如 `Chat`）。\n2.  拖入处理节点（如 `LLM`、`Vector DB` 或 `Agent`）。\n3.  连接输入\u002F输出连线（Input\u002FOutput Lanes），确保数据类型匹配。\n4.  点击节点进行配置（如选择 LLM 提供商、填写 API Key、设置 Prompt 等）。\n\n> **提示**: 支持多智能体工作流，可直接调用 CrewAI 或 LangChain 节点，并共享内存上下文。\n\n### 3. 运行与调试\n\n*   **即时运行**: 在画布上点击源节点旁边的 **▶** 按钮，或在 `Connection Manager` 中触发运行。\n*   **可观测性**: 运行结束后，点击流水线查看详细的分析数据，包括调用树、Token 消耗、延迟及内存使用情况，以便优化性能。\n\n### 4. 集成到应用\n\n构建完成后，你可以通过 SDK 将流水线集成到现有的 Python 或 TypeScript 项目中：\n\n**Python 示例:**\n```python\nfrom rocketride import Client\n\nclient = Client(host=\"http:\u002F\u002Flocalhost:5565\")\nresponse = client.run_pipeline(\"my_first_flow\", input_data={\"message\": \"Hello RocketRide\"})\nprint(response)\n```\n\n**TypeScript 示例:**\n```typescript\nimport { Client } from 'rocketride';\n\nconst client = new Client({ host: 'http:\u002F\u002Flocalhost:5565' });\nconst response = await client.runPipeline('my_first_flow', { message: 'Hello RocketRide' });\nconsole.log(response);\n```\n\n现在，你已经成功在本地构建并运行了一个 AI 流水线。更多高级用法（如自定义节点、多模态搜索等）请参考官方文档。","某电商公司的 AI 团队正在构建一个实时多模态商品搜索系统，需要同时处理用户上传的图片（OCR 识别）、提取关键实体（NER），并调用大模型生成个性化推荐文案。\n\n### 没有 rocketride-server 时\n- **开发环境割裂**：工程师需要在本地 Python 脚本、云端 API 测试工具和 Docker 容器之间反复切换，无法在 IDE 中直观看到完整的数据流转逻辑。\n- **性能瓶颈难优化**：基于纯 Python 的串行工作流在处理高并发图片上传时延迟极高，且难以利用多线程优势，导致用户等待时间过长。\n- **集成与维护成本高**：对接不同的向量数据库和 13+ 个大模型提供商需要编写大量重复的适配代码，一旦某个服务接口变更，整个链路容易崩溃且调试困难。\n\n### 使用 rocketride-server 后\n- **IDE 内一站式构建**：团队直接在 VS Code 中通过可视化界面编排包含 OCR、NER 及大模型节点的复杂流水线，无需离开编辑器即可完成从设计到调试的全过程。\n- **C++ 核心加速执行**：依托 rocketride-server 的多线程 C++ 运行时引擎，原本串行的处理流程被并行化，显著降低了端到端延迟，轻松支撑高并发实时请求。\n- **灵活扩展与稳定部署**：利用其内置的 50+ 可扩展节点，快速切换不同的向量数据库或模型供应商，并通过统一的 JSON 定义实现跨环境的便携式部署，大幅降低了运维复杂度。\n\nrocketride-server 让开发者能在熟悉的 IDE 环境中，以原生般的流畅体验构建并部署高性能、可扩展的生产级 AI 工作流。","https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Frocketride-org_rocketride-server_b4e3a818.png","rocketride-org","rocketride.org","https:\u002F\u002Foss.gittoolsai.com\u002Favatars\u002Frocketride-org_a4aab348.png","",null,"https:\u002F\u002Frocketride.org\u002F","https:\u002F\u002Fgithub.com\u002Frocketride-org",[80,84,88,92,96,100,104,108,112,116],{"name":81,"color":82,"percentage":83},"C++","#f34b7d",47.7,{"name":85,"color":86,"percentage":87},"Python","#3572A5",29.4,{"name":89,"color":90,"percentage":91},"TypeScript","#3178c6",15,{"name":93,"color":94,"percentage":95},"JavaScript","#f1e05a",3.1,{"name":97,"color":98,"percentage":99},"C","#555555",1.5,{"name":101,"color":102,"percentage":103},"CSS","#663399",1.3,{"name":105,"color":106,"percentage":107},"Java","#b07219",1.1,{"name":109,"color":110,"percentage":111},"CMake","#DA3434",0.7,{"name":113,"color":114,"percentage":115},"Shell","#89e051",0.2,{"name":117,"color":118,"percentage":119},"HTML","#e34c26",0,1634,39,"2026-04-09T20:20:54","MIT","Linux, macOS, Windows","未说明",{"notes":127,"python":125,"dependencies":128},"该工具核心运行时为 C++，支持通过 Docker 一键部署或在本地直接运行。官方强调‘零依赖头痛’，自动管理 Python 环境、C++ 工具链及节点依赖（如 Java\u002FTika），无需手动配置。支持在 VS Code 中通过插件进行可视化管道构建和调试。可通过 Python 或 TypeScript SDK 集成到现有应用中。",[129,130],"Docker (可选，用于部署)","VS Code (推荐，用于可视化构建)",[13,15,16,52,14],[133,134,135,136,137,138,139,140,141,142],"ai","cpp","data-pipeline","data-processing","machine-learning","mcp","python","sdk","typescript","vscode-extension","2026-03-27T02:49:30.150509","2026-04-10T10:32:06.748088",[146,151,156,161,166,170],{"id":147,"question_zh":148,"answer_zh":149,"source_url":150},27459,"为什么 VS Code 扩展在 Cursor 中打开项目时会出现左下角通知闪烁且无法关闭的问题？","该问题通常是由于 .env 文件中缺少或配置了冲突的 API 密钥设置导致的。解决方法是打开项目文件夹中的 .env 文件，设置有效的 ROCKETRIDE_APIKEY（例如：ROCKETRIDE_APIKEY=MYAPIKEY）。设置后，闪烁的通知会停止并稳定显示完整信息。该问题已在后续的 PR #45 中修复，建议更新至最新版本。","https:\u002F\u002Fgithub.com\u002Frocketride-org\u002Frocketride-server\u002Fissues\u002F38",{"id":152,"question_zh":153,"answer_zh":154,"source_url":155},27460,"当 Agentic Workflow（如 PR Reviewer Suggestion 或 Docs Drift Detection）失败时，应该如何调试和修复？","有两种主要处理方式：\n1. **自动修复**：将该 Issue 指派给 Copilot，并使用 `agentic-workflows` 子代理自动调试和修复工作流失败。\n2. **手动调试**：使用 Agent CLI 加载提示文件进行调试。步骤如下：\n   - 启动你的 Agent。\n   - 从 `.github\u002Fagents\u002Fagentic-workflows.agent.md` 或在线地址加载 `agentic-workflows` 提示。\n   - 输入命令：`debug the agentic workflow \u003Cworkflow-name> failure in \u003Crun-url>`（例如：`debug the agentic workflow pr-reviewer-suggest failure in https:\u002F\u002Fgithub.com\u002Frocketride-org\u002Frocketride-server\u002Factions\u002Fruns\u002F22571370197`）。\n注意：如果看到“关闭 — agentic workflows disabled until API credits are restored”的评论，说明当前因 API 额度耗尽暂时禁用了自动工作流，需等待额度恢复。","https:\u002F\u002Fgithub.com\u002Frocketride-org\u002Frocketride-server\u002Fissues\u002F140",{"id":157,"question_zh":158,"answer_zh":159,"source_url":160},27461,"什么是 Agentic Workflows 中的 \"No-Op\"（无操作）状态？它代表失败吗？","\"No-Op\"（No Operation）不代表失败，而是表示工作流成功运行但判断无需执行任何操作。例如：安全扫描未发现漏洞、更新检查无需更新、或 PR 已经分配了审查者因此跳过建议步骤。这是一种成功的预期结果，旨在提供工作流行为的透明度。用户可以在专门的追踪 Issue（如 #116）中查看这些记录，以区分真正的故障和正常的无操作状态。","https:\u002F\u002Fgithub.com\u002Frocketride-org\u002Frocketride-server\u002Fissues\u002F116",{"id":162,"question_zh":163,"answer_zh":164,"source_url":165},27462,"在使用 text-question 节点时，为什么复杂的提示词会导致无法检索向量数据库中的文档？","这是一个已知问题：当在 `text-question` 节点的 Question 字段中输入包含严格约束（如“不要幻觉”、“只返回文档事实”）的复杂提示词时，LLM 可能会错误地声称无法访问向量数据库文档，而简单提示词则能正常工作。这影响了需要严格行为控制的流程（如文件调查器）。目前建议暂时使用较简单的提示词结构，或者将复杂的指令放在系统消息（System Message）或其他上游节点中处理，避免直接作为 Question 输入导致检索逻辑失效。","https:\u002F\u002Fgithub.com\u002Frocketride-org\u002Frocketride-server\u002Fissues\u002F31",{"id":167,"question_zh":168,"answer_zh":169,"source_url":165},27463,"text-question 节点的 Question 字段是否必须填写？能否留空以传递上游原始文本？","在当前版本中，Question 字段被标记为必填，导致节点无法在没有输入的情况下通过验证或保存。然而，用户期望能够留空该字段，以便节点直接将来源节点（如 Webhook 或 Dropper）的原始文本传递给 LLM 作为问题。这是一个待改进的功能点，目前的变通方法是填入一个占位符或简单的转发指令，直到官方移除该字段的强制校验限制。",{"id":171,"question_zh":172,"answer_zh":173,"source_url":160},27464,"PR Reviewer Suggestion 工作流在什么情况下会报告 \"No action needed\"？","当工作流检测到目标 Pull Request 已经分配了审查者时，会报告 \"No action needed\" 并跳过建议步骤。例如，如果 PR #126 已经分配了 kwit75 和 Rod-Christensen，或者 PR #125 已经分配了 Rod-Christensen，系统会判定无需额外操作。这属于正常的 \"No-Op\" 状态，表明自动化逻辑按预期工作，避免了重复分配。",[175,180,185,190,195,199,204,209,214,219,224,229,234,239,244,249,254,259,264,269],{"id":176,"version":177,"summary_zh":178,"released_at":179},180610,"server-v3.1.2-prerelease","从 `develop` 分支自动进行的夜间预发布。\n\n**服务器** v3.1.2","2026-04-08T04:54:11",{"id":181,"version":182,"summary_zh":183,"released_at":184},180611,"vscode-v1.0.6-prerelease","从 `develop` 分支自动构建的夜间预发布版本。\n\n**VS Code 扩展** v1.0.6","2026-04-08T04:53:55",{"id":186,"version":187,"summary_zh":188,"released_at":189},180612,"client-typescript-v1.0.6-prerelease","从 `develop` 分支自动进行的夜间预发布。\n\n**TypeScript 客户端** v1.0.6","2026-04-08T04:53:54",{"id":191,"version":192,"summary_zh":193,"released_at":194},180613,"client-python-v1.0.6-prerelease","`develop` 分支的夜间自动预发布。\n\n**Python 客户端** v1.0.6","2026-04-08T04:53:50",{"id":196,"version":197,"summary_zh":198,"released_at":194},180614,"client-mcp-v1.0.7-prerelease","`develop` 分支的夜间自动预发布。\n\n**MCP 客户端** v1.0.7",{"id":200,"version":201,"summary_zh":202,"released_at":203},180615,"client-mcp-v1.0.7","## 变更内容\n* chore: 将 rocketride-mcp 升级至 1.0.7，以修复 PyPI 横幅问题，由 @kwit75 在 https:\u002F\u002Fgithub.com\u002Frocketride-org\u002Frocketride-server\u002Fpull\u002F476 中完成\n* chore: 发布 MCP 1.0.7 版本，修复横幅问题，由 @kwit75 在 https:\u002F\u002Fgithub.com\u002Frocketride-org\u002Frocketride-server\u002Fpull\u002F477 中完成\n\n\n**完整变更日志**: https:\u002F\u002Fgithub.com\u002Frocketride-org\u002Frocketride-server\u002Fcompare\u002Fclient-mcp-v1.0.6...client-mcp-v1.0.7","2026-03-30T01:51:49",{"id":205,"version":206,"summary_zh":207,"released_at":208},180616,"client-python-v1.0.6","## 变更内容\n* 修复：将所有横幅 SVG 转换为 PNG，并为 npm\u002FPyPI\u002F市场提供绝对 URL，由 @kwit75 在 https:\u002F\u002Fgithub.com\u002Frocketride-org\u002Frocketride-server\u002Fpull\u002F472 中完成\n* 杂项：将 develop 分支合并到 main 分支，以发布横幅修复版本，由 @kwit75 在 https:\u002F\u002Fgithub.com\u002Frocketride-org\u002Frocketride-server\u002Fpull\u002F473 中完成\n* 杂项（版本）：为横幅修复版本升级至 1.0.6，由 @kwit75 在 https:\u002F\u002Fgithub.com\u002Frocketride-org\u002Frocketride-server\u002Fpull\u002F474 中完成\n* 杂项：发布 1.0.6 — 横幅修复版本，由 @kwit75 在 https:\u002F\u002Fgithub.com\u002Frocketride-org\u002Frocketride-server\u002Fpull\u002F475 中完成\n\n\n**完整变更日志**：https:\u002F\u002Fgithub.com\u002Frocketride-org\u002Frocketride-server\u002Fcompare\u002Fclient-python-v1.0.5...client-python-v1.0.6","2026-03-30T00:22:20",{"id":210,"version":211,"summary_zh":212,"released_at":213},180617,"client-mcp-v1.0.6","## 变更内容\n* 修复：将所有横幅 SVG 转换为 PNG，并为 npm\u002FPyPI\u002F市场提供绝对 URL，由 @kwit75 在 https:\u002F\u002Fgithub.com\u002Frocketride-org\u002Frocketride-server\u002Fpull\u002F472 中完成\n* 杂项：将 develop 分支合并到 main 分支，以发布横幅修复版本，由 @kwit75 在 https:\u002F\u002Fgithub.com\u002Frocketride-org\u002Frocketride-server\u002Fpull\u002F473 中完成\n* 杂项（版本）：为横幅修复版本升级至 1.0.6，由 @kwit75 在 https:\u002F\u002Fgithub.com\u002Frocketride-org\u002Frocketride-server\u002Fpull\u002F474 中完成\n* 杂项：发布 1.0.6 — 横幅修复版本，由 @kwit75 在 https:\u002F\u002Fgithub.com\u002Frocketride-org\u002Frocketride-server\u002Fpull\u002F475 中完成\n\n\n**完整变更日志**：https:\u002F\u002Fgithub.com\u002Frocketride-org\u002Frocketride-server\u002Fcompare\u002Fclient-python-v1.0.5...client-mcp-v1.0.6","2026-03-30T00:22:16",{"id":215,"version":216,"summary_zh":217,"released_at":218},180618,"client-typescript-v1.0.6","## 变更内容\n* 修复：将所有横幅 SVG 转换为 PNG，并为 npm\u002FPyPI\u002F市场提供绝对 URL，由 @kwit75 在 https:\u002F\u002Fgithub.com\u002Frocketride-org\u002Frocketride-server\u002Fpull\u002F472 中完成\n* 杂项：将 `develop` 分支合并到 `main` 分支，以发布横幅修复版本，由 @kwit75 在 https:\u002F\u002Fgithub.com\u002Frocketride-org\u002Frocketride-server\u002Fpull\u002F473 中完成\n* 杂项（版本）：为横幅修复版本升级至 1.0.6，由 @kwit75 在 https:\u002F\u002Fgithub.com\u002Frocketride-org\u002Frocketride-server\u002Fpull\u002F474 中完成\n* 杂项：发布 1.0.6 — 横幅修复版本，由 @kwit75 在 https:\u002F\u002Fgithub.com\u002Frocketride-org\u002Frocketride-server\u002Fpull\u002F475 中完成\n\n\n**完整变更日志**：https:\u002F\u002Fgithub.com\u002Frocketride-org\u002Frocketride-server\u002Fcompare\u002Fclient-python-v1.0.5...client-typescript-v1.0.6","2026-03-30T00:22:10",{"id":220,"version":221,"summary_zh":222,"released_at":223},180619,"client-python-v1.0.5","## 变更内容\n* 功能（node）：由 @ryan-t-christensen 在 https:\u002F\u002Fgithub.com\u002Frocketride-org\u002Frocketride-server\u002Fpull\u002F459 中为帧捕获节点和视觉节点添加文档通道。\n* 功能（trace）：由 @Rod-Christensen 在 https:\u002F\u002Fgithub.com\u002Frocketride-org\u002Frocketride-server\u002Fpull\u002F466 中为跟踪详情面板添加交互式 JSON 树查看器。\n* 杂项（versions）：由 @Rod-Christensen 在 https:\u002F\u002Fgithub.com\u002Frocketride-org\u002Frocketride-server\u002Fpull\u002F467 中提升补丁版本以准备发布。\n* 文档：由 @joshuadarron 在 https:\u002F\u002Fgithub.com\u002Frocketride-org\u002Frocketride-server\u002Fpull\u002F465 中重新设计根目录的 README，并统一各包的 README 样式（RR-405）。\n* 杂项（release）：由 @Rod-Christensen 在 https:\u002F\u002Fgithub.com\u002Frocketride-org\u002Frocketride-server\u002Fpull\u002F468 中将所有可发布的模块的新版本推送上线。\n* 修复（ci）：由 @kwit75 在 https:\u002F\u002Fgithub.com\u002Frocketride-org\u002Frocketride-server\u002Fpull\u002F469 中为发布和 Docker 任务添加权限。\n* 修复（vscode）：由 @kwit75 在 https:\u002F\u002Fgithub.com\u002Frocketride-org\u002Frocketride-server\u002Fpull\u002F471 中将横幅 SVG 转换为 PNG 格式，以便在市场中使用。\n* 杂项：由 @kwit75 在 https:\u002F\u002Fgithub.com\u002Frocketride-org\u002Frocketride-server\u002Fpull\u002F470 中将 develop 分支合并到 main 分支，以准备发布。\n\n\n**完整变更日志**：https:\u002F\u002Fgithub.com\u002Frocketride-org\u002Frocketride-server\u002Fcompare\u002Fclient-mcp-v1.0.5-prerelease...client-python-v1.0.5","2026-03-29T22:31:27",{"id":225,"version":226,"summary_zh":227,"released_at":228},180620,"client-typescript-v1.0.5","## What's Changed\n* feat(node): Add documents lane to frame grabber and vision nodes by @ryan-t-christensen in https:\u002F\u002Fgithub.com\u002Frocketride-org\u002Frocketride-server\u002Fpull\u002F459\n* feat(trace): interactive JSON tree viewer in trace detail panel by @Rod-Christensen in https:\u002F\u002Fgithub.com\u002Frocketride-org\u002Frocketride-server\u002Fpull\u002F466\n* chore(versions): bump patch versions for release by @Rod-Christensen in https:\u002F\u002Fgithub.com\u002Frocketride-org\u002Frocketride-server\u002Fpull\u002F467\n* docs: redesign root README and standardize package README styling (RR-405) by @joshuadarron in https:\u002F\u002Fgithub.com\u002Frocketride-org\u002Frocketride-server\u002Fpull\u002F465\n* chore(release): New release pushed out on all releasable modules  by @Rod-Christensen in https:\u002F\u002Fgithub.com\u002Frocketride-org\u002Frocketride-server\u002Fpull\u002F468\n* fix(ci): add permissions to release and docker jobs by @kwit75 in https:\u002F\u002Fgithub.com\u002Frocketride-org\u002Frocketride-server\u002Fpull\u002F469\n* fix(vscode): convert banner SVG to PNG for marketplace by @kwit75 in https:\u002F\u002Fgithub.com\u002Frocketride-org\u002Frocketride-server\u002Fpull\u002F471\n* chore: merge develop into main for release by @kwit75 in https:\u002F\u002Fgithub.com\u002Frocketride-org\u002Frocketride-server\u002Fpull\u002F470\n\n\n**Full Changelog**: https:\u002F\u002Fgithub.com\u002Frocketride-org\u002Frocketride-server\u002Fcompare\u002Fclient-mcp-v1.0.5-prerelease...client-typescript-v1.0.5","2026-03-29T22:31:21",{"id":230,"version":231,"summary_zh":232,"released_at":233},180621,"server-v3.1.2","## What's Changed\n* feat(node): Add documents lane to frame grabber and vision nodes by @ryan-t-christensen in https:\u002F\u002Fgithub.com\u002Frocketride-org\u002Frocketride-server\u002Fpull\u002F459\n* feat(trace): interactive JSON tree viewer in trace detail panel by @Rod-Christensen in https:\u002F\u002Fgithub.com\u002Frocketride-org\u002Frocketride-server\u002Fpull\u002F466\n* chore(versions): bump patch versions for release by @Rod-Christensen in https:\u002F\u002Fgithub.com\u002Frocketride-org\u002Frocketride-server\u002Fpull\u002F467\n* docs: redesign root README and standardize package README styling (RR-405) by @joshuadarron in https:\u002F\u002Fgithub.com\u002Frocketride-org\u002Frocketride-server\u002Fpull\u002F465\n* chore(release): New release pushed out on all releasable modules  by @Rod-Christensen in https:\u002F\u002Fgithub.com\u002Frocketride-org\u002Frocketride-server\u002Fpull\u002F468\n* fix(ci): add permissions to release and docker jobs by @kwit75 in https:\u002F\u002Fgithub.com\u002Frocketride-org\u002Frocketride-server\u002Fpull\u002F469\n* fix(vscode): convert banner SVG to PNG for marketplace by @kwit75 in https:\u002F\u002Fgithub.com\u002Frocketride-org\u002Frocketride-server\u002Fpull\u002F471\n* chore: merge develop into main for release by @kwit75 in https:\u002F\u002Fgithub.com\u002Frocketride-org\u002Frocketride-server\u002Fpull\u002F470\n\n\n**Full Changelog**: https:\u002F\u002Fgithub.com\u002Frocketride-org\u002Frocketride-server\u002Fcompare\u002Fclient-mcp-v1.0.5-prerelease...server-v3.1.2","2026-03-29T22:31:28",{"id":235,"version":236,"summary_zh":237,"released_at":238},180622,"vscode-v1.0.5","## What's Changed\n* fix(vscode): complete README packaging fix (from #323) by @kwit75 in https:\u002F\u002Fgithub.com\u002Frocketride-org\u002Frocketride-server\u002Fpull\u002F324\n* fix(vscode): add missing glob dependency for vsix packaging by @kwit75 in https:\u002F\u002Fgithub.com\u002Frocketride-org\u002Frocketride-server\u002Fpull\u002F330\n* fix(vscode): use @vscode\u002Fvsce for vsix packaging by @kwit75 in https:\u002F\u002Fgithub.com\u002Frocketride-org\u002Frocketride-server\u002Fpull\u002F449\n* fix(ci): remove main from scorecard push trigger by @kwit75 in https:\u002F\u002Fgithub.com\u002Frocketride-org\u002Frocketride-server\u002Fpull\u002F452\n* fix(vscode): restore marketplace extension name in vsix staging by @kwit75 in https:\u002F\u002Fgithub.com\u002Frocketride-org\u002Frocketride-server\u002Fpull\u002F458\n\n\n**Full Changelog**: https:\u002F\u002Fgithub.com\u002Frocketride-org\u002Frocketride-server\u002Fcompare\u002Fvscode-v1.0.3...vscode-v1.0.5","2026-03-27T22:01:46",{"id":240,"version":241,"summary_zh":242,"released_at":243},180623,"vscode-v1.0.3","## What's Changed\n* fix(vscode): include README.md in vsix package by @kwit75 in https:\u002F\u002Fgithub.com\u002Frocketride-org\u002Frocketride-server\u002Fpull\u002F322\n\n\n**Full Changelog**: https:\u002F\u002Fgithub.com\u002Frocketride-org\u002Frocketride-server\u002Fcompare\u002Fclient-mcp-v1.0.4...vscode-v1.0.3","2026-03-22T00:56:26",{"id":245,"version":246,"summary_zh":247,"released_at":248},180624,"vscode-v1.0.2","## What's Changed\n* chore: bump package versions for hackathon release by @kwit75 in https:\u002F\u002Fgithub.com\u002Frocketride-org\u002Frocketride-server\u002Fpull\u002F318\n\n\n**Full Changelog**: https:\u002F\u002Fgithub.com\u002Frocketride-org\u002Frocketride-server\u002Fcompare\u002Fclient-mcp-v1.0.3...vscode-v1.0.2","2026-03-21T23:37:46",{"id":250,"version":251,"summary_zh":252,"released_at":253},180625,"client-mcp-v1.0.4","## What's Changed\n* chore: bump package versions for hackathon release by @kwit75 in https:\u002F\u002Fgithub.com\u002Frocketride-org\u002Frocketride-server\u002Fpull\u002F318\n\n\n**Full Changelog**: https:\u002F\u002Fgithub.com\u002Frocketride-org\u002Frocketride-server\u002Fcompare\u002Fclient-mcp-v1.0.3...client-mcp-v1.0.4","2026-03-21T23:37:29",{"id":255,"version":256,"summary_zh":257,"released_at":258},180626,"client-python-v1.0.4","## What's Changed\n* chore: bump package versions for hackathon release by @kwit75 in https:\u002F\u002Fgithub.com\u002Frocketride-org\u002Frocketride-server\u002Fpull\u002F318\n\n\n**Full Changelog**: https:\u002F\u002Fgithub.com\u002Frocketride-org\u002Frocketride-server\u002Fcompare\u002Fclient-mcp-v1.0.3...client-python-v1.0.4","2026-03-21T23:37:28",{"id":260,"version":261,"summary_zh":262,"released_at":263},180627,"client-typescript-v1.0.4","## What's Changed\n* chore: bump package versions for hackathon release by @kwit75 in https:\u002F\u002Fgithub.com\u002Frocketride-org\u002Frocketride-server\u002Fpull\u002F318\n\n\n**Full Changelog**: https:\u002F\u002Fgithub.com\u002Frocketride-org\u002Frocketride-server\u002Fcompare\u002Fclient-mcp-v1.0.3...client-typescript-v1.0.4","2026-03-21T23:37:26",{"id":265,"version":266,"summary_zh":267,"released_at":268},180628,"vscode-v1.0.1","## What's Changed\n* docs: cherry-pick README updates for hackathon by @kwit75 in https:\u002F\u002Fgithub.com\u002Frocketride-org\u002Frocketride-server\u002Fpull\u002F303\n\n\n**Full Changelog**: https:\u002F\u002Fgithub.com\u002Frocketride-org\u002Frocketride-server\u002Fcompare\u002Fclient-typescript-v1.0.2...vscode-v1.0.1","2026-03-21T21:10:24",{"id":270,"version":271,"summary_zh":272,"released_at":273},180629,"client-mcp-v1.0.3","## What's Changed\n* docs: cherry-pick README updates for hackathon by @kwit75 in https:\u002F\u002Fgithub.com\u002Frocketride-org\u002Frocketride-server\u002Fpull\u002F303\n\n\n**Full Changelog**: https:\u002F\u002Fgithub.com\u002Frocketride-org\u002Frocketride-server\u002Fcompare\u002Fclient-typescript-v1.0.2...client-mcp-v1.0.3","2026-03-21T21:10:12"]