[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"similar-litanlitudan--skyagi":3,"tool-litanlitudan--skyagi":64},[4,17,27,35,44,52],{"id":5,"name":6,"github_repo":7,"description_zh":8,"stars":9,"difficulty_score":10,"last_commit_at":11,"category_tags":12,"status":16},3808,"stable-diffusion-webui","AUTOMATIC1111\u002Fstable-diffusion-webui","stable-diffusion-webui 是一个基于 Gradio 构建的网页版操作界面，旨在让用户能够轻松地在本地运行和使用强大的 Stable Diffusion 图像生成模型。它解决了原始模型依赖命令行、操作门槛高且功能分散的痛点，将复杂的 AI 绘图流程整合进一个直观易用的图形化平台。\n\n无论是希望快速上手的普通创作者、需要精细控制画面细节的设计师，还是想要深入探索模型潜力的开发者与研究人员，都能从中获益。其核心亮点在于极高的功能丰富度：不仅支持文生图、图生图、局部重绘（Inpainting）和外绘（Outpainting）等基础模式，还独创了注意力机制调整、提示词矩阵、负向提示词以及“高清修复”等高级功能。此外，它内置了 GFPGAN 和 CodeFormer 等人脸修复工具，支持多种神经网络放大算法，并允许用户通过插件系统无限扩展能力。即使是显存有限的设备，stable-diffusion-webui 也提供了相应的优化选项，让高质量的 AI 艺术创作变得触手可及。",162132,3,"2026-04-05T11:01:52",[13,14,15],"开发框架","图像","Agent","ready",{"id":18,"name":19,"github_repo":20,"description_zh":21,"stars":22,"difficulty_score":23,"last_commit_at":24,"category_tags":25,"status":16},1381,"everything-claude-code","affaan-m\u002Feverything-claude-code","everything-claude-code 是一套专为 AI 编程助手（如 Claude Code、Codex、Cursor 等）打造的高性能优化系统。它不仅仅是一组配置文件，而是一个经过长期实战打磨的完整框架，旨在解决 AI 代理在实际开发中面临的效率低下、记忆丢失、安全隐患及缺乏持续学习能力等核心痛点。\n\n通过引入技能模块化、直觉增强、记忆持久化机制以及内置的安全扫描功能，everything-claude-code 能显著提升 AI 在复杂任务中的表现，帮助开发者构建更稳定、更智能的生产级 AI 代理。其独特的“研究优先”开发理念和针对 Token 消耗的优化策略，使得模型响应更快、成本更低，同时有效防御潜在的攻击向量。\n\n这套工具特别适合软件开发者、AI 研究人员以及希望深度定制 AI 工作流的技术团队使用。无论您是在构建大型代码库，还是需要 AI 协助进行安全审计与自动化测试，everything-claude-code 都能提供强大的底层支持。作为一个曾荣获 Anthropic 黑客大奖的开源项目，它融合了多语言支持与丰富的实战钩子（hooks），让 AI 真正成长为懂上",140436,2,"2026-04-05T23:32:43",[13,15,26],"语言模型",{"id":28,"name":29,"github_repo":30,"description_zh":31,"stars":32,"difficulty_score":23,"last_commit_at":33,"category_tags":34,"status":16},2271,"ComfyUI","Comfy-Org\u002FComfyUI","ComfyUI 是一款功能强大且高度模块化的视觉 AI 引擎，专为设计和执行复杂的 Stable Diffusion 图像生成流程而打造。它摒弃了传统的代码编写模式，采用直观的节点式流程图界面，让用户通过连接不同的功能模块即可构建个性化的生成管线。\n\n这一设计巧妙解决了高级 AI 绘图工作流配置复杂、灵活性不足的痛点。用户无需具备编程背景，也能自由组合模型、调整参数并实时预览效果，轻松实现从基础文生图到多步骤高清修复等各类复杂任务。ComfyUI 拥有极佳的兼容性，不仅支持 Windows、macOS 和 Linux 全平台，还广泛适配 NVIDIA、AMD、Intel 及苹果 Silicon 等多种硬件架构，并率先支持 SDXL、Flux、SD3 等前沿模型。\n\n无论是希望深入探索算法潜力的研究人员和开发者，还是追求极致创作自由度的设计师与资深 AI 绘画爱好者，ComfyUI 都能提供强大的支持。其独特的模块化架构允许社区不断扩展新功能，使其成为当前最灵活、生态最丰富的开源扩散模型工具之一，帮助用户将创意高效转化为现实。",107662,"2026-04-03T11:11:01",[13,14,15],{"id":36,"name":37,"github_repo":38,"description_zh":39,"stars":40,"difficulty_score":10,"last_commit_at":41,"category_tags":42,"status":16},4292,"Deep-Live-Cam","hacksider\u002FDeep-Live-Cam","Deep-Live-Cam 是一款专注于实时换脸与视频生成的开源工具，用户仅需一张静态照片，即可通过“一键操作”实现摄像头画面的即时变脸或制作深度伪造视频。它有效解决了传统换脸技术流程繁琐、对硬件配置要求极高以及难以实时预览的痛点，让高质量的数字内容创作变得触手可及。\n\n这款工具不仅适合开发者和技术研究人员探索算法边界，更因其极简的操作逻辑（仅需三步：选脸、选摄像头、启动），广泛适用于普通用户、内容创作者、设计师及直播主播。无论是为了动画角色定制、服装展示模特替换，还是制作趣味短视频和直播互动，Deep-Live-Cam 都能提供流畅的支持。\n\n其核心技术亮点在于强大的实时处理能力，支持口型遮罩（Mouth Mask）以保留使用者原始的嘴部动作，确保表情自然精准；同时具备“人脸映射”功能，可同时对画面中的多个主体应用不同面孔。此外，项目内置了严格的内容安全过滤机制，自动拦截涉及裸露、暴力等不当素材，并倡导用户在获得授权及明确标注的前提下合规使用，体现了技术发展与伦理责任的平衡。",88924,"2026-04-06T03:28:53",[13,14,15,43],"视频",{"id":45,"name":46,"github_repo":47,"description_zh":48,"stars":49,"difficulty_score":23,"last_commit_at":50,"category_tags":51,"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":53,"name":54,"github_repo":55,"description_zh":56,"stars":57,"difficulty_score":23,"last_commit_at":58,"category_tags":59,"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",[14,60,43,61,15,62,26,13,63],"数据工具","插件","其他","音频",{"id":65,"github_repo":66,"name":67,"description_en":68,"description_zh":69,"ai_summary_zh":69,"readme_en":70,"readme_zh":71,"quickstart_zh":72,"use_case_zh":73,"hero_image_url":74,"owner_login":75,"owner_name":76,"owner_avatar_url":77,"owner_bio":78,"owner_company":79,"owner_location":80,"owner_email":81,"owner_twitter":75,"owner_website":82,"owner_url":83,"languages":84,"stars":120,"forks":121,"last_commit_at":122,"license":123,"difficulty_score":23,"env_os":124,"env_gpu":124,"env_ram":124,"env_deps":125,"category_tags":129,"github_topics":130,"view_count":23,"oss_zip_url":136,"oss_zip_packed_at":136,"status":16,"created_at":137,"updated_at":138,"faqs":139,"releases":169},4198,"litanlitudan\u002Fskyagi","skyagi","SkyAGI: Emerging human-behavior simulation capability in LLM","SkyAGI 是一款基于大语言模型（LLM）的 Python 开源工具，旨在模拟逼真的人类行为。它实现了“生成式智能体”（Generative Agents）的前沿理念，能够构建出具备记忆、规划与反应能力的虚拟角色，让用户在角色扮演游戏中获得极具沉浸感的互动体验。\n\n传统 AI 控制的非玩家角色（NPC）往往回应生硬、缺乏连贯性，而 SkyAGI 有效解决了这一痛点。其核心亮点在于赋予了智能体类似人类的记忆机制与自主决策能力：角色不仅能记住过往对话细节，还能根据情境变化主动调整策略，甚至在没有人工干预的情况下推动剧情自然发展，使得交互过程难以被分辨为机器生成。\n\n该项目非常适合游戏开发者、AI 研究人员以及互动叙事设计师使用。开发者可利用它革新 NPC 脚本编写方式，创造更生动的游戏世界；研究人员可借此探索大模型在社会模拟中的涌现能力；设计师则能快速原型化复杂的角色互动场景。虽然普通用户也可通过配置 JSON 文件自定义如《生活大爆炸》或《复仇者联盟》中的角色进行体验，但其核心价值更多体现在为专业创作者提供强大的行为模拟基座，启发对未来人机交互形态的重新思考。","# SkyAGI: Emerging human-behavior simulation capability in LLM\n\nhttps:\u002F\u002Fgithub.com\u002Flitanlitudan\u002Fskyagi\u002Fassets\u002F4970420\u002Fa584b364-e659-476d-a884-932b3c04df61\n\n\u003Cp align=\"center\">\n    \u003Ca href=\"https:\u002F\u002Fpypi.org\u002Fproject\u002Fskyagi\u002F\">\n        \u003Cimg alt=\"PyPI\" src=\"https:\u002F\u002Fimg.shields.io\u002Fpypi\u002Fv\u002Fskyagi?color=gree\">\n    \u003C\u002Fa>\n\u003C\u002Fp>\n\n`SkyAGI` is a python package that demonstrates LLM's emerging capability in simulating believable human behaviors.\nSpecifically, `SkyAGI` implements the idea of [Generative Agents](https:\u002F\u002Farxiv.org\u002Fabs\u002F2304.03442) and delivers a role-playing game that creates a very interesting user experience.\n\nDifferent from previous AI based NPC systems, `SkyAGI`'s NPC generates very believable human responses.\nThe interesting observations in this demo show a huge potential for rethinking game development in many aspects, such as NPC script writing.\n\nTo demonstrate this, `SkyAGI` provides example characters from `The Big Bang Theory` and `The Avengers` as a starting point.\nUsers could also define customized characters by creating config json files like [customized_character.json](https:\u002F\u002Fgithub.com\u002Flitanlitudan\u002Fskyagi\u002Fblob\u002Fmain\u002Fexamples\u002Fexample_agent.json)\nFor details about the interesting observations, refer to the [observations section](https:\u002F\u002Fgithub.com\u002Flitanlitudan\u002Fskyagi\u002F#interesting-observations-in-this-demo).\n\n## Quick Start\n\nInstallation\n\n```sh\npip install --upgrade skyagi\n```\n\nOr\n\n```sh\nmake install\n```\n\nHow to run\n\n```sh\nexport OPENAI_API_KEY=\"...\"\nskyagi\n# or\nOPENAI_API_KEY=\"...\" skyagi\n```\n\nFor example if the OpenAI key is `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`, then the exact command would be the following\n\n```sh\n# make sure no quote around the token\nexport OPENAI_API_KEY=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\nskyagi\n# or\nOPENAI_API_KEY=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 skyagi\n```\n\nTo use example agent configs, download it from here: https:\u002F\u002Fgithub.com\u002Flitanlitudan\u002Fskyagi\u002Ftree\u002Fmain\u002Fexamples\n(pip install doesn't contain the agent configuration)\n\nAn example agent configuration (Sheldon) looks something like this:\n\n```json\n{\n    \"name\": \"Sheldon\",\n    \"age\": 27,\n    \"personality\": \"Intelligent, rigid, socially challenged, quirky, and arrogant.\",\n    \"memories\": [\n        \"Sheldon is a theoretical physicist who works at Caltech.\",\n        \"Sheldon has an eidetic memory and is highly intelligent, but struggles with social skills and sarcasm.\",\n        ...\n        \"Knock, knock, knock, Penny - This is the specific knock that Sheldon uses when he visits Penny's apartment, which he repeats three times.\",\n        \"Bazinga! - This is Sheldon's catchphrase that he uses to indicate he was joking or playing a prank on someone.\"\n    ],\n    \"current_status\": \"Sheldon is at the Cheesecake Factory\"\n}\n```\n\n## Interesting observations in this demo\n\nHere is a screenshot of a live demo using The Big Bang Theory example.\n![demo](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Flitanlitudan_skyagi_readme_15894ac76e94.png)\nFrom the conversation, we can observe three interesting points that have not been widely seen in previous systems:\n\n1. Leonard remembered that Penny had asked him to persuade Sheldon to go for a hike, which shows the capability of some kind of memory.\n2. Leonard changed his mind after Sheldon whispered to him and even tried to convince Penny to join the scientific effort, which shows that the agents had meaningful progress in the story even without human intervention.\n3. All the responses are quite human-like. As a user, it's quite hard to tell whether it's actually an AI behind the responses.\n\n## References\n\n1. https:\u002F\u002Farxiv.org\u002Fabs\u002F2304.03442\n2. https:\u002F\u002Fpython.langchain.com\u002Fen\u002Flatest\u002Fuse_cases\u002Fagent_simulations\u002Fcharacters.html#create-a-generative-character\n","# SkyAGI：大语言模型中新兴的人类行为模拟能力\n\nhttps:\u002F\u002Fgithub.com\u002Flitanlitudan\u002Fskyagi\u002Fassets\u002F4970420\u002Fa584b364-e659-476d-a884-932b3c04df61\n\n\u003Cp align=\"center\">\n    \u003Ca href=\"https:\u002F\u002Fpypi.org\u002Fproject\u002Fskyagi\u002F\">\n        \u003Cimg alt=\"PyPI\" src=\"https:\u002F\u002Fimg.shields.io\u002Fpypi\u002Fv\u002Fskyagi?color=gree\">\n    \u003C\u002Fa>\n\u003C\u002Fp>\n\n`SkyAGI` 是一个 Python 包，展示了大语言模型在模拟可信人类行为方面的新兴能力。\n具体来说，`SkyAGI` 实现了 [生成式智能体](https:\u002F\u002Farxiv.org\u002Fabs\u002F2304.03442) 的理念，并提供了一款角色扮演游戏，带来了非常有趣的用户体验。\n\n与以往基于 AI 的 NPC 系统不同，`SkyAGI` 的 NPC 能够生成非常逼真的人类回应。这一演示中的有趣观察表明，在 NPC 脚本编写等诸多方面，游戏开发有着巨大的重新思考潜力。\n\n为了展示这一点，`SkyAGI` 提供了来自《生活大爆炸》和《复仇者联盟》的示例角色作为起点。用户也可以通过创建类似 [customized_character.json](https:\u002F\u002Fgithub.com\u002Flitanlitudan\u002Fskyagi\u002Fblob\u002Fmain\u002Fexamples\u002Fexample_agent.json) 的配置文件来定义自定义角色。有关这些有趣观察的详细信息，请参阅 [观测部分](https:\u002F\u002Fgithub.com\u002Flitanlitudan\u002Fskyagi\u002F#interesting-observations-in-this-demo)。\n\n## 快速开始\n\n安装\n\n```sh\npip install --upgrade skyagi\n```\n\n或者\n\n```sh\nmake install\n```\n\n运行方法\n\n```sh\nexport OPENAI_API_KEY=\"...\"\nskyagi\n# 或\nOPENAI_API_KEY=\"...\" skyagi\n```\n\n例如，如果 OpenAI 密钥是 `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`，那么确切的命令如下：\n\n```sh\n# 确保令牌周围没有引号\nexport OPENAI_API_KEY=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\nskyagi\n# 或\nOPENAI_API_KEY=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 skyagi\n```\n\n要使用示例智能体配置，请从这里下载：https:\u002F\u002Fgithub.com\u002Flitanlitudan\u002Fskyagi\u002Ftree\u002Fmain\u002Fexamples\n（通过 pip 安装不会包含智能体配置）\n\n一个示例智能体配置（谢尔顿）大致如下：\n\n```json\n{\n    \"name\": \"Sheldon\",\n    \"age\": 27,\n    \"personality\": \"聪明、固执、社交困难、古怪且傲慢。\",\n    \"memories\": [\n        \"谢尔顿是一名在加州理工学院工作的理论物理学家。\",\n        \"谢尔顿拥有绝对记忆，智力超群，但社交能力和理解讽刺的能力较弱。\",\n        ...\n        \"敲敲敲，佩妮——这是谢尔顿拜访佩妮公寓时使用的特定敲门方式，他会重复三次。\",\n        \"巴津嘎！——这是谢尔顿用来表示自己在开玩笑或捉弄他人的口头禅。\"\n    ],\n    \"current_status\": \"谢尔顿正在芝士蛋糕工厂\"\n}\n```\n\n## 本演示中的有趣观察\n\n以下是使用《生活大爆炸》示例进行实时演示的截图：\n![demo](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Flitanlitudan_skyagi_readme_15894ac76e94.png)\n从这段对话中，我们可以观察到三个在以往系统中很少见的有趣点：\n\n1. 莱纳德记得佩妮曾让他劝说谢尔顿一起去徒步旅行，这表明系统具备某种记忆能力。\n2. 在谢尔顿低声对莱纳德耳语后，莱纳德改变了主意，甚至试图说服佩妮加入科学活动，这说明即使没有人类干预，智能体之间也能在故事情节中取得有意义的进展。\n3. 所有回应都相当贴近人类的表达方式。作为用户，很难判断这些回应背后是否真的是人工智能。\n\n## 参考文献\n\n1. https:\u002F\u002Farxiv.org\u002Fabs\u002F2304.03442\n2. https:\u002F\u002Fpython.langchain.com\u002Fen\u002Flatest\u002Fuse_cases\u002Fagent_simulations\u002Fcharacters.html#create-a-generative-character","# SkyAGI 快速上手指南\n\nSkyAGI 是一个基于大语言模型（LLM）的 Python 库，旨在模拟逼真的人类行为。它实现了“生成式智能体”（Generative Agents）的概念，能够创建具有记忆、个性并能自主推进剧情的角色扮演体验。\n\n## 环境准备\n\n在开始之前，请确保满足以下要求：\n\n*   **操作系统**：Linux、macOS 或 Windows\n*   **Python 版本**：建议 Python 3.8 及以上版本\n*   **依赖项**：需要有效的 OpenAI API Key\n*   **网络环境**：由于需要调用 OpenAI 服务，请确保网络通畅（如需加速，请自行配置代理或使用国内镜像中转服务）\n\n## 安装步骤\n\n可以通过 PyPI 直接安装最新版本的 SkyAGI：\n\n```sh\npip install --upgrade skyagi\n```\n\n或者，如果你克隆了源代码仓库，也可以使用 make 命令安装：\n\n```sh\nmake install\n```\n\n> **注意**：通过 `pip` 安装的包不包含示例角色配置文件。如需使用预设角色（如《生活大爆炸》或《复仇者联盟》中的角色），请从 GitHub 仓库下载 `examples` 目录：\n> https:\u002F\u002Fgithub.com\u002Flitanlitudan\u002Fskyagi\u002Ftree\u002Fmain\u002Fexamples\n\n## 基本使用\n\n### 1. 配置 API Key\n\n在使用前，需要设置环境变量 `OPENAI_API_KEY`。请确保密钥周围**没有引号**。\n\n**方式一：临时导出变量并运行**\n\n```sh\nexport OPENAI_API_KEY=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\nskyagi\n```\n\n**方式二：单行命令运行**\n\n```sh\nOPENAI_API_KEY=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 skyagi\n```\n\n*(请将上述命令中的示例密钥替换为你自己的真实 Key)*\n\n### 2. 自定义角色（可选）\n\n你可以创建 JSON 文件来定义独特的智能体角色。以下是一个基于 Sheldon 的配置示例：\n\n```json\n{\n    \"name\": \"Sheldon\",\n    \"age\": 27,\n    \"personality\": \"Intelligent, rigid, socially challenged, quirky, and arrogant.\",\n    \"memories\": [\n        \"Sheldon is a theoretical physicist who works at Caltech.\",\n        \"Sheldon has an eidetic memory and is highly intelligent, but struggles with social skills and sarcasm.\",\n        \"Knock, knock, knock, Penny - This is the specific knock that Sheldon uses when he visits Penny's apartment, which he repeats three times.\",\n        \"Bazinga! - This is Sheldon's catchphrase that he uses to indicate he was joking or playing a prank on someone.\"\n    ],\n    \"current_status\": \"Sheldon is at the Cheesecake Factory\"\n}\n```\n\n配置完成后，启动程序即可体验具备记忆能力和自主剧情推进能力的 AI 角色扮演游戏。","一家独立游戏工作室正在开发一款叙事驱动的 RPG 游戏，策划团队希望游戏中的 NPC 能像真人一样拥有记忆和自主社交能力，而不仅仅是重复预设台词。\n\n### 没有 skyagi 时\n- **对话僵硬死板**：NPC 只能根据固定的脚本树回复玩家，一旦玩家提问超出预设范围，角色就会答非所问或陷入循环，严重破坏沉浸感。\n- **缺乏记忆连贯性**：角色无法记住之前的互动细节（如玩家曾答应帮忙），每次对话都像初次见面，导致剧情逻辑断裂。\n- **剧情推进困难**：若想让 NPC 之间自发产生互动以推动支线剧情，开发者必须手动编写成千上万行复杂的触发脚本，工作量巨大且难以维护。\n- **个性千人一面**：不同角色的回复风格趋同，难以体现如“谢尔顿”般的独特性格特征（如特定的口头禅或社交障碍），角色缺乏灵魂。\n\n### 使用 skyagi 后\n- **拟人化自然交互**：skyagi 基于大模型生成的回复极具真实感，NPC 能理解语境并做出符合人类逻辑的反应，玩家几乎无法察觉背后是 AI。\n- **长效记忆机制**：角色自动存储并调用过往经历（如记得同伴的嘱托），能在后续对话中主动提及旧事，使故事发展连贯且富有深度。\n- **自主剧情演化**：无需人工干预，skyagi 驱动的角色间可自发协商甚至改变立场（如被说服加入科学实验），动态生成意想不到的精彩情节。\n- **鲜明性格定制**：通过简单的 JSON 配置即可定义角色的年龄、性格及背景记忆，skyagi 能精准还原特定人物的说话风格和行为习惯。\n\nskyagi 将游戏开发从繁琐的脚本编写中解放出来，让 NPC 真正拥有了“生命”，为下一代沉浸式游戏体验奠定了坚实基础。","https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Flitanlitudan_skyagi_b102d1ea.png","litanlitudan","Tan Li","https:\u002F\u002Foss.gittoolsai.com\u002Favatars\u002Flitanlitudan_6c69ee01.jpg","I crash drones","That Workshop","Palo Alto","hey@tanli.dev","tanli.dev","https:\u002F\u002Fgithub.com\u002Flitanlitudan",[85,89,93,97,101,105,109,113,116],{"name":86,"color":87,"percentage":88},"TypeScript","#3178c6",33.7,{"name":90,"color":91,"percentage":92},"Svelte","#ff3e00",33.4,{"name":94,"color":95,"percentage":96},"Python","#3572A5",20.6,{"name":98,"color":99,"percentage":100},"JavaScript","#f1e05a",8.1,{"name":102,"color":103,"percentage":104},"CSS","#663399",2.3,{"name":106,"color":107,"percentage":108},"Shell","#89e051",1.3,{"name":110,"color":111,"percentage":112},"PLpgSQL","#336790",0.3,{"name":114,"color":115,"percentage":112},"Makefile","#427819",{"name":117,"color":118,"percentage":119},"HTML","#e34c26",0.1,784,56,"2026-03-28T14:26:44","Apache-2.0","未说明",{"notes":126,"python":124,"dependencies":127},"该工具是一个 Python 包，主要通过调用 OpenAI API 运行，因此必须配置有效的 OPENAI_API_KEY 环境变量。README 中未提及本地 GPU、特定显存或 CUDA 版本需求，推测计算负载主要由云端 API 承担。示例角色配置文件不包含在 pip 安装包中，需单独从 GitHub 下载。",[67,128],"openai",[26,15,13],[131,132,133,134,135],"aigc","langchain","language-model","llm","ai-agent",null,"2026-03-27T02:49:30.150509","2026-04-06T14:05:08.656731",[140,145,150,155,160,165],{"id":141,"question_zh":142,"answer_zh":143,"source_url":144},19121,"如何修复因 config.json 不存在导致的启动报错？","该问题已在后续更新中通过遵循 XDG 规范解决。建议新用户运行 `skyagi config --help` 命令来查看配置帮助或生成配置文件，这能确保 CLI 正常工作。","https:\u002F\u002Fgithub.com\u002Flitanlitudan\u002Fskyagi\u002Fissues\u002F82",{"id":146,"question_zh":147,"answer_zh":148,"source_url":149},19122,"SkyAGI 是否支持作为服务部署（skyagi-as-a-service）？","是的，SkyAGI 的 WebSocket API 已经基于 langchain-serve 构建。您可以参考 skyagi-api 目录下的说明文档进行部署，它支持本地到云端的快速部署及自动扩缩容。","https:\u002F\u002Fgithub.com\u002Flitanlitudan\u002Fskyagi\u002Fissues\u002F54",{"id":151,"question_zh":152,"answer_zh":153,"source_url":154},19123,"遇到 'LiveError: Only one live display may be active at once' 错误如何解决？","这是一个已知的 rich 库显示冲突问题。维护者已发布补丁版本（patch release）修复此问题，请尝试升级 SkyAGI 到最新版本。如果问题依旧，可关注相关的 PR #64 获取更彻底的修复方案。","https:\u002F\u002Fgithub.com\u002Flitanlitudan\u002Fskyagi\u002Fissues\u002F56",{"id":156,"question_zh":157,"answer_zh":158,"source_url":159},19124,"如何在本地调试 SkyAGI 代码（例如使用 VSCode 或 pdb）？","您可以使用 Python 内置的调试器 pdb 来设置断点进行调试。虽然项目暂无专门的 VSCode 调试教程，但可以通过标准 Python 调试流程运行源码。对于需要降低 API 请求频率以适配免费账户的情况，可以直接修改源代码添加 sleep 延时，并通过 `python -m` 方式运行相关模块进行测试。","https:\u002F\u002Fgithub.com\u002Flitanlitudan\u002Fskyagi\u002Fissues\u002F66",{"id":161,"question_zh":162,"answer_zh":163,"source_url":164},19125,"发现 README 文档中有拼写错误怎么办？","欢迎直接提交 Issue 指出错误。维护者会迅速响应并合并修复 PR。所有关于文档的反馈都受到鼓励，以帮助改进项目文档质量。","https:\u002F\u002Fgithub.com\u002Flitanlitudan\u002Fskyagi\u002Fissues\u002F45",{"id":166,"question_zh":167,"answer_zh":168,"source_url":149},19126,"SkyAGI CLI 是什么类型的框架？","SkyAGI CLI 是一个纯 Python 编写的框架。用户可以通过命令行界面轻松测试 API 并专注于对话逻辑，无需处理复杂的底层路由配置。",[170,175,180,185,190,195,200,205,210,215,220,225,230,235,240,245,250,255,260,265],{"id":171,"version":172,"summary_zh":173,"released_at":174},117135,"0.0.30","## 变更内容\n* 由 @serenaqiaoo 在 https:\u002F\u002Fgithub.com\u002Flitanlitudan\u002Fskyagi\u002Fpull\u002F81 中为新 UI 清理前端代码\n* [Web] 由 @law-liet 在 https:\u002F\u002Fgithub.com\u002Flitanlitudan\u002Fskyagi\u002Fpull\u002F85 中创建代理数据表单\n* [api] 由 @qizheng7 在 https:\u002F\u002Fgithub.com\u002Flitanlitudan\u002Fskyagi\u002Fpull\u002F91 中实现发送对话消息功能，并添加几个端点占位符\n* [web] 由 @PandaKunQiao 在 https:\u002F\u002Fgithub.com\u002Flitanlitudan\u002Fskyagi\u002Fpull\u002F90 中创建对话房间\n* [api] 由 @qizheng7 在 https:\u002F\u002Fgithub.com\u002Flitanlitudan\u002Fskyagi\u002Fpull\u002F94 中添加更多端点\n* [api] 由 @qizheng7 在 https:\u002F\u002Fgithub.com\u002Flitanlitudan\u002Fskyagi\u002Fpull\u002F95 中实现获取代理端点\n* [api] 由 @qizheng7 在 https:\u002F\u002Fgithub.com\u002Flitanlitudan\u002Fskyagi\u002Fpull\u002F97 中添加获取对话相关端点\n* [web] 由 @PandaKunQiao 在 https:\u002F\u002Fgithub.com\u002Flitanlitudan\u002Fskyagi\u002Fpull\u002F98 中为 room-new 添加搜索功能并进行清理\n* [tools] 由 @litanlitudan 在 https:\u002F\u002Fgithub.com\u002Flitanlitudan\u002Fskyagi\u002Fpull\u002F103 中初始化社区分析工具\n\n## 新贡献者\n* @PandaKunQiao 在 https:\u002F\u002Fgithub.com\u002Flitanlitudan\u002Fskyagi\u002Fpull\u002F90 中完成了首次贡献\n\n**完整变更日志**: https:\u002F\u002Fgithub.com\u002Flitanlitudan\u002Fskyagi\u002Fcompare\u002F0.0.29...0.0.30","2023-06-05T01:30:21",{"id":176,"version":177,"summary_zh":178,"released_at":179},117136,"0.0.29","## 变更内容\n* [api] 由 @qizheng7 在 https:\u002F\u002Fgithub.com\u002Flitanlitudan\u002Fskyagi\u002Fpull\u002F76 中更新了 API 的 README 和示例\n* [Web UI] 由 @law-liet 在 https:\u002F\u002Fgithub.com\u002Flitanlitudan\u002Fskyagi\u002Fpull\u002F77 中添加了角色仪表盘\n* [config] 由 @tonyz0x0 在 https:\u002F\u002Fgithub.com\u002Flitanlitudan\u002Fskyagi\u002Fpull\u002F75 中进行了模型配置\n* [readme] 由 @litanlitudan 在 https:\u002F\u002Fgithub.com\u002Flitanlitudan\u002Fskyagi\u002Fpull\u002F68 中添加了介绍视频\n* [readme] 由 @litanlitudan 在 https:\u002F\u002Fgithub.com\u002Flitanlitudan\u002Fskyagi\u002Fpull\u002F80 中修复了拼写错误\n* [cli] 由 @qizheng7 在 https:\u002F\u002Fgithub.com\u002Flitanlitudan\u002Fskyagi\u002Fpull\u002F83 中修复了 CLI 的拼写错误\n* [cli] 由 @qizheng7 在 https:\u002F\u002Fgithub.com\u002Flitanlitudan\u002Fskyagi\u002Fpull\u002F84 中支持不使用配置文件\n\n\n**完整变更日志**: https:\u002F\u002Fgithub.com\u002Flitanlitudan\u002Fskyagi\u002Fcompare\u002F0.0.28...0.0.29","2023-05-24T18:06:02",{"id":181,"version":182,"summary_zh":183,"released_at":184},117137,"0.0.28","## 变更内容\n* [readme] 增加由 @law-liet 在 https:\u002F\u002Fgithub.com\u002Flitanlitudan\u002Fskyagi\u002Fpull\u002F74 中提出的另一种安装方式\n* [UI] 首页基础布局由 @serenaqiaoo 在 https:\u002F\u002Fgithub.com\u002Flitanlitudan\u002Fskyagi\u002Fpull\u002F72 中完成\n* [api] 引入 skyagi REST API，由 @qizheng7 在 https:\u002F\u002Fgithub.com\u002Flitanlitudan\u002Fskyagi\u002Fpull\u002F73 中实现\n\n## 新贡献者\n* @law-liet 在 https:\u002F\u002Fgithub.com\u002Flitanlitudan\u002Fskyagi\u002Fpull\u002F74 中完成了首次贡献\n\n**完整变更日志**: https:\u002F\u002Fgithub.com\u002Flitanlitudan\u002Fskyagi\u002Fcompare\u002F0.0.27...0.0.28","2023-05-08T16:07:55",{"id":186,"version":187,"summary_zh":188,"released_at":189},117138,"0.0.27","## 变更内容\n* [cli] 锁定到最新的 LangChain 版本，并修复了由 @qizheng7 在 https:\u002F\u002Fgithub.com\u002Flitanlitudan\u002Fskyagi\u002Fpull\u002F63 中提出的使用最新 LangChain 的改动。\n* [ci] 修复 issue-56 “LiveError: 同一时间只能有一个活动的实时显示”问题，通过避免嵌套使用 rich.live 来实现，由 @qizheng7 在 https:\u002F\u002Fgithub.com\u002Flitanlitudan\u002Fskyagi\u002Fpull\u002F64 中完成。\n* [supabase] 设置认证框架，由 @serenaqiaoo 在 https:\u002F\u002Fgithub.com\u002Flitanlitudan\u002Fskyagi\u002Fpull\u002F67 中完成。\n* [cli] console.status() 不支持将样式作为参数传递，由 @qizheng7 在 https:\u002F\u002Fgithub.com\u002Flitanlitudan\u002Fskyagi\u002Fpull\u002F70 中提出并修复。\n* [simulation] 重构 talks_to 函数，使其使用生成式智能体模型，由 @tonyz0x0 在 https:\u002F\u002Fgithub.com\u002Flitanlitudan\u002Fskyagi\u002Fpull\u002F69 中完成。\n\n## 新贡献者\n* @qizheng7 在 https:\u002F\u002Fgithub.com\u002Flitanlitudan\u002Fskyagi\u002Fpull\u002F63 中完成了首次贡献。\n* @serenaqiaoo 在 https:\u002F\u002Fgithub.com\u002Flitanlitudan\u002Fskyagi\u002Fpull\u002F67 中完成了首次贡献。\n* @tonyz0x0 在 https:\u002F\u002Fgithub.com\u002Flitanlitudan\u002Fskyagi\u002Fpull\u002F69 中完成了首次贡献。\n\n**完整变更日志**: https:\u002F\u002Fgithub.com\u002Flitanlitudan\u002Fskyagi\u002Fcompare\u002F0.0.26...0.0.27","2023-05-05T18:13:49",{"id":191,"version":192,"summary_zh":193,"released_at":194},117139,"0.0.26","## 变更内容\n* [cicd] 修复 Python 包构建，由 litanlitudan 在 https:\u002F\u002Fgithub.com\u002Flitanlitudan\u002Fskyagi\u002Fpull\u002F62 中完成\n\n\n**完整变更日志**: https:\u002F\u002Fgithub.com\u002Flitanlitudan\u002Fskyagi\u002Fcompare\u002F0.0.25...0.0.26","2023-04-30T23:39:33",{"id":196,"version":197,"summary_zh":198,"released_at":199},117140,"0.0.25","## 变更内容\n* [杂项] 重构代码库，以支持 Web 界面，由 litanlitudan 在 https:\u002F\u002Fgithub.com\u002Flitanlitudan\u002Fskyagi\u002Fpull\u002F61 中完成\n\n\n**完整变更日志**: https:\u002F\u002Fgithub.com\u002Flitanlitudan\u002Fskyagi\u002Fcompare\u002F0.0.24...0.0.25","2023-04-30T23:32:53",{"id":201,"version":202,"summary_zh":203,"released_at":204},117141,"0.0.24","## 变更内容\n* [杂项] 由 @eltociear 在 https:\u002F\u002Fgithub.com\u002Flitanlitudan\u002Fskyagi\u002Fpull\u002F58 中修复了 skyagi.py 中的拼写错误\n* [Web] 由 @litanlitudan 在 https:\u002F\u002Fgithub.com\u002Flitanlitudan\u002Fskyagi\u002Fpull\u002F59 中搭建了 SvelteKit 脚手架\n* [Vercel] 由 @litanlitudan 在 https:\u002F\u002Fgithub.com\u002Flitanlitudan\u002Fskyagi\u002Fpull\u002F60 中配置了分析工具\n\n## 新贡献者\n* @eltociear 在 https:\u002F\u002Fgithub.com\u002Flitanlitudan\u002Fskyagi\u002Fpull\u002F58 中完成了首次贡献\n\n**完整变更日志**: https:\u002F\u002Fgithub.com\u002Flitanlitudan\u002Fskyagi\u002Fcompare\u002F0.0.23...0.0.24","2023-04-30T23:17:32",{"id":206,"version":207,"summary_zh":208,"released_at":209},117142,"0.0.23","## 变更内容\n* [readme] 调整背景图片大小，由 @litanlitudan 在 https:\u002F\u002Fgithub.com\u002Flitanlitudan\u002Fskyagi\u002Fpull\u002F51 中完成\n* [readme] 优化文案，由 @litanlitudan 在 https:\u002F\u002Fgithub.com\u002Flitanlitudan\u002Fskyagi\u002Fpull\u002F53 中完成\n* [readme] 修正拼写和语法错误，由 @xuemingdg 在 https:\u002F\u002Fgithub.com\u002Flitanlitudan\u002Fskyagi\u002Fpull\u002F55 中完成\n* [cli] 避免因 OpenAI 连接不良导致程序崩溃，由 @litanlitudan 在 https:\u002F\u002Fgithub.com\u002Flitanlitudan\u002Fskyagi\u002Fpull\u002F57 中完成\n\n## 新贡献者\n* @xuemingdg 在 https:\u002F\u002Fgithub.com\u002Flitanlitudan\u002Fskyagi\u002Fpull\u002F55 中完成了首次贡献\n\n**完整变更日志**: https:\u002F\u002Fgithub.com\u002Flitanlitudan\u002Fskyagi\u002Fcompare\u002F0.0.22...0.0.23","2023-04-28T23:23:17",{"id":211,"version":212,"summary_zh":213,"released_at":214},117143,"0.0.22","## 变更内容\n* [tui] 由 @litanlitudan 在 https:\u002F\u002Fgithub.com\u002Flitanlitudan\u002Fskyagi\u002Fpull\u002F50 中添加加载进度\n\n\n**完整变更日志**: https:\u002F\u002Fgithub.com\u002Flitanlitudan\u002Fskyagi\u002Fcompare\u002F0.0.21...0.0.22","2023-04-25T02:14:19",{"id":216,"version":217,"summary_zh":218,"released_at":219},117144,"0.0.21","## 变更内容\n* [cli] 更新名称选择提示，由 @litanlitudan 在 https:\u002F\u002Fgithub.com\u002Flitanlitudan\u002Fskyagi\u002Fpull\u002F49 中完成\n\n\n**完整变更日志**: https:\u002F\u002Fgithub.com\u002Flitanlitudan\u002Fskyagi\u002Fcompare\u002F0.0.20...0.0.21","2023-04-25T00:39:40",{"id":221,"version":222,"summary_zh":223,"released_at":224},117145,"0.0.20","## What's Changed\n* [examples] format json files by @litanlitudan in https:\u002F\u002Fgithub.com\u002Flitanlitudan\u002Fskyagi\u002Fpull\u002F43\n* [readme] update readme by @litanlitudan in https:\u002F\u002Fgithub.com\u002Flitanlitudan\u002Fskyagi\u002Fpull\u002F44\n* [readme] update title by @litanlitudan in https:\u002F\u002Fgithub.com\u002Flitanlitudan\u002Fskyagi\u002Fpull\u002F46\n* [readme] update config example by @litanlitudan in https:\u002F\u002Fgithub.com\u002Flitanlitudan\u002Fskyagi\u002Fpull\u002F47\n* [readme] typo fix by @litanlitudan in https:\u002F\u002Fgithub.com\u002Flitanlitudan\u002Fskyagi\u002Fpull\u002F48\n\n\n**Full Changelog**: https:\u002F\u002Fgithub.com\u002Flitanlitudan\u002Fskyagi\u002Fcompare\u002F0.0.19...0.0.20","2023-04-25T00:27:15",{"id":226,"version":227,"summary_zh":228,"released_at":229},117146,"0.0.19","## What's Changed\n* [examples] remove legacy examples by @litanlitudan in https:\u002F\u002Fgithub.com\u002Flitanlitudan\u002Fskyagi\u002Fpull\u002F31\n* [license] add apache2.0 by @litanlitudan in https:\u002F\u002Fgithub.com\u002Flitanlitudan\u002Fskyagi\u002Fpull\u002F32\n* adding example json file by @yuyuan223 in https:\u002F\u002Fgithub.com\u002Flitanlitudan\u002Fskyagi\u002Fpull\u002F33\n* Add files via upload by @solstice-stone in https:\u002F\u002Fgithub.com\u002Flitanlitudan\u002Fskyagi\u002Fpull\u002F34\n* [example] restructure examples by @litanlitudan in https:\u002F\u002Fgithub.com\u002Flitanlitudan\u002Fskyagi\u002Fpull\u002F35\n* [readme] update readme instruction by @litanlitudan in https:\u002F\u002Fgithub.com\u002Flitanlitudan\u002Fskyagi\u002Fpull\u002F36\n* [readme] update env instruction by @litanlitudan in https:\u002F\u002Fgithub.com\u002Flitanlitudan\u002Fskyagi\u002Fpull\u002F37\n* [readme] update instructions by @litanlitudan in https:\u002F\u002Fgithub.com\u002Flitanlitudan\u002Fskyagi\u002Fpull\u002F38\n* [readme] update the intro by @litanlitudan in https:\u002F\u002Fgithub.com\u002Flitanlitudan\u002Fskyagi\u002Fpull\u002F39\n* [readme] update observations by @litanlitudan in https:\u002F\u002Fgithub.com\u002Flitanlitudan\u002Fskyagi\u002Fpull\u002F40\n* [cli] at least two agents by @litanlitudan in https:\u002F\u002Fgithub.com\u002Flitanlitudan\u002Fskyagi\u002Fpull\u002F42\n\n## New Contributors\n* @yuyuan223 made their first contribution in https:\u002F\u002Fgithub.com\u002Flitanlitudan\u002Fskyagi\u002Fpull\u002F33\n* @solstice-stone made their first contribution in https:\u002F\u002Fgithub.com\u002Flitanlitudan\u002Fskyagi\u002Fpull\u002F34\n\n**Full Changelog**: https:\u002F\u002Fgithub.com\u002Flitanlitudan\u002Fskyagi\u002Fcompare\u002F0.0.18...0.0.19","2023-04-24T09:12:21",{"id":231,"version":232,"summary_zh":233,"released_at":234},117147,"0.0.18","## What's Changed\n* [pypi] setup linting by @litanlitudan in https:\u002F\u002Fgithub.com\u002Flitanlitudan\u002Fskyagi\u002Fpull\u002F29\n* [agent] enable user stop the conversation by @litanlitudan in https:\u002F\u002Fgithub.com\u002Flitanlitudan\u002Fskyagi\u002Fpull\u002F30\n\n\n**Full Changelog**: https:\u002F\u002Fgithub.com\u002Flitanlitudan\u002Fskyagi\u002Fcompare\u002F0.0.17...0.0.18","2023-04-23T09:19:31",{"id":236,"version":237,"summary_zh":238,"released_at":239},117148,"0.0.17","## What's Changed\n* [app] add readme background by @litanlitudan in https:\u002F\u002Fgithub.com\u002Flitanlitudan\u002Fskyagi\u002Fpull\u002F27\n* [pip] remove unnecessary packages by @litanlitudan in https:\u002F\u002Fgithub.com\u002Flitanlitudan\u002Fskyagi\u002Fpull\u002F28\n\n\n**Full Changelog**: https:\u002F\u002Fgithub.com\u002Flitanlitudan\u002Fskyagi\u002Fcompare\u002F0.0.16...0.0.17","2023-04-23T08:46:23",{"id":241,"version":242,"summary_zh":243,"released_at":244},117149,"0.0.16","## What's Changed\n* [doc] setup the documentation by @litanlitudan in https:\u002F\u002Fgithub.com\u002Flitanlitudan\u002Fskyagi\u002Fpull\u002F26\n\n\n**Full Changelog**: https:\u002F\u002Fgithub.com\u002Flitanlitudan\u002Fskyagi\u002Fcompare\u002F0.0.15...0.0.16","2023-04-23T07:34:37",{"id":246,"version":247,"summary_zh":248,"released_at":249},117150,"0.0.15","## What's Changed\n* [pip] update setup.cfg by @litanlitudan in https:\u002F\u002Fgithub.com\u002Flitanlitudan\u002Fskyagi\u002Fpull\u002F25\n\n\n**Full Changelog**: https:\u002F\u002Fgithub.com\u002Flitanlitudan\u002Fskyagi\u002Fcompare\u002F0.0.14...0.0.15","2023-04-22T00:28:34",{"id":251,"version":252,"summary_zh":253,"released_at":254},117151,"0.0.14","## What's Changed\n* [discord] setup discord bot by @litanlitudan in https:\u002F\u002Fgithub.com\u002Flitanlitudan\u002Fskyagi\u002Fpull\u002F24\n\n\n**Full Changelog**: https:\u002F\u002Fgithub.com\u002Flitanlitudan\u002Fskyagi\u002Fcompare\u002F0.0.13...0.0.14","2023-04-22T00:14:01",{"id":256,"version":257,"summary_zh":258,"released_at":259},117152,"0.0.13","## What's Changed\n* [pip] fix by @litanlitudan in https:\u002F\u002Fgithub.com\u002Flitanlitudan\u002Fskyagi\u002Fpull\u002F23\n\n\n**Full Changelog**: https:\u002F\u002Fgithub.com\u002Flitanlitudan\u002Fskyagi\u002Fcompare\u002F0.0.11...0.0.13","2023-04-21T11:20:45",{"id":261,"version":262,"summary_zh":263,"released_at":264},117153,"0.0.12","## What's Changed\n* [cli] fix submodule by @litanlitudan in https:\u002F\u002Fgithub.com\u002Flitanlitudan\u002Fskyagi\u002Fpull\u002F22\n\n\n**Full Changelog**: https:\u002F\u002Fgithub.com\u002Flitanlitudan\u002Fskyagi\u002Fcompare\u002F0.0.10...0.0.12","2023-04-21T11:13:21",{"id":266,"version":267,"summary_zh":268,"released_at":269},117154,"0.0.11","## What's Changed\n* [cli] fix submodule by @litanlitudan in https:\u002F\u002Fgithub.com\u002Flitanlitudan\u002Fskyagi\u002Fpull\u002F22\n\n\n**Full Changelog**: https:\u002F\u002Fgithub.com\u002Flitanlitudan\u002Fskyagi\u002Fcompare\u002F0.0.10...0.0.11","2023-04-21T11:11:00"]