[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"similar-leon-ai--leon":3,"tool-leon-ai--leon":64},[4,17,27,35,43,56],{"id":5,"name":6,"github_repo":7,"description_zh":8,"stars":9,"difficulty_score":10,"last_commit_at":11,"category_tags":12,"status":16},3808,"stable-diffusion-webui","AUTOMATIC1111\u002Fstable-diffusion-webui","stable-diffusion-webui 是一个基于 Gradio 构建的网页版操作界面，旨在让用户能够轻松地在本地运行和使用强大的 Stable Diffusion 图像生成模型。它解决了原始模型依赖命令行、操作门槛高且功能分散的痛点，将复杂的 AI 绘图流程整合进一个直观易用的图形化平台。\n\n无论是希望快速上手的普通创作者、需要精细控制画面细节的设计师，还是想要深入探索模型潜力的开发者与研究人员，都能从中获益。其核心亮点在于极高的功能丰富度：不仅支持文生图、图生图、局部重绘（Inpainting）和外绘（Outpainting）等基础模式，还独创了注意力机制调整、提示词矩阵、负向提示词以及“高清修复”等高级功能。此外，它内置了 GFPGAN 和 CodeFormer 等人脸修复工具，支持多种神经网络放大算法，并允许用户通过插件系统无限扩展能力。即使是显存有限的设备，stable-diffusion-webui 也提供了相应的优化选项，让高质量的 AI 艺术创作变得触手可及。",162132,3,"2026-04-05T11:01:52",[13,14,15],"开发框架","图像","Agent","ready",{"id":18,"name":19,"github_repo":20,"description_zh":21,"stars":22,"difficulty_score":23,"last_commit_at":24,"category_tags":25,"status":16},1381,"everything-claude-code","affaan-m\u002Feverything-claude-code","everything-claude-code 是一套专为 AI 编程助手（如 Claude Code、Codex、Cursor 等）打造的高性能优化系统。它不仅仅是一组配置文件，而是一个经过长期实战打磨的完整框架，旨在解决 AI 代理在实际开发中面临的效率低下、记忆丢失、安全隐患及缺乏持续学习能力等核心痛点。\n\n通过引入技能模块化、直觉增强、记忆持久化机制以及内置的安全扫描功能，everything-claude-code 能显著提升 AI 在复杂任务中的表现，帮助开发者构建更稳定、更智能的生产级 AI 代理。其独特的“研究优先”开发理念和针对 Token 消耗的优化策略，使得模型响应更快、成本更低，同时有效防御潜在的攻击向量。\n\n这套工具特别适合软件开发者、AI 研究人员以及希望深度定制 AI 工作流的技术团队使用。无论您是在构建大型代码库，还是需要 AI 协助进行安全审计与自动化测试，everything-claude-code 都能提供强大的底层支持。作为一个曾荣获 Anthropic 黑客大奖的开源项目，它融合了多语言支持与丰富的实战钩子（hooks），让 AI 真正成长为懂上",138956,2,"2026-04-05T11:33:21",[13,15,26],"语言模型",{"id":28,"name":29,"github_repo":30,"description_zh":31,"stars":32,"difficulty_score":23,"last_commit_at":33,"category_tags":34,"status":16},2271,"ComfyUI","Comfy-Org\u002FComfyUI","ComfyUI 是一款功能强大且高度模块化的视觉 AI 引擎，专为设计和执行复杂的 Stable Diffusion 图像生成流程而打造。它摒弃了传统的代码编写模式，采用直观的节点式流程图界面，让用户通过连接不同的功能模块即可构建个性化的生成管线。\n\n这一设计巧妙解决了高级 AI 绘图工作流配置复杂、灵活性不足的痛点。用户无需具备编程背景，也能自由组合模型、调整参数并实时预览效果，轻松实现从基础文生图到多步骤高清修复等各类复杂任务。ComfyUI 拥有极佳的兼容性，不仅支持 Windows、macOS 和 Linux 全平台，还广泛适配 NVIDIA、AMD、Intel 及苹果 Silicon 等多种硬件架构，并率先支持 SDXL、Flux、SD3 等前沿模型。\n\n无论是希望深入探索算法潜力的研究人员和开发者，还是追求极致创作自由度的设计师与资深 AI 绘画爱好者，ComfyUI 都能提供强大的支持。其独特的模块化架构允许社区不断扩展新功能，使其成为当前最灵活、生态最丰富的开源扩散模型工具之一，帮助用户将创意高效转化为现实。",107662,"2026-04-03T11:11:01",[13,14,15],{"id":36,"name":37,"github_repo":38,"description_zh":39,"stars":40,"difficulty_score":23,"last_commit_at":41,"category_tags":42,"status":16},3704,"NextChat","ChatGPTNextWeb\u002FNextChat","NextChat 是一款轻量且极速的 AI 助手，旨在为用户提供流畅、跨平台的大模型交互体验。它完美解决了用户在多设备间切换时难以保持对话连续性，以及面对众多 AI 模型不知如何统一管理的痛点。无论是日常办公、学习辅助还是创意激发，NextChat 都能让用户随时随地通过网页、iOS、Android、Windows、MacOS 或 Linux 端无缝接入智能服务。\n\n这款工具非常适合普通用户、学生、职场人士以及需要私有化部署的企业团队使用。对于开发者而言，它也提供了便捷的自托管方案，支持一键部署到 Vercel 或 Zeabur 等平台。\n\nNextChat 的核心亮点在于其广泛的模型兼容性，原生支持 Claude、DeepSeek、GPT-4 及 Gemini Pro 等主流大模型，让用户在一个界面即可自由切换不同 AI 能力。此外，它还率先支持 MCP（Model Context Protocol）协议，增强了上下文处理能力。针对企业用户，NextChat 提供专业版解决方案，具备品牌定制、细粒度权限控制、内部知识库整合及安全审计等功能，满足公司对数据隐私和个性化管理的高标准要求。",87618,"2026-04-05T07:20:52",[13,26],{"id":44,"name":45,"github_repo":46,"description_zh":47,"stars":48,"difficulty_score":23,"last_commit_at":49,"category_tags":50,"status":16},2268,"ML-For-Beginners","microsoft\u002FML-For-Beginners","ML-For-Beginners 是由微软推出的一套系统化机器学习入门课程，旨在帮助零基础用户轻松掌握经典机器学习知识。这套课程将学习路径规划为 12 周，包含 26 节精炼课程和 52 道配套测验，内容涵盖从基础概念到实际应用的完整流程，有效解决了初学者面对庞大知识体系时无从下手、缺乏结构化指导的痛点。\n\n无论是希望转型的开发者、需要补充算法背景的研究人员，还是对人工智能充满好奇的普通爱好者，都能从中受益。课程不仅提供了清晰的理论讲解，还强调动手实践，让用户在循序渐进中建立扎实的技能基础。其独特的亮点在于强大的多语言支持，通过自动化机制提供了包括简体中文在内的 50 多种语言版本，极大地降低了全球不同背景用户的学习门槛。此外，项目采用开源协作模式，社区活跃且内容持续更新，确保学习者能获取前沿且准确的技术资讯。如果你正寻找一条清晰、友好且专业的机器学习入门之路，ML-For-Beginners 将是理想的起点。",84991,"2026-04-05T10:45:23",[14,51,52,53,15,54,26,13,55],"数据工具","视频","插件","其他","音频",{"id":57,"name":58,"github_repo":59,"description_zh":60,"stars":61,"difficulty_score":10,"last_commit_at":62,"category_tags":63,"status":16},3128,"ragflow","infiniflow\u002Fragflow","RAGFlow 是一款领先的开源检索增强生成（RAG）引擎，旨在为大语言模型构建更精准、可靠的上下文层。它巧妙地将前沿的 RAG 技术与智能体（Agent）能力相结合，不仅支持从各类文档中高效提取知识，还能让模型基于这些知识进行逻辑推理和任务执行。\n\n在大模型应用中，幻觉问题和知识滞后是常见痛点。RAGFlow 通过深度解析复杂文档结构（如表格、图表及混合排版），显著提升了信息检索的准确度，从而有效减少模型“胡编乱造”的现象，确保回答既有据可依又具备时效性。其内置的智能体机制更进一步，使系统不仅能回答问题，还能自主规划步骤解决复杂问题。\n\n这款工具特别适合开发者、企业技术团队以及 AI 研究人员使用。无论是希望快速搭建私有知识库问答系统，还是致力于探索大模型在垂直领域落地的创新者，都能从中受益。RAGFlow 提供了可视化的工作流编排界面和灵活的 API 接口，既降低了非算法背景用户的上手门槛，也满足了专业开发者对系统深度定制的需求。作为基于 Apache 2.0 协议开源的项目，它正成为连接通用大模型与行业专有知识之间的重要桥梁。",77062,"2026-04-04T04:44:48",[15,14,13,26,54],{"id":65,"github_repo":66,"name":67,"description_en":68,"description_zh":69,"ai_summary_zh":69,"readme_en":70,"readme_zh":71,"quickstart_zh":72,"use_case_zh":73,"hero_image_url":74,"owner_login":75,"owner_name":76,"owner_avatar_url":77,"owner_bio":78,"owner_company":79,"owner_location":79,"owner_email":80,"owner_twitter":81,"owner_website":82,"owner_url":83,"languages":84,"stars":113,"forks":114,"last_commit_at":115,"license":116,"difficulty_score":23,"env_os":117,"env_gpu":118,"env_ram":118,"env_deps":119,"category_tags":124,"github_topics":125,"view_count":145,"oss_zip_url":79,"oss_zip_packed_at":79,"status":16,"created_at":146,"updated_at":147,"faqs":148,"releases":178},703,"leon-ai\u002Fleon","leon","🧠 Leon is your open-source personal assistant.","Leon 是一款开源的个人 AI 助手，旨在成为你数字生活中的智能伙伴。与传统仅能回复文本的语音助手不同，Leon 专注于解决“听懂指令但无法落地”的问题。它通过工具调用、上下文感知和记忆机制，真正实现从简单指令到复杂任务的全流程自动化执行。\n\nLeon 特别适合注重数据隐私的开发者、技术极客以及希望将 AI 能力集成到本地环境的用户。其独特之处在于支持完全本地运行，平衡了隐私控制与 AI 能力。系统内置分层记忆，能持久保存偏好并理解当前环境状态。在操作模式上，Leon 提供智能、工作流和智能体三种选择，让它在处理日常任务时既灵活又可靠。目前项目正处于 2.0 版本迭代中，持续优化核心架构，为社区提供了探索未来智能体应用的机会。","\u003Cp align=\"center\">\n  \u003Ca href=\"https:\u002F\u002Fgetleon.ai\">\u003Cimg width=\"800\" src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fleon-ai_leon_readme_f03e200e8389.gif\" \u002F>\u003C\u002Fa>\n\u003C\u002Fp>\n\n\u003Ch1 align=\"center\">\n  \u003Ca href=\"https:\u002F\u002Fgetleon.ai\">\u003Cimg width=\"96\" src=\"https:\u002F\u002Fgetleon.ai\u002Fimg\u002Flogo.svg\" alt=\"Leon\">\u003C\u002Fa>\u003Cbr>\n  Leon\n\u003C\u002Fh1>\n\n_\u003Cp align=\"center\">Your open-source personal AI assistant.\u003C\u002Fp>_\n\n\u003Cp align=\"center\">\n  \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fleon-ai\u002Fleon\u002Fblob\u002Fdevelop\u002FLICENSE.md\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Flicense-MIT-blue.svg?label=License&style=flat\" \u002F>\u003C\u002Fa>\n  \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fleon-ai\u002Fleon\u002Fblob\u002Fdevelop\u002F.github\u002FCONTRIBUTING.md\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FPRs-welcome-brightgreen.svg?style=flat\" \u002F>\u003C\u002Fa>\n  \u003Cbr>\n  \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fleon-ai\u002Fleon\u002Factions\u002Fworkflows\u002Fbuild.yml\">\u003Cimg src=\"https:\u002F\u002Fgithub.com\u002Fleon-ai\u002Fleon\u002Factions\u002Fworkflows\u002Fbuild.yml\u002Fbadge.svg?branch=develop\" \u002F>\u003C\u002Fa>\n  \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fleon-ai\u002Fleon\u002Factions\u002Fworkflows\u002Ftests.yml\">\u003Cimg src=\"https:\u002F\u002Fgithub.com\u002Fleon-ai\u002Fleon\u002Factions\u002Fworkflows\u002Ftests.yml\u002Fbadge.svg?branch=develop\" \u002F>\u003C\u002Fa>\n  \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fleon-ai\u002Fleon\u002Factions\u002Fworkflows\u002Flint.yml\">\u003Cimg src=\"https:\u002F\u002Fgithub.com\u002Fleon-ai\u002Fleon\u002Factions\u002Fworkflows\u002Flint.yml\u002Fbadge.svg?branch=develop\" \u002F>\u003C\u002Fa>\n  \u003Cbr>\n  \u003Ca href=\"https:\u002F\u002Fdiscord.gg\u002FMNQqqKg\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FDiscord-%235865F2.svg?style=for-the-badge&logo=discord&logoColor=white\" \u002F>\u003C\u002Fa>\n\u003C\u002Fp>\n\n\u003Cp align=\"center\">\n  Follow development updates on \u003Ca href=\"https:\u002F\u002Fx.com\u002Fgrenlouis\">\u003Cstrong>X \u002F @grenlouis\u003C\u002Fstrong>\u003C\u002Fa>\n\u003C\u002Fp>\n\n\u003Cp align=\"center\">\n  \u003Ca href=\"https:\u002F\u002Fgetleon.ai\">Website\u003C\u002Fa> ::\n  \u003Ca href=\"https:\u002F\u002Fdocs.getleon.ai\">Legacy Docs\u003C\u002Fa> ::\n  \u003Ca href=\"http:\u002F\u002Froadmap.getleon.ai\">Roadmap\u003C\u002Fa> ::\n  \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fleon-ai\u002Fleon\u002Fblob\u002Fdevelop\u002F.github\u002FCONTRIBUTING.md\">Contributing\u003C\u002Fa> ::\n  \u003Ca href=\"https:\u002F\u002Fblog.getleon.ai\u002Fthe-story-behind-leon\u002F\">Story\u003C\u002Fa>\n\u003C\u002Fp>\n\n---\n\n## ⚠️ Important Notice (as of 2026-03-29)\n\n> [!IMPORTANT]\n> Leon is currently focused on the **2.0 Developer Preview** on the `develop` branch.\n>\n> - The new documentation is **not ready yet**.\n> - The current docs site and older guides mostly reflect the legacy architecture.\n> - If you want the legacy, more stable pre-agentic version of Leon, use the `master` branch.\n> - If you want to explore or contribute to Leon's new core, `develop` is the right place.\n\nThe most accurate high-level references for Leon's current state are:\n\n- [`core\u002Fcontext\u002FLEON.md`](.\u002Fcore\u002Fcontext\u002FLEON.md)\n- [`core\u002Fcontext\u002FARCHITECTURE.md`](.\u002Fcore\u002Fcontext\u002FARCHITECTURE.md)\n\n## 👋 Introduction\n\n**Leon** is **your open-source personal AI assistant** built around **tools, context, memory, and agentic execution**.\n\nLeon is designed to stay practical, privacy-aware, and grounded in your real environment. It can operate locally, use dedicated tools instead of relying on free-form guessing, and complete tasks from start to finish across deterministic workflows and agent-style execution.\n\n## 🧠 What Leon Is Today\n\nLeon is no longer just a classic intent-classification assistant like it was for its first release in 2019.\n\nToday, Leon is being built as a more capable assistant that can understand a goal, choose how to handle it, use tools, remember useful information, and recover when something goes wrong.\n\n- Leon can run in different ways depending on the task: `smart` mode chooses for you, `workflow` mode follows a fixed path, and `agent` mode can plan step by step.\n- Leon can use real tools to get work done instead of only replying with plain text.\n- Leon can use context about your environment so answers stay grounded in what is actually happening on your machine and setup.\n- Leon keeps layered memory so it can remember durable preferences, day-to-day context, and recent discussion context.\n- Leon supports both local and remote AI providers, which helps balance privacy, control, and capability.\n- Under the hood, the core is organized as `Skills -> Actions -> Tools -> Functions (-> Binaries)`.\n\nLeon also keeps a compact self-model and a bounded proactive pulse system so it can stay more consistent over time without flooding itself with unnecessary context.\n\n## Why?\n\n- **Privacy matters**: Leon can work with local models and local context instead of forcing everything through third-party services.\n- **Grounded behavior matters**: Leon prefers explicit tools, context, and memory over vague model-only responses.\n- **Extensibility matters**: skills, toolkits, bridges, and binaries make it possible to keep Leon modular.\n- **Open source matters**: anyone can inspect the architecture, build on top of it, and help shape where it goes next.\n\n## 🚀 Getting Started\n\n### Prerequisites\n\n- [Node.js](https:\u002F\u002Fnodejs.org\u002F) >= 24.0.0\n- Supported OSes: Linux, macOS, and Windows\n\nRecommended: manage Node.js with [Volta](https:\u002F\u002Fvolta.sh\u002F).\n\n### Installation\n\n```sh\n# Clone the repository\ngit clone https:\u002F\u002Fgithub.com\u002Fleon-ai\u002Fleon.git\n\n# Go to the project root\ncd leon\n\n# Install pnpm\nnpm install --global pnpm@latest\n\n# Install dependencies\npnpm install\n```\n\n### Run Leon\n\n```sh\n# Run Leon\npnpm start\n```\n\n### Check Your Setup\n\n```sh\n# Check the setup went well\npnpm run check\n```\n\nBy default, Leon runs locally and the app is available on `http:\u002F\u002Flocalhost:1337`.\n\n## 🏗️ Architecture Snapshot\n\nAt a high level, Leon currently consists of:\n\n- `server\u002F`: the main runtime, routing, memory, context management, HTTP API, and agent\u002Fworkflow execution\n- `app\u002F`: the web application\n- `aurora\u002F`: UI components and preview environment\n- `skills\u002F`: user-facing capabilities built on top of the core\n- `bridges\u002F`: Node.js and Python bridges plus toolkit definitions and tool runtimes\n- `tcp_server\u002F`: Python services used by parts of the runtime stack\n- `core\u002Fcontext\u002F`: generated identity and architecture context documents that describe Leon's current behavior\n\nThis repository already includes skills and toolkits for areas such as search, productivity, system utilities, media workflows, coding assistance, memory-backed interactions, and voice\u002Faudio features.\n\n## 📚 Documentation Status\n\nThe new docs for Leon 2.0 are not ready yet.\n\nFor now:\n\n- treat this repository as the source of truth for the **2.0 Developer Preview**\n- use [`core\u002Fcontext\u002FLEON.md`](.\u002Fcore\u002Fcontext\u002FLEON.md) for Leon's current identity and behavior\n- use [`core\u002Fcontext\u002FARCHITECTURE.md`](.\u002Fcore\u002Fcontext\u002FARCHITECTURE.md) for the current architecture overview\n- expect the public docs site to lag behind the new core until the updated documentation is published\n\n## ❤️ Contributing\n\nWe are starting to progressively onboard contributors for the **2.0 Developer Preview**.\n\nIf you want to follow the project or express interest in joining that onboarding:\n\n- [2.0 Developer Preview contributor form](https:\u002F\u002Fforms.gle\u002F6PCG2D5rYo1q8tKMA)\n- [Roadmap](http:\u002F\u002Froadmap.getleon.ai)\n- [Discord](https:\u002F\u002Fdiscord.gg\u002FMNQqqKg)\n- [GitHub issues](https:\u002F\u002Fgithub.com\u002Fleon-ai\u002Fleon\u002Fissues)\n\n### Why is there a small amount of contributors?\n\nLeon has been evolving for a long time, but the current 2.0 work is a major transition period.\n\nFor a long time, Leon was a smaller assistant project with a simpler architecture. Today, the core is being rebuilt into a much more capable system around tools, memory, context, and agent-style execution. That means a lot of things are still moving, and it makes contribution harder than it will be once the new docs and architecture settle down.\n\nAnother important reason is simply time: Leon is still developed largely during spare time. So progress can be uneven, and opening the project more broadly has to be balanced with keeping the direction coherent while the 2.0 Developer Preview is still taking shape.\n\n## 📖 The Story Behind Leon\n\nLeon started in 2017 and has been active since 2019. If you want the longer backstory, read [the story behind Leon](https:\u002F\u002Fblog.getleon.ai\u002Fthe-story-behind-leon\u002F).\n\n## 🔔 Stay Tuned\n\n- [X \u002F Twitter](https:\u002F\u002Fx.com\u002Fgrenlouis)\n- [Newsletter](https:\u002F\u002Fleonai.substack.com\u002Fsubscribe)\n- [Blog](https:\u002F\u002Fblog.getleon.ai)\n- [YouTube](https:\u002F\u002Fwww.youtube.com\u002Fchannel\u002FUCW6mk6j6nQUzFYY97r47emQ)\n\n## 👨 Author\n\n**Louis Grenard** ([@grenlouis](https:\u002F\u002Fx.com\u002Fgrenlouis))\n\n## 👍 Sponsors\n\n\u003Ctable>\n  \u003Ctbody>\n    \u003Ctr>\n      \u003Ctd align=\"center\" valign=\"middle\" width=\"128\">\n        \u003Ca href=\"https:\u002F\u002Fgithub.com\u002FAppwrite\">\n          \u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fleon-ai_leon_readme_6394531b5a9b.png\" \u002F>\n          Appwrite\n        \u003C\u002Fa>\u003Cbr>\n        \u003Csub>\u003Csup>250 USD \u002F month\u003C\u002Fsup>\u003C\u002Fsub>\n      \u003C\u002Ftd>\n      \u003Ctd align=\"center\" valign=\"middle\" width=\"128\">\n        \u003Cimg src=\"https:\u002F\u002Fgetleon.ai\u002Fimg\u002Fanonymous.svg\" width=\"128\" \u002F>\n        Anonymous\n        \u003Cbr>\n        \u003Csub>\u003Csup>100 USD \u002F month\u003C\u002Fsup>\u003C\u002Fsub>\n      \u003C\u002Ftd>\n      \u003Ctd align=\"center\" valign=\"middle\" width=\"128\">\n        \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fherbundkraut\">\n          \u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fleon-ai_leon_readme_4f53a68786e4.png\" \u002F>\n          herbundkraut\n        \u003C\u002Fa>\u003Cbr>\n        \u003Csub>\u003Csup>10 USD \u002F month\u003C\u002Fsup>\u003C\u002Fsub>\n      \u003C\u002Ftd>\n      \u003Ctd align=\"center\" valign=\"middle\" width=\"128\">\n        \u003Ca href=\"http:\u002F\u002Fsponsor.getleon.ai\u002F\">\n          You?\n        \u003C\u002Fa>\n      \u003C\u002Ftd>\n    \u003C\u002Ftr>\n  \u003C\u002Ftbody>\n\u003C\u002Ftable>\n\nYou can also contribute by [sponsoring Leon](http:\u002F\u002Fsponsor.getleon.ai).\n","\u003Cp align=\"center\">\n  \u003Ca href=\"https:\u002F\u002Fgetleon.ai\">\u003Cimg width=\"800\" src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fleon-ai_leon_readme_f03e200e8389.gif\" \u002F>\u003C\u002Fa>\n\u003C\u002Fp>\n\n\u003Ch1 align=\"center\">\n  \u003Ca href=\"https:\u002F\u002Fgetleon.ai\">\u003Cimg width=\"96\" src=\"https:\u002F\u002Fgetleon.ai\u002Fimg\u002Flogo.svg\" alt=\"Leon\">\u003C\u002Fa>\u003Cbr>\n  Leon\n\u003C\u002Fh1>\n\n_\u003Cp align=\"center\">你的开源个人 AI 助手。\u003C\u002Fp>_\n\n\u003Cp align=\"center\">\n  \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fleon-ai\u002Fleon\u002Fblob\u002Fdevelop\u002FLICENSE.md\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Flicense-MIT-blue.svg?label=许可证&style=flat\" \u002F>\u003C\u002Fa>\n  \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fleon-ai\u002Fleon\u002Fblob\u002Fdevelop\u002F.github\u002FCONTRIBUTING.md\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FPRs-欢迎-brightgreen.svg?style=flat\" \u002F>\u003C\u002Fa>\n  \u003Cbr>\n  \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fleon-ai\u002Fleon\u002Factions\u002Fworkflows\u002Fbuild.yml\">\u003Cimg src=\"https:\u002F\u002Fgithub.com\u002Fleon-ai\u002Fleon\u002Factions\u002Fworkflows\u002Fbuild.yml\u002Fbadge.svg?branch=develop\" \u002F>\u003C\u002Fa>\n  \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fleon-ai\u002Fleon\u002Factions\u002Fworkflows\u002Ftests.yml\">\u003Cimg src=\"https:\u002F\u002Fgithub.com\u002Fleon-ai\u002Fleon\u002Factions\u002Fworkflows\u002Ftests.yml\u002Fbadge.svg?branch=develop\" \u002F>\u003C\u002Fa>\n  \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fleon-ai\u002Fleon\u002Factions\u002Fworkflows\u002Flint.yml\">\u003Cimg src=\"https:\u002F\u002Fgithub.com\u002Fleon-ai\u002Fleon\u002Factions\u002Fworkflows\u002Flint.yml\u002Fbadge.svg?branch=develop\" \u002F>\u003C\u002Fa>\n  \u003Cbr>\n  \u003Ca href=\"https:\u002F\u002Fdiscord.gg\u002FMNQqqKg\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FDiscord-%235865F2.svg?style=for-the-badge&logo=discord&logoColor=white\" \u002F>\u003C\u002Fa>\n\u003C\u002Fp>\n\n\u003Cp align=\"center\">\n  在 \u003Ca href=\"https:\u002F\u002Fx.com\u002Fgrenlouis\">\u003Cstrong>X \u002F @grenlouis\u003C\u002Fstrong>\u003C\u002Fa> 上关注开发动态\n\u003C\u002Fp>\n\n\u003Cp align=\"center\">\n  \u003Ca href=\"https:\u002F\u002Fgetleon.ai\">官网\u003C\u002Fa> ::\n  \u003Ca href=\"https:\u002F\u002Fdocs.getleon.ai\">旧版文档\u003C\u002Fa> ::\n  \u003Ca href=\"http:\u002F\u002Froadmap.getleon.ai\">路线图\u003C\u002Fa> ::\n  \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fleon-ai\u002Fleon\u002Fblob\u002Fdevelop\u002F.github\u002FCONTRIBUTING.md\">贡献指南\u003C\u002Fa> ::\n  \u003Ca href=\"https:\u002F\u002Fblog.getleon.ai\u002Fthe-story-behind-leon\u002F\">项目故事\u003C\u002Fa>\n\u003C\u002Fp>\n\n---\n\n## ⚠️ 重要通知（截至 2026-03-29）\n\n> [!IMPORTANT]\n> Leon 目前专注于 `develop` 分支上的 **2.0 开发者预览版 (2.0 Developer Preview)**。\n>\n> - 新文档 **尚未准备好**。\n> - 当前文档站点和旧指南主要反映的是**遗留架构 (legacy architecture)**。\n> - 如果你想要更稳定、非代理式的旧版 Leon，请使用 `master` 分支。\n> - 如果你想探索或为 Leon 的新核心做出贡献，`develop` 是正确的选择。\n\n关于 Leon 当前状态最准确的高级参考是：\n\n- [`core\u002Fcontext\u002FLEON.md`](.\u002Fcore\u002Fcontext\u002FLEON.md)\n- [`core\u002Fcontext\u002FARCHITECTURE.md`](.\u002Fcore\u002Fcontext\u002FARCHITECTURE.md)\n\n## 👋 简介\n\n**Leon** 是 **你的开源个人 AI 助手 (AI Assistant)**，围绕**工具 (Tools)、上下文 (Context)、记忆 (Memory) 和代理式执行 (Agentic Execution)** 构建。\n\nLeon 旨在保持实用、注重隐私感知 (Privacy-aware)，并扎根于你的真实环境。它可以在本地运行，使用专用工具而不是依赖自由形式的猜测，并在确定性工作流 (Deterministic Workflows) 和代理式执行中从头到尾完成任务。\n\n## 🧠 Leon 的现状\n\nLeon 不再仅仅像 2019 年首次发布时那样是一个经典的意图分类 (Intent-Classification) 助手。\n\n如今，Leon 正在被构建为一个更有能力的助手，它能够理解目标、选择处理方式、使用工具、记住有用信息，并在出现问题时进行恢复。\n\n- Leon 可以根据任务以不同方式运行：`smart` 模式为你选择，`workflow` 模式遵循固定路径，而 `agent` 模式可以逐步规划。\n- Leon 可以使用真实工具来完成任务，而不仅仅是回复纯文本。\n- Leon 可以利用关于你环境的上下文信息，使答案扎根于你的机器和设置上实际发生的事情。\n- Leon 保持分层记忆，以便它可以记住持久偏好、日常上下文和最近的讨论上下文。\n- Leon 支持本地和远程 AI 提供商，这有助于平衡隐私、控制和能力。\n- 在底层，核心组织为 `Skills -> Actions -> Tools -> Functions (-> Binaries)`。\n\nLeon 还保持紧凑的自我模型 (Self-Model) 和有界的主动脉冲系统 (Bounded Proactive Pulse System)，以便它在一段时间内保持一致，而不会被不必要的上下文淹没。\n\n## 为什么？\n\n- **隐私很重要**：Leon 可以与本地模型 (Local Models) 和本地上下文一起工作，而不是强制所有操作都通过第三方服务 (Third-party Services)。\n- **行为的落地性很重要**：Leon 更喜欢明确的工具、上下文和记忆，而不是模糊的仅基于模型的响应。\n- **可扩展性很重要**：技能 (Skills)、工具包 (Toolkits)、桥接 (Bridges) 和二进制文件 (Binaries) 使得保持 Leon 模块化成为可能。\n- **开源很重要**：任何人都可以检查架构，在其之上构建，并帮助塑造其下一步方向。\n\n## 🚀 入门指南\n\n### 前置条件\n\n- [Node.js](https:\u002F\u002Fnodejs.org\u002F) >= 24.0.0\n- 支持的操作系统：Linux, macOS, 和 Windows\n\n推荐：使用 [Volta](https:\u002F\u002Fvolta.sh\u002F) 管理 Node.js。\n\n### 安装\n\n```sh\n# Clone the repository\ngit clone https:\u002F\u002Fgithub.com\u002Fleon-ai\u002Fleon.git\n\n# Go to the project root\ncd leon\n\n# Install pnpm\nnpm install --global pnpm@latest\n\n# Install dependencies\npnpm install\n```\n\n### 运行 Leon\n\n```sh\n# Run Leon\npnpm start\n```\n\n### 检查你的设置\n\n```sh\n# Check the setup went well\npnpm run check\n```\n\n默认情况下，Leon 在本地运行，应用程序可在 `http:\u002F\u002Flocalhost:1337` 访问。\n\n## 🏗️ 架构快照\n\n在高级层面，Leon 目前由以下部分组成：\n\n- `server\u002F`: 主运行时、路由、内存、上下文管理、HTTP API 以及代理\u002F工作流执行\n- `app\u002F`: Web 应用程序\n- `aurora\u002F`: UI 组件和预览环境\n- `skills\u002F`: 基于核心构建的用户可见功能\n- `bridges\u002F`: Node.js 和 Python 桥接以及工具包定义和工具运行时\n- `tcp_server\u002F`: 运行时堆栈部分使用的 Python 服务\n- `core\u002Fcontext\u002F`: 生成的身份和架构上下文文档，描述 Leon 的当前行为\n\n该仓库已经包含了搜索、生产力、系统工具、媒体工作流、编码辅助、基于记忆的交互以及语音\u002F音频功能等领域的技能和工具包。\n\n## 📚 文档状态\n\nLeon 2.0 的新文档尚未准备好。\n\n目前：\n\n- 将此仓库视为 **2.0 开发者预览版 (2.0 Developer Preview)** 的权威来源 (Source of Truth)\n- 使用 [`core\u002Fcontext\u002FLEON.md`](.\u002Fcore\u002Fcontext\u002FLEON.md) 获取 Leon 当前的身份和行为\n- 使用 [`core\u002Fcontext\u002FARCHITECTURE.md`](.\u002Fcore\u002Fcontext\u002FARCHITECTURE.md) 获取当前架构概览\n- 预期公共文档站点在新核心更新之前会滞后于新核心，直到更新的文档发布\n\n## ❤️ 贡献指南\n\n我们开始逐步为 **2.0 开发者预览版 (2.0 Developer Preview)** 招募贡献者。\n\n如果你想关注该项目或表达加入该入职流程的兴趣：\n\n- [2.0 开发者预览版贡献者表单](https:\u002F\u002Fforms.gle\u002F6PCG2D5rYo1q8tKMA)\n- [路线图](http:\u002F\u002Froadmap.getleon.ai)\n- [Discord](https:\u002F\u002Fdiscord.gg\u002FMNQqqKg)\n- [GitHub issues](https:\u002F\u002Fgithub.com\u002Fleon-ai\u002Fleon\u002Fissues)\n\n### 为什么贡献者数量较少？\n\nLeon 已经发展了很长时间，但当前的 2.0 工作正处于一个重大转型期。\n\n长期以来，Leon 是一个架构更简单的较小助手项目。如今，核心正在被重构为一个围绕工具（tools）、记忆（memory）、上下文（context）以及代理式执行（agent-style execution）的更强大系统。这意味着许多事情仍在变动中，这使得贡献比新文档和架构稳定后更加困难。\n\n另一个重要原因仅仅是时间问题：Leon 的开发主要仍是在业余时间进行的。因此进度可能不均衡，而在 2.0 开发者预览版（Developer Preview）仍在成型的过程中，扩大项目的开放度必须与保持方向的一致性相平衡。\n\n## 📖 Leon 背后的故事\n\nLeon 始于 2017 年，自 2019 年起一直活跃至今。如果你想了解更详细的前因后果，请阅读 [Leon 背后的故事](https:\u002F\u002Fblog.getleon.ai\u002Fthe-story-behind-leon\u002F)。\n\n## 🔔 关注动态\n\n- [X \u002F Twitter](https:\u002F\u002Fx.com\u002Fgrenlouis)\n- [通讯订阅](https:\u002F\u002Fleonai.substack.com\u002Fsubscribe)\n- [博客](https:\u002F\u002Fblog.getleon.ai)\n- [YouTube](https:\u002F\u002Fwww.youtube.com\u002Fchannel\u002FUCW6mk6j6nQUzFYY97r47emQ)\n\n## 👨 作者\n\n**Louis Grenard** ([@grenlouis](https:\u002F\u002Fx.com\u002Fgrenlouis))\n\n## 👍 赞助者\n\n\u003Ctable>\n  \u003Ctbody>\n    \u003Ctr>\n      \u003Ctd align=\"center\" valign=\"middle\" width=\"128\">\n        \u003Ca href=\"https:\u002F\u002Fgithub.com\u002FAppwrite\">\n          \u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fleon-ai_leon_readme_6394531b5a9b.png\" \u002F>\n          Appwrite\n        \u003C\u002Fa>\u003Cbr>\n        \u003Csub>\u003Csup>250 美元\u002F月\u003C\u002Fsup>\u003C\u002Fsub>\n      \u003C\u002Ftd>\n      \u003Ctd align=\"center\" valign=\"middle\" width=\"128\">\n        \u003Cimg src=\"https:\u002F\u002Fgetleon.ai\u002Fimg\u002Fanonymous.svg\" width=\"128\" \u002F>\n        匿名\n        \u003Cbr>\n        \u003Csub>\u003Csup>100 美元\u002F月\u003C\u002Fsup>\u003C\u002Fsub>\n      \u003C\u002Ftd>\n      \u003Ctd align=\"center\" valign=\"middle\" width=\"128\">\n        \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fherbundkraut\">\n          \u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fleon-ai_leon_readme_4f53a68786e4.png\" \u002F>\n          herbundkraut\n        \u003C\u002Fa>\u003Cbr>\n        \u003Csub>\u003Csup>10 美元\u002F月\u003C\u002Fsup>\u003C\u002Fsub>\n      \u003C\u002Ftd>\n      \u003Ctd align=\"center\" valign=\"middle\" width=\"128\">\n        \u003Ca href=\"http:\u002F\u002Fsponsor.getleon.ai\u002F\">\n          你？\n        \u003C\u002Fa>\n      \u003C\u002Ftd>\n    \u003C\u002Ftr>\n  \u003C\u002Ftbody>\n\u003C\u002Ftable>\n\n你也可以通过 [赞助 Leon](http:\u002F\u002Fsponsor.getleon.ai) 来做出贡献。","# Leon 快速上手指南\n\nLeon 是一款开源个人 AI 助手，基于工具、上下文、记忆和智能体执行构建。当前版本专注于 2.0 Developer Preview，支持本地运行与隐私保护。\n\n## 环境准备\n\n- **操作系统**：Linux, macOS, Windows\n- **运行时**：Node.js >= 24.0.0\n- **包管理器**：pnpm (推荐通过 [Volta](https:\u002F\u002Fvolta.sh\u002F) 管理 Node.js)\n- **分支说明**：\n  - `develop` 分支：2.0 开发者预览版（新功能核心）\n  - `master` 分支：旧版稳定架构\n  - *注：本文档基于 `develop` 分支特性编写*\n\n## 安装步骤\n\n```sh\n# 克隆仓库\ngit clone https:\u002F\u002Fgithub.com\u002Fleon-ai\u002Fleon.git\n\n# 进入项目根目录\ncd leon\n\n# 全局安装 pnpm\nnpm install --global pnpm@latest\n\n# 安装依赖\npnpm install\n```\n\n## 基本使用\n\n启动 Leon 服务：\n\n```sh\npnpm start\n```\n\n服务默认运行在本地，可通过浏览器访问：\n> http:\u002F\u002Flocalhost:1337\n\n完成安装后，建议运行以下命令检查环境配置：\n\n```sh\npnpm run check\n```\n\n---\n\n> **重要提示**：\n> - 新版文档尚未发布，请以仓库内的 [`core\u002Fcontext\u002FLEON.md`](.\u002Fcore\u002Fcontext\u002FLEON.md) 和 [`core\u002Fcontext\u002FARCHITECTURE.md`](.\u002Fcore\u002Fcontext\u002FARCHITECTURE.md) 为准。\n> - Leon 支持本地模型与远程 AI 提供商，可根据需求平衡隐私与控制权。","一位全栈开发者需要在每日晨会前快速汇总服务器健康报告并同步团队进度。\n\n### 没有 leon 时\n- 需手动打开多个终端窗口分别查询数据库连接数、CPU 负载及磁盘空间，切换频繁易出错\n- 编写日报时需要反复复制粘贴日志片段，容易遗漏关键错误信息或格式混乱\n- 临时修改的环境变量常因未记录而导致后续部署出现兼容性问题，排查困难\n- 敏感的系统日志若上传至公共 AI 平台，存在泄露核心架构与用户数据的隐私风险\n\n### 使用 leon 后\n- leon 直接在本地运行诊断脚本，一次性聚合输出所有监控指标，无需切换界面\n- 基于记忆模块自动提取异常日志摘要，生成结构化的日报草稿供人工审核\n- 能够记住常用配置偏好，自动校验环境变量一致性避免部署冲突，减少人为疏忽\n- 所有指令均在本地闭环执行，确保核心运维数据不出内网环境，完全自主可控\n\nleon 通过将零散运维动作转化为可记忆的本地智能代理，让开发者从重复劳动中解放出来。","https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fleon-ai_leon_f03e200e.gif","leon-ai","Leon AI","https:\u002F\u002Foss.gittoolsai.com\u002Favatars\u002Fleon-ai_ac4c0ff1.png","Open-Source Personal Assistant.",null,"louis@getleon.ai","grenlouis","https:\u002F\u002Fgetleon.ai","https:\u002F\u002Fgithub.com\u002Fleon-ai",[85,89,93,97,101,105,109],{"name":86,"color":87,"percentage":88},"TypeScript","#3178c6",68,{"name":90,"color":91,"percentage":92},"Python","#3572A5",21.5,{"name":94,"color":95,"percentage":96},"JavaScript","#f1e05a",8.1,{"name":98,"color":99,"percentage":100},"Sass","#a53b70",1.3,{"name":102,"color":103,"percentage":104},"SCSS","#c6538c",0.7,{"name":106,"color":107,"percentage":108},"HTML","#e34c26",0.4,{"name":110,"color":111,"percentage":112},"CSS","#663399",0,17132,1435,"2026-04-05T06:57:32","MIT","Linux, macOS, Windows","未说明",{"notes":120,"python":118,"dependencies":121},"当前核心处于 2.0 开发者预览阶段（develop 分支），官方文档尚未更新完成，稳定版本建议使用 master 分支；默认运行端口为 1337；支持本地与远程 AI 提供商混合使用；项目内部包含 Python 桥接服务和 TCP 服务器组件。",[122,123],"Node.js >= 24.0.0","pnpm",[14,54,26,15,13,55],[67,126,127,128,129,130,131,132,133,134,135,136,137,138,139,140,141,142,143,144],"personal-assistant","nodejs","python","ai","artificial-intelligence","speech-to-text","text-to-speech","speech-recognition","speech-synthesis","flite","assistant","virtual-assistant","chatbot","bot","voice-assistant","automation","offline","privacy","ai-assistant",10,"2026-03-27T02:49:30.150509","2026-04-06T05:37:16.729250",[149,154,158,163,168,173],{"id":150,"question_zh":151,"answer_zh":152,"source_url":153},2943,"为什么 Leon 无法自动检测系统中的 Python 3 版本？","在较新的系统（如 Debian）中默认可能仍使用 Python 2，且 Leon 的架构已更新。根据维护者反馈，Leon 现在不再需要在运行时依赖 Python。建议不要手动替换系统默认 Python，而是按照新流程初始化。","https:\u002F\u002Fgithub.com\u002Fleon-ai\u002Fleon\u002Fissues\u002F72",{"id":155,"question_zh":156,"answer_zh":157,"source_url":153},2944,"Leon 初始化的标准命令流程是什么？","请使用以下三个命令来安装 Beta 版本的 CLI 并创建实例：\n1. `npm install --global @leon-ai\u002Fcli@beta`\n2. `leon create birth --develop`\n3. `leon check`\n这样可以确保环境配置正确，无需担心 Python 版本检测问题。",{"id":159,"question_zh":160,"answer_zh":161,"source_url":162},2945,"使用 Python 3.8 或 Node 14 时安装失败怎么办？","有用户反馈 Python 3.7+ 版本存在兼容性问题。如果遇到 `npm run check` 或 `npm install` 失败，建议下载并安装 Python 3.6 版本进行测试。虽然部分功能（如语音输入输出）可能仍有问题，但 Python 3.6 能解决大部分安装检查错误。","https:\u002F\u002Fgithub.com\u002Fleon-ai\u002Fleon\u002Fissues\u002F188",{"id":164,"question_zh":165,"answer_zh":166,"source_url":167},2946,"与 Leon 用法语对话时程序崩溃如何解决？","如果在使用特定语言（如法语）时 Leon 崩溃，通常是由于代码未更新导致的。尝试执行以下命令重新构建项目即可修复：\n`npm run build`\n`npm start`","https:\u002F\u002Fgithub.com\u002Fleon-ai\u002Fleon\u002Fissues\u002F102",{"id":169,"question_zh":170,"answer_zh":171,"source_url":172},2947,"在 Gitpod 浏览器版本启动时出现 TCP 连接错误如何处理？","如果遇到 TCP 连接相关的报错，可以尝试升级 setuptools 库来解决。请在终端运行以下命令：\n`pip install --upgrade setuptools`\n然后重试启动过程。","https:\u002F\u002Fgithub.com\u002Fleon-ai\u002Fleon\u002Fissues\u002F397",{"id":174,"question_zh":175,"answer_zh":176,"source_url":177},2948,"本地 Python 版本与项目要求不一致（如找不到 3.6）如何配置？","如果系统安装了其他版本（如 3.7）但项目要求 3.6，可以通过修改配置文件来适配本地环境。请编辑以下三个文件，将 `python_version` 从 3.6 替换为 3.7：\n1. `bridges\u002Fpython\u002FPipfile`\n2. `bridges\u002Fpython\u002FPipfile.lock`\n3. `scripts\u002Fcheck.js` (查找 `pythonRequiredVersion`)","https:\u002F\u002Fgithub.com\u002Fleon-ai\u002Fleon\u002Fissues\u002F138",[179,184,189,194,199,204,208,212,216,220,224,229,233,237,241,245,249,254,259,264],{"id":180,"version":181,"summary_zh":182,"released_at":183},102454,"tcp-server_v2.0.0","*Leon's TCP server to communicate between the core and third-party nodes.*","2026-02-19T09:08:01",{"id":185,"version":186,"summary_zh":187,"released_at":188},102455,"python-bridge_v1.4.0","*Leon's Python bridge to communicate between the core and skills made with Python.*","2026-02-19T08:36:46",{"id":190,"version":191,"summary_zh":192,"released_at":193},102456,"nodejs-bridge_v1.3.0","*Leon's Node.js bridge to communicate between the core and skills made with JavaScript.*","2026-02-19T08:39:46",{"id":195,"version":196,"summary_zh":197,"released_at":198},102457,"python-bridge_v1.3.0","*Leon's Python bridge to communicate between the core and skills made with Python. Windows is not supported for this version.*","2024-05-08T16:59:47",{"id":200,"version":201,"summary_zh":202,"released_at":203},102458,"nodejs-bridge_v1.2.0","Leon's Node.js bridge to communicate between the core and skills made with JavaScript.","2024-05-08T17:04:39",{"id":205,"version":206,"summary_zh":182,"released_at":207},102459,"tcp-server_v1.1.0","2023-11-14T15:50:46",{"id":209,"version":210,"summary_zh":187,"released_at":211},102460,"python-bridge_v1.2.0","2023-11-14T15:50:17",{"id":213,"version":214,"summary_zh":192,"released_at":215},102461,"nodejs-bridge_v1.1.0","2023-11-14T15:49:47",{"id":217,"version":218,"summary_zh":187,"released_at":219},102462,"python-bridge_v1.1.0","2023-05-29T14:54:57",{"id":221,"version":222,"summary_zh":192,"released_at":223},102463,"nodejs-bridge_v1.0.0","2023-05-29T14:54:23",{"id":225,"version":226,"summary_zh":227,"released_at":228},102464,"v1.0.0-beta.8","_Please refer to [our latest blog post](https:\u002F\u002Fblog.getleon.ai\u002Fbinaries-and-typescript-rewrite-1-0-0-beta-8\u002F) for more information on the new release of our dear Leon._","2023-05-01T02:18:11",{"id":230,"version":231,"summary_zh":192,"released_at":232},102465,"nodejs-bridge_v0.0.1-alpha.0","2023-05-01T14:52:59",{"id":234,"version":235,"summary_zh":192,"released_at":236},102466,"nodejs-bridge_v0.0.0","2023-04-30T16:54:43",{"id":238,"version":239,"summary_zh":187,"released_at":240},102467,"python-bridge_v1.0.1","2023-04-26T16:03:45",{"id":242,"version":243,"summary_zh":182,"released_at":244},102468,"tcp-server_v1.0.0","2022-10-22T15:24:07",{"id":246,"version":247,"summary_zh":187,"released_at":248},102469,"python-bridge_v1.0.0","2022-10-22T15:24:02",{"id":250,"version":251,"summary_zh":252,"released_at":253},102470,"v1.0.0-beta.7","*Please [read this blog post](https:\u002F\u002Fblog.getleon.ai\u002Fa-much-better-nlp-and-future-1-0-0-beta-7\u002F) to know more about all the new features and the exciting future of Leon.*\r\n\r\n### BREAKING CHANGES\r\n - remove legacy packages [07743657](https:\u002F\u002Fgithub.com\u002Fleon-ai\u002Fleon\u002Fcommit\u002F07743657cd2954e7f850c08eea7c032c24b28a96) \r\n  \r\n### Features\r\n - create new NLP skills resolvers model + NLP global resolvers model [602604e4](https:\u002F\u002Fgithub.com\u002Fleon-ai\u002Fleon\u002Fcommit\u002F602604e43788c6b6be8c402d54fe54342d0cd5d6) \r\n - better isolate skill resolvers from global resolvers + finish up Akinator skill [905d248e](https:\u002F\u002Fgithub.com\u002Fleon-ai\u002Fleon\u002Fcommit\u002F905d248ebf7e84b1ccc74450520228aef9a8804a) \r\n - transfer language from core to skills + support thematics on Akinator skill [b35a249b](https:\u002F\u002Fgithub.com\u002Fleon-ai\u002Fleon\u002Fcommit\u002Fb35a249bf68000d6708aaee4abc4cd97f5b80035) \r\n - actions on slot level + akinator skill progress [7101b8b4](https:\u002F\u002Fgithub.com\u002Fleon-ai\u002Fleon\u002Fcommit\u002F7101b8b4b828b49e009da2fcdac7c5ed2e48c8f8) \r\n - add Cartesian sample training on resolvers + enum entities [6ed88a59](https:\u002F\u002Fgithub.com\u002Fleon-ai\u002Fleon\u002Fcommit\u002F6ed88a5946c77b356e49fe8b9cbe890b8dd1f037) \r\n - map skills resolvers intents [eb5ade76](https:\u002F\u002Fgithub.com\u002Fleon-ai\u002Fleon\u002Fcommit\u002Feb5ade76844dd14f5d5a5c5eeb434eed70fe62f4) \r\n - train skills resolvers and remap as per changes [82df0a3c](https:\u002F\u002Fgithub.com\u002Fleon-ai\u002Fleon\u002Fcommit\u002F82df0a3c235fbd50ad0cfe12e23a51f777dcd658) \r\n - achieve Cartesian training [a1e9011d](https:\u002F\u002Fgithub.com\u002Fleon-ai\u002Fleon\u002Fcommit\u002Fa1e9011d5db48ed8e9f49cef2d813ee7e2400ec2) \r\n - introduce suggestions [dcddacca](https:\u002F\u002Fgithub.com\u002Fleon-ai\u002Fleon\u002Fcommit\u002Fdcddacca2956529de0aea8ff98e1e6f16104966a) \r\n - communicate suggestions to the client [4b5a8835](https:\u002F\u002Fgithub.com\u002Fleon-ai\u002Fleon\u002Fcommit\u002F4b5a883510fd4421a491f999cc21d8f7dd369a03) \r\n - shared skills memory [795acc5b](https:\u002F\u002Fgithub.com\u002Fleon-ai\u002Fleon\u002Fcommit\u002F795acc5bdd29e9a27d1cf3b4407453648d573973) \r\n - support dynamic variables on skill NLU settings for logic type [10d10a16](https:\u002F\u002Fgithub.com\u002Fleon-ai\u002Fleon\u002Fcommit\u002F10d10a1690cb65970932ee7230e3f324ec67dbce) \r\n - tmp resolvers mapping [b1a332ba](https:\u002F\u002Fgithub.com\u002Fleon-ai\u002Fleon\u002Fcommit\u002Fb1a332bab6af8b74a8c58c07bac3ef3a1cebad89) \r\n - start to map resolvers between the core and skills [e88495a9](https:\u002F\u002Fgithub.com\u002Fleon-ai\u002Fleon\u002Fcommit\u002Fe88495a9a94e86026fd0c7c4c44f3ff06edb2e80) \r\n - train affirmation and denial resolver [993d52e8](https:\u002F\u002Fgithub.com\u002Fleon-ai\u002Fleon\u002Fcommit\u002F993d52e8686f335039ff3d5e2a82c1a37efb1825) \r\n - Python TCP server and Node.js TCP client for IPC (wip) [5970ec9e](https:\u002F\u002Fgithub.com\u002Fleon-ai\u002Fleon\u002Fcommit\u002F5970ec9e8e4c2784c50e2ddc76b34b71aa4310e6) \r\n - introduce spaCy for complete NER (wip) [caa86fc8](https:\u002F\u002Fgithub.com\u002Fleon-ai\u002Fleon\u002Fcommit\u002Fcaa86fc8a6850b18f67ba7bedb423be693a88d17) \r\n - slot filling (wip) [76547d94](https:\u002F\u002Fgithub.com\u002Fleon-ai\u002Fleon\u002Fcommit\u002F76547d9411c32e0eb2ccfdac3a4901d2d2fb37f6) \r\n - share data across domains [f4f9fff9](https:\u002F\u002Fgithub.com\u002Fleon-ai\u002Fleon\u002Fcommit\u002Ff4f9fff9783861be183990d7869973c7a30c8104) \r\n - dynamic variable binding on NLG [0367b44f](https:\u002F\u002Fgithub.com\u002Fleon-ai\u002Fleon\u002Fcommit\u002F0367b44f211c1629fffe6981a730f171707bf0c0) \r\n - context and slot filling preparation (wip) [975b8ebc](https:\u002F\u002Fgithub.com\u002Fleon-ai\u002Fleon\u002Fcommit\u002F975b8ebcf00db91b44dd067be6dde5c1bf32fff1) \r\n - annotate entities on the fly + prepare for dialog skill type and cross-domains data [4107932d](https:\u002F\u002Fgithub.com\u002Fleon-ai\u002Fleon\u002Fcommit\u002F4107932d000086188d6f44ef67b73cc322fc58e5) \r\n - new NLP training [d8023308](https:\u002F\u002Fgithub.com\u002Fleon-ai\u002Fleon\u002Fcommit\u002Fd8023308d0ef1f3eede37f21f45daa2f893031b0) \r\n  \r\n - **server:**\r\n   - trigger next action suggestions or current ones [244d08c0](https:\u002F\u002Fgithub.com\u002Fleon-ai\u002Fleon\u002Fcommit\u002F244d08c0bd0fea315269f52ab899f9b7fe083f51) \r\n   - introduce main NLP model and resolvers NLP model [e37526d9](https:\u002F\u002Fgithub.com\u002Fleon-ai\u002Fleon\u002Fcommit\u002Fe37526d9056d858ebcf17b81f6714f47b67c77cb) \r\n   - change log emojis [843bc428](https:\u002F\u002Fgithub.com\u002Fleon-ai\u002Fleon\u002Fcommit\u002F843bc428b8deb397e2d051a8e0bfaf1b82b459a2) \r\n   - provide nextAction even when no slot is set and clean up NLU object on context switch [8377c63d](https:\u002F\u002Fgithub.com\u002Fleon-ai\u002Fleon\u002Fcommit\u002F8377c63db4e4e42ed929171cd8b9abdb13c44b2a) \r\n   - report full traceback from skills execution [b69b1fea](https:\u002F\u002Fgithub.com\u002Fleon-ai\u002Fleon\u002Fcommit\u002Fb69b1fea16250421bc7d5def1c973dd43e453071) \r\n   - support on-the-fly entity annotation for built-in entities [567b030c](https:\u002F\u002Fgithub.com\u002Fleon-ai\u002Fleon\u002Fcommit\u002F567b030c4fcf8df266c39cca61a146fb33b9e0fc) \r\n   - save slots within conversation context [fce47cdb](https:\u002F\u002Fgithub.com\u002Fleon-ai\u002Fleon\u002Fcommit\u002Ffce47cdbd570993ac5cca2b4ff5bc97969df4e40) \r\n   - resolve resolvers tmp [ceea47ff](https:\u002F\u002Fgithub.com\u002Fleon-ai\u002Fleon\u002Fcommit\u002Fceea47ff7dd536bfd3adf3cc355e90e3e94b1cbd) \r\n   - prepare the next action on non-slot-filled skills [0acb31a9](https:\u002F\u002Fgithub.com\u002Fleon-ai\u002Fleon\u002Fcommit\u002F0acb31a9c61c1c094b29f3d0ff2647d625eab0be) \r\n   - add more affirmative utterance samples [870ab2e8](https:\u002F\u002Fgithub.com\u002Fleon-ai\u002Fleon\u002Fcommit\u002F870ab2e87e","2022-08-24T13:29:28",{"id":255,"version":256,"summary_zh":257,"released_at":258},102471,"v1.0.0-beta.6","### Features\r\n - simple coqui-ai stt integration [86a4816b](https:\u002F\u002Fgithub.com\u002Fleon-ai\u002Fleon\u002Fcommit\u002F86a4816b777fee8ec9c89648c5866a75de56c017) @johannbarbie \r\n - HTTP API key generator [d10a7fa7](https:\u002F\u002Fgithub.com\u002Fleon-ai\u002Fleon\u002Fcommit\u002Fd10a7fa7880a0bf2fb1cae7904d1ef4257f05257) \r\n - avoid unnecessary routes generation  \r\n  \r\n - **server:**\r\n   - make Coqui STT the default STT solution [70399187](https:\u002F\u002Fgithub.com\u002Fleon-ai\u002Fleon\u002Fcommit\u002F7039918760c0ef7ba93bf45820e3cae774c42d8c) \r\n     - add HTTP API key middleware [cdf41499](https:\u002F\u002Fgithub.com\u002Fleon-ai\u002Fleon\u002Fcommit\u002Fcdf4149939cbe3f3ae81039957dba3377a78f5a6) \r\n     - expose queries over HTTP [b6428d03](https:\u002F\u002Fgithub.com\u002Fleon-ai\u002Fleon\u002Fcommit\u002Fb6428d038452619f1682c863892cd8f376efca84) \r\n     - add timeout action over HTTP [115f9c16](https:\u002F\u002Fgithub.com\u002Fleon-ai\u002Fleon\u002Fcommit\u002F115f9c164559d761625cc6f362749f7d2417d300) \r\n     - handle built-in and trim entities over HTTP + add \"disabled\" HTTP API action option [82fb967a](https:\u002F\u002Fgithub.com\u002Fleon-ai\u002Fleon\u002Fcommit\u002F82fb967af8f49421e3b2474184da3d34fb17294f) \r\n     - execute modules over HTTP [2e5b2c59](https:\u002F\u002Fgithub.com\u002Fleon-ai\u002Fleon\u002Fcommit\u002F2e5b2c59da0bafe3acd966773c6fac3611b3bd0c) \r\n     - generate Fastify routes on the file to expose packages over HTTP [5b41713a](https:\u002F\u002Fgithub.com\u002Fleon-ai\u002Fleon\u002Fcommit\u002F5b41713a68ee628e695212dbebc88f6b9a94b461) \r\n  ### Bug Fixes\r\n - do not ask to regenerate the HTTP API key if this one isn't available yet [d265377a](https:\u002F\u002Fgithub.com\u002Fleon-ai\u002Fleon\u002Fcommit\u002Fd265377a43fd4506cf12db46f261b891f2054ed2) \r\n - Python deps tree check [c6c01291](https:\u002F\u002Fgithub.com\u002Fleon-ai\u002Fleon\u002Fcommit\u002Fc6c012915824227efdf0c50df6a8f1cd8d70ed42) \r\n - hotword offline (#342) [f563d01d](https:\u002F\u002Fgithub.com\u002Fleon-ai\u002Fleon\u002Fcommit\u002Ff563d01d077499c836e94c86f85cedc2ad4d56e6) \r\n - addressed comments by @JRMeyer [b1c6f5c8](https:\u002F\u002Fgithub.com\u002Fleon-ai\u002Fleon\u002Fcommit\u002Fb1c6f5c883103d57d4fe566af640fc3ac5ce713d) \r\n - allow to detect STT offline capabilities [04d62288](https:\u002F\u002Fgithub.com\u002Fleon-ai\u002Fleon\u002Fcommit\u002F04d622884165e0bde65785569a659f59cf9e8582) \r\n - Amazon Polly is always configured on check script due to new structure [e6246d1f](https:\u002F\u002Fgithub.com\u002Fleon-ai\u002Fleon\u002Fcommit\u002Fe6246d1f8f9ec15a4ebe9600764afffbaa7e62d9) \r\n  \r\n### Performance Improvements\r\n - check if Python deps tree has been updated before going through deps install [2d0b0f13](https:\u002F\u002Fgithub.com\u002Fleon-ai\u002Fleon\u002Fcommit\u002F2d0b0f1365d8e4d6eadf9f7cc0a16b7b4b4306f4)","2022-02-07T09:08:21",{"id":260,"version":261,"summary_zh":262,"released_at":263},102472,"v1.0.0-beta.5","*This release marks a major turn in the future versions of the Leon core. Please [read this blog post](https:\u002F\u002Fblog.getleon.ai\u002Fi-ran-away-from-open-source\u002F) to know more.*\r\n\r\n### BREAKING CHANGES\r\n - Node.js 16+ and npm 8+ minimum requirements [2f66f1c1](https:\u002F\u002Fgithub.com\u002Fleon-ai\u002Fleon\u002Fcommit\u002F2f66f1c17bb2e4a1c18b4251d49de252b8d87344)\r\n### Features\r\n - **server:** support arrays on NER between conditions [7cf7f979](https:\u002F\u002Fgithub.com\u002Fleon-ai\u002Fleon\u002Fcommit\u002F7cf7f9791254e1950fe9128ce1b3a58079cc2ada)\r\n### Bug Fixes\r\n - jest-extended new setup due to latest update [02f766d6](https:\u002F\u002Fgithub.com\u002Fleon-ai\u002Fleon\u002Fcommit\u002F02f766d6a8453609ebaec78356aa6e6d4df0967b)\r\n### Performance Improvements\r\n - Windows setup on DeepSpeech dep removal [13f5a49f](https:\u002F\u002Fgithub.com\u002Fleon-ai\u002Fleon\u002Fcommit\u002F13f5a49f678f8f67a93b67d4f558cddcf237e204)\r\n### Documentation Changes\r\n - URL redirect managed by registrar [c16d5b28](https:\u002F\u002Fgithub.com\u002Fleon-ai\u002Fleon\u002Fcommit\u002Fc16d5b280b758f7e18305e30678adec79f0a0716)  ","2021-12-28T13:30:34",{"id":265,"version":266,"summary_zh":267,"released_at":268},102473,"v1.0.0-beta.4","*This release includes a lot of changes that are made under the hood and are not displayed here, please **[read the blog post](https:\u002F\u002Fblog.getleon.ai\u002Fgetting-rid-of-dust-1-0-0-beta-4\u002F)** to know more.*\r\n\r\n### BREAKING CHANGES\r\n\r\n - **package\u002Fchecker:** introduce Have I Been Pwned v3 API with API key ([0ca89fe3](https:\u002F\u002Fgithub.com\u002Fleon-ai\u002Fleon\u002Fcommit\u002F0ca89fe32d51c80cec5f9446acf14990390a5917))\r\n - **server:**\r\n   - AWS SDK new structure due to v3 and adapt Amazon Polly changes ([f15f2db7](https:\u002F\u002Fgithub.com\u002Fleon-ai\u002Fleon\u002Fcommit\u002Ff15f2db78e5781d05e5e2bcb186645966d17debf))\r\n   - IBM Watson TTS and STT new structure ([f41ea0e9](https:\u002F\u002Fgithub.com\u002Fleon-ai\u002Fleon\u002Fcommit\u002Ff41ea0e9a1479bfd6a1cb2e8d1f70aec744c685b) | [2668c295](https:\u002F\u002Fgithub.com\u002Fleon-ai\u002Fleon\u002Fcommit\u002F2668c295880ee753ef7ca26a91dbc7e0901febff))\r\n### Features \r\n - **package\u002Fcalendar:** introduce To-Do list module ([0cdd73d6](https:\u002F\u002Fgithub.com\u002Fleon-ai\u002Fleon\u002Fcommit\u002F0cdd73d6c24a287915f691e3b12edacd75fd383a) | [857be947](https:\u002F\u002Fgithub.com\u002Fleon-ai\u002Fleon\u002Fcommit\u002F857be947792c650ac35847e14fc41064008cef24) | [2041be14](https:\u002F\u002Fgithub.com\u002Fleon-ai\u002Fleon\u002Fcommit\u002F2041be14dbc01640a61de96d1982cc20cd05a8b3) | [12e8f5c3](https:\u002F\u002Fgithub.com\u002Fleon-ai\u002Fleon\u002Fcommit\u002F12e8f5c3bfb436aa212557cd99d9926aa431ab4f) | [8575e9e3](https:\u002F\u002Fgithub.com\u002Fleon-ai\u002Fleon\u002Fcommit\u002F8575e9e3ef01499d9f7be6d313a85d48549e9107) | [5e128df0](https:\u002F\u002Fgithub.com\u002Fleon-ai\u002Fleon\u002Fcommit\u002F5e128df023977525de3e66ce2826aace87569308) | [602aa694](https:\u002F\u002Fgithub.com\u002Fleon-ai\u002Fleon\u002Fcommit\u002F602aa694ac49333f48c119cf2ca2aa7f54b8ae44) | [b9693df9](https:\u002F\u002Fgithub.com\u002Fleon-ai\u002Fleon\u002Fcommit\u002Fb9693df90cbc01067e18e64db4d377e41b3fd1d4) | [581da8cd](https:\u002F\u002Fgithub.com\u002Fleon-ai\u002Fleon\u002Fcommit\u002F581da8cd9806323aabb0e85778d645df3c0948b9) | [53f7db55](https:\u002F\u002Fgithub.com\u002Fleon-ai\u002Fleon\u002Fcommit\u002F53f7db55c6e916751f1d59c239628d5ea8914009) | [ae073971](https:\u002F\u002Fgithub.com\u002Fleon-ai\u002Fleon\u002Fcommit\u002Fae0739717b6a17373d8f9bc69571c67c1c571b4a))\r\n - **package\u002Fchecker:** introduce Have I Been Pwned module ([61c1b55a](https:\u002F\u002Fgithub.com\u002Fleon-ai\u002Fleon\u002Fcommit\u002F61c1b55af5691c03f6a6dae0cf3f236a374f1fe7) | [5a999bc6](https:\u002F\u002Fgithub.com\u002Fleon-ai\u002Fleon\u002Fcommit\u002F5a999bc63aa0c667c4e3092daac6a05a6c4b4499) | [36368664](https:\u002F\u002Fgithub.com\u002Fleon-ai\u002Fleon\u002Fcommit\u002F36368664fce8bcf0c17c4c83818aeb418f1e2f23) | [a7a6d885](https:\u002F\u002Fgithub.com\u002Fleon-ai\u002Fleon\u002Fcommit\u002Fa7a6d885a83455163eeca74a355177d65db156b8) | [c73ba52b](https:\u002F\u002Fgithub.com\u002Fleon-ai\u002Fleon\u002Fcommit\u002Fc73ba52ba8575a64b3329e59a50050d15281d0ec) | [8374e548](https:\u002F\u002Fgithub.com\u002Fleon-ai\u002Fleon\u002Fcommit\u002F8374e5481022de9b134f49180a8dfe28db136261) | [a476fd0f](https:\u002F\u002Fgithub.com\u002Fleon-ai\u002Fleon\u002Fcommit\u002Fa476fd0f38f18bf8035db213be2c55f83871038d))\r\n - **package\u002Fnetwork:** add speedtest module ([09ad4340](https:\u002F\u002Fgithub.com\u002Fleon-ai\u002Fleon\u002Fcommit\u002F09ad43406d3df8ca65f385a91c159def51f91811))\r\n - **server:**\r\n   - add regex entity type [3fda3526](https:\u002F\u002Fgithub.com\u002Fleon-ai\u002Fleon\u002Fcommit\u002F3fda3526c7425bdea4b669474fa77efd61c06a8e) \r\n   - catch unsupported action entity type [5bc6c3f1](https:\u002F\u002Fgithub.com\u002Fleon-ai\u002Fleon\u002Fcommit\u002F5bc6c3f116d6b9ece2cc3bebdbdb08f019ee90b9) \r\n   - NER backbone [24cf3c9a](https:\u002F\u002Fgithub.com\u002Fleon-ai\u002Fleon\u002Fcommit\u002F24cf3c9a4facd05a4c626ff9d2e7c83a5ae15298) \r\n   - introduce actions module [b449376f](https:\u002F\u002Fgithub.com\u002Fleon-ai\u002Fleon\u002Fcommit\u002Fb449376f61dc995e2e264c6a14ba123926f5cc58) \r\n### Bug Fixes\r\n - set correct status code for GET \u002Fdownloads [690f1841](https:\u002F\u002Fgithub.com\u002Fleon-ai\u002Fleon\u002Fcommit\u002F690f1841d681a1e48e1837e3e166228d6c2ddaf6) \r\n - take `.env` in consideration when using Docker [d38e6095](https:\u002F\u002Fgithub.com\u002Fleon-ai\u002Fleon\u002Fcommit\u002Fd38e6095f9b71467b8486430fba4bb7007ec4c5a) \r\n - spinner test [9071c927](https:\u002F\u002Fgithub.com\u002Fleon-ai\u002Fleon\u002Fcommit\u002F9071c92790be674687590e4a896bbf44bc26fb43) \r\n - e2e tests by adding modules actions level [5cf77d90](https:\u002F\u002Fgithub.com\u002Fleon-ai\u002Fleon\u002Fcommit\u002F5cf77d9011a80b326f229b2309a6910ac0f1cfa2) \r\n  \r\n - **package\u002Fleon:** fix english translations [90225707](https:\u002F\u002Fgithub.com\u002Fleon-ai\u002Fleon\u002Fcommit\u002F90225707f94154021cadeb9c61bdc48c3de5aa29)\r\n - **package\u002Fnetwork:** make use of new compatible speedtest lib [0c925626](https:\u002F\u002Fgithub.com\u002Fleon-ai\u002Fleon\u002Fcommit\u002F0c925626df65858fa039972b3f3d5f38fde93eb6) \r\n - **package\u002Ftrend:**\r\n   - GitHub module new scraping [68414937](https:\u002F\u002Fgithub.com\u002Fleon-ai\u002Fleon\u002Fcommit\u002F6841493740ca859000c1fd8d692b73fc79fcf500) \r\n   - when there is no star provided on the GitHub module [563fb409](https:\u002F\u002Fgithub.com\u002Fleon-ai\u002Fleon\u002Fcommit\u002F563fb40955e2deb5c6d0bd064fc9cc8766a6fcaf) \r\n - **server:**\r\n   - make use of Basic plugin from the main NLP container [e1d5bed3](https:\u002F\u002Fgithub.com\u002Fleon-ai\u002Fleon\u002Fcommit\u002Fe1d5bed3e688db566a0cb803dda5c2d57c599d8c) \r\n   - NER trim entity on after conditions [fa6a5a43](https:\u002F\u002Fgithub.com\u002Fleon-ai\u002Fleon\u002Fcommit\u002Ffa6a5a43a60b493aa403a44957082382494c129b) \r\n### Documentation Changes\r\n - add minimum Pipenv version requirement to README [72e46bd6](https:\u002F\u002Fgithub.com\u002Fleon-ai\u002Fleon\u002Fcommit\u002F72e46bd6c175a4a149fb6b14522823b224d7c152) \r\n - hunt broken links [b2a22792](https:\u002F\u002Fgithub.com\u002Fleon-ai\u002Fleon\u002Fcommit\u002Fb2a2279243e7566b57fb7f6960","2021-05-01T13:37:32"]