[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"similar-fmaclen--hollama":3,"tool-fmaclen--hollama":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",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":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":80,"owner_email":79,"owner_twitter":75,"owner_website":81,"owner_url":82,"languages":83,"stars":106,"forks":107,"last_commit_at":108,"license":109,"difficulty_score":23,"env_os":110,"env_gpu":111,"env_ram":111,"env_deps":112,"category_tags":115,"github_topics":116,"view_count":23,"oss_zip_url":79,"oss_zip_packed_at":79,"status":16,"created_at":122,"updated_at":123,"faqs":124,"releases":155},2000,"fmaclen\u002Fhollama","hollama","A minimal LLM chat app that runs entirely in your browser","Hollama 是一个完全在浏览器中运行的轻量级大模型聊天应用，无需安装任何软件，打开网页即可使用。它支持连接 Ollama 和 OpenAI 等多个后端服务，让你自由选择模型，无论是文本生成还是图文理解都能应对。特别适合希望在本地隐私环境下使用 AI 的用户，所有对话数据都保存在你的浏览器中，可随时导入导出，无需注册或上传敏感内容。支持 Markdown 渲染、LaTeX 数学公式、代码高亮、多轮编辑与重试，还内置了代码编辑器和自定义系统提示功能，提升交互体验。你甚至可以直接在界面上下载 Ollama 模型，省去命令行操作。界面响应式设计，支持深色\u002F浅色主题和多语言，适合开发者、研究人员、技术爱好者，以及注重隐私的普通用户。无需服务器，不依赖云端，真正实现“开箱即用”的本地 AI 体验。","# Hollama\n\nA minimal LLM chat app that runs _entirely_ in your browser.\n\n### Features\n\n- Support for **Ollama** & **OpenAI** servers\n- Multi-server support\n- Text & vision models\n- Large prompt fields\n- Support for reasoning models\n- Markdown rendering with syntax highlighting\n- KaTeX math notation\n- Code editor features\n- Customizable system prompts & advanced Ollama parameters\n- Copy code snippets, messages or entire sessions\n- Edit & retry messages\n- Stores data locally on your browser\n- Import & export stored data\n- Responsive layout\n- Light & dark themes\n- Multi-language interface\n- Download [Ollama models](https:\u002F\u002Follama.ai\u002Fmodels) directly from the UI\n\n### Get started\n\n- ⚡️ [Live demo](https:\u002F\u002Fhollama.fernando.is)\n  - _No sign-up required_\n- 🖥️ Download for [macOS, Windows & Linux](https:\u002F\u002Fgithub.com\u002Ffmaclen\u002Fhollama\u002Freleases)\n- 🐳 [Self-hosting](SELF_HOSTING.md) with Docker\n- 🐞 [Contribute](CONTRIBUTING.md)\n\n| ![session](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Ffmaclen_hollama_readme_e37b0f3beb43.png)         | ![settings](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Ffmaclen_hollama_readme_fcc1044be184.png)   |\n| ------------------------------------------------------------ | -------------------------------------------------------- |\n| ![session-new](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Ffmaclen_hollama_readme_6acc9d139c8c.png) | ![knowledge](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Ffmaclen_hollama_readme_7a2a8efd753b.png) |\n","# Hollama\n\n一款完全在浏览器中运行的极简大型语言模型聊天应用。\n\n### 功能特点\n\n- 支持 **Ollama** 和 **OpenAI** 服务器\n- 多服务器支持\n- 文本与视觉模型\n- 大型提示字段\n- 支持推理模型\n- 带语法高亮的 Markdown 渲染\n- KaTeX 数学符号\n- 代码编辑器功能\n- 可自定义系统提示及高级 Ollama 参数\n- 复制代码片段、消息或整个会话\n- 编辑并重试消息\n- 数据本地存储于您的浏览器\n- 导入与导出已存储数据\n- 响应式布局\n- 浅色与深色主题\n- 多语言界面\n- 直接从界面下载 [Ollama 模型](https:\u002F\u002Follama.ai\u002Fmodels)\n\n### 开始使用\n\n- ⚡️ [实时演示](https:\u002F\u002Fhollama.fernando.is)\n  - _无需注册_\n- 🖥️ 下载适用于 [macOS、Windows 和 Linux](https:\u002F\u002Fgithub.com\u002Ffmaclen\u002Fhollama\u002Freleases)\n- 🐳 使用 Docker [自托管](SELF_HOSTING.md)\n- 🐞 [贡献](CONTRIBUTING.md)\n\n| ![session](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Ffmaclen_hollama_readme_e37b0f3beb43.png)         | ![settings](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Ffmaclen_hollama_readme_fcc1044be184.png)   |\n| ------------------------------------------------------------ | -------------------------------------------------------- |\n| ![session-new](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Ffmaclen_hollama_readme_6acc9d139c8c.png) | ![knowledge](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Ffmaclen_hollama_readme_7a2a8efd753b.png) |","# Hollama 快速上手指南\n\n## 环境准备\n\n- **系统要求**：支持 macOS、Windows、Linux，推荐现代浏览器（Chrome \u002F Edge \u002F Firefox）\n- **前置依赖**：无强制依赖，浏览器即可运行；如需本地推理，可安装 [Ollama](https:\u002F\u002Follama.ai)（支持 Linux\u002FmacOS）\n\n> 💡 国内用户可使用 [Ollama 镜像源](https:\u002F\u002Fmirrors.aliyun.com\u002Follama\u002F) 加速模型下载\n\n## 安装步骤\n\n### 方式一：在线使用（推荐快速体验）\n直接访问：[https:\u002F\u002Fhollama.fernando.is](https:\u002F\u002Fhollama.fernando.is)  \n无需注册，即开即用。\n\n### 方式二：下载桌面版\n前往 GitHub 发布页下载对应系统版本：  \n[https:\u002F\u002Fgithub.com\u002Ffmaclen\u002Fhollama\u002Freleases](https:\u002F\u002Fgithub.com\u002Ffmaclen\u002Fhollama\u002Freleases)\n\n### 方式三：Docker 自托管\n```bash\ndocker run -d -p 3000:3000 fmaclen\u002Fhollama\n```\n访问 `http:\u002F\u002Flocalhost:3000` 即可使用。\n\n## 基本使用\n\n1. 打开浏览器访问 [https:\u002F\u002Fhollama.fernando.is](https:\u002F\u002Fhollama.fernando.is)\n2. 在输入框中输入提示词，例如：\n   ```\n   用中文解释什么是大语言模型\n   ```\n3. 点击发送，模型将返回响应\n4. 可切换模型：点击左下角模型选择器，支持 Ollama 或 OpenAI 服务\n5. 支持上传图片进行视觉问答（Vision 模型）\n6. 代码块自动高亮，可点击复制按钮复制内容\n\n> 所有对话数据本地存储，支持导入\u002F导出 JSON 文件备份。","一位前端开发者在本地调试 AI 驱动的代码生成需求时，常需反复测试不同 LLM 的响应质量。使用前，他依赖多个网页端聊天平台，每次切换模型都要重新登录、复制粘贴上下文，且无法保存历史对话。遇到数学公式或代码片段时，排版混乱、无法高亮，调试效率极低。他想用 Ollama 运行本地的 Mistral 模型，却苦于没有轻量、离线可用的界面。\n\n使用后，他直接下载了 hollama，无需注册，一键启动。他添加了本地 Ollama 服务，选择 `mistral:7b-instruct` 模型，将系统提示词设为“你是一个严谨的 JavaScript 开发者，只输出可运行代码，不解释”。在大文本框中输入复杂需求：“写一个带防抖的搜索输入框，使用 React 18 和 TypeScript”，hollama 自动渲染出带语法高亮的完整代码，并正确显示 KaTeX 数学公式（如函数复杂度 O(n)）。他发现响应不够精准，直接编辑上一条消息，点击“重试”，模型立刻重新生成。整个会话自动保存在浏览器本地，他导出为 JSON 文件，第二天继续修改。当他想测试 Vision 模型时，只需拖入一张 UI 设计图，hollama 就能分析结构并生成对应代码。他甚至从 UI 直接下载了 `llava:13b` 模型，无需命令行。现在，他每天在离线状态下高效完成 5–8 次模型测试，不再依赖网络，也不再丢失上下文。","https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Ffmaclen_hollama_e37b0f3b.png","fmaclen","Fernando Maclen","https:\u002F\u002Foss.gittoolsai.com\u002Favatars\u002Ffmaclen_48a34a15.jpg","Design + Code",null,"Miami, FL","https:\u002F\u002Ffernando.is","https:\u002F\u002Fgithub.com\u002Ffmaclen",[84,88,92,95,99,103],{"name":85,"color":86,"percentage":87},"TypeScript","#3178c6",67.4,{"name":89,"color":90,"percentage":91},"Svelte","#ff3e00",29.3,{"name":93,"color":94,"percentage":23},"JavaScript","#f1e05a",{"name":96,"color":97,"percentage":98},"CSS","#663399",0.9,{"name":100,"color":101,"percentage":102},"HTML","#e34c26",0.2,{"name":104,"color":105,"percentage":102},"Dockerfile","#384d54",1118,87,"2026-04-05T19:36:34","MIT","Linux, macOS, Windows","未说明",{"notes":113,"python":111,"dependencies":114},"该工具完全在浏览器中运行，无需安装本地环境；模型由 Ollama 或 OpenAI 服务器提供，本地无需 GPU 或 Python 环境；可直接从 UI 下载 Ollama 模型，首次使用可能需下载模型文件（大小依模型而定）",[],[14,26,13,15],[117,118,119,120,121],"ai","chatbot","local-ai","ollama","llm","2026-03-27T02:49:30.150509","2026-04-06T08:18:25.508304",[125,130,135,140,145,150],{"id":126,"question_zh":127,"answer_zh":128,"source_url":129},9034,"复制按钮在 HTTP 环境下无效，如何解决？","在非安全上下文（如 HTTP）中，浏览器会阻止 navigator.clipboard.writeText。解决方案是使用备用方法：创建一个临时 textarea，选中内容并执行 document.execCommand('copy')。同时应提示用户当前环境不安全。代码示例：if (navigator.clipboard && window.isSecureContext) { navigator.clipboard.writeText(content); } else { const textArea = document.createElement('textarea'); textArea.value = content; document.body.appendChild(textArea); textArea.select(); document.execCommand('copy'); document.body.removeChild(textArea); }","https:\u002F\u002Fgithub.com\u002Ffmaclen\u002Fhollama\u002Fissues\u002F250",{"id":131,"question_zh":132,"answer_zh":133,"source_url":134},9035,"如何直接使用 llama.cpp 而不通过 ollama？","Hollama 已支持直接连接 llama.cpp 的本地 Web 服务器。只需确保 llama.cpp 启动了 OpenAI 兼容的 HTTP 端点（默认 localhost:11434），然后在 Hollama 中配置模型地址为该端点即可，无需依赖 ollama 服务。","https:\u002F\u002Fgithub.com\u002Ffmaclen\u002Fhollama\u002Fissues\u002F233",{"id":136,"question_zh":137,"answer_zh":138,"source_url":139},9036,"如何让模型正确渲染数学公式（如 KaTeX）？","Hollama 已集成数学解析器，可自动渲染 LaTeX 公式。升级到 v0.28.0 或更高版本后，系统会自动将类似 \\frac{\\partial g}{\\partial y} 的公式转换为可视化数学表达式，无需手动配置。","https:\u002F\u002Fgithub.com\u002Ffmaclen\u002Fhollama\u002Fissues\u002F263",{"id":141,"question_zh":142,"answer_zh":143,"source_url":144},9037,"如何将知识库内容作为系统提示词（system prompt）传递给模型？","在 v0.5.0 及以上版本中，可在知识库设置中启用「作为系统提示词」选项。启用后，知识库内容将被插入为 system 角色消息，而非用户消息前的 XML 块，从而避免模型混淆角色意图。","https:\u002F\u002Fgithub.com\u002Ffmaclen\u002Fhollama\u002Fissues\u002F100",{"id":146,"question_zh":147,"answer_zh":148,"source_url":149},9038,"对话上下文在多次交互后丢失，如何避免？","此问题在 v0.7.8 中已修复。建议升级到最新版本，并确保使用 Ollama 的 \u002Fapi\u002Fchat 端点而非旧接口。若仍出现上下文截断，可尝试减少单次对话长度，或启用上下文摘要功能（如后续版本支持）。","https:\u002F\u002Fgithub.com\u002Ffmaclen\u002Fhollama\u002Fissues\u002F103",{"id":151,"question_zh":152,"answer_zh":153,"source_url":154},9039,"多个会话同时响应时输出内容错乱，如何修复？","该问题已在后续版本中修复。修复方案是为每个会话独立绑定 HTTP 流响应，确保 chunked 数据仅写入对应会话的 UI 区域。请升级至最新版本以获得稳定多会话支持。","https:\u002F\u002Fgithub.com\u002Ffmaclen\u002Fhollama\u002Fissues\u002F126",[156,161,166,171,176,181,186,191,196,201,206,211,216,221,226,231,236,241,246,251],{"id":157,"version":158,"summary_zh":159,"released_at":160},116177,"0.35.4","## [0.35.4](https:\u002F\u002Fgithub.com\u002Ffmaclen\u002Fhollama\u002Fcompare\u002F0.35.3...0.35.4) (2025-10-12)\r\n\r\n> [!IMPORTANT]  \r\n> **This is a Docker-only release**.\r\n> The most current version of Hollama for macOS, Linux or Windows is [`0.35.1`](https:\u002F\u002Fgithub.com\u002Ffmaclen\u002Fhollama\u002Freleases\u002Ftag\u002F0.35.1)\r\n\r\n### Bug Fixes\r\n\r\n* port mapping for VITE after container update - 2 ([#336](https:\u002F\u002Fgithub.com\u002Ffmaclen\u002Fhollama\u002Fissues\u002F336)) ([db6a375](https:\u002F\u002Fgithub.com\u002Ffmaclen\u002Fhollama\u002Fcommit\u002Fdb6a375510e9dbb4cb9a2e5a15b841b3d919106f)), closes [#335](https:\u002F\u002Fgithub.com\u002Ffmaclen\u002Fhollama\u002Fissues\u002F335)\r\n\r\n\r\n\r\n","2025-10-12T02:14:55",{"id":162,"version":163,"summary_zh":164,"released_at":165},116178,"0.35.3","## [0.35.3](https:\u002F\u002Fgithub.com\u002Ffmaclen\u002Fhollama\u002Fcompare\u002F0.35.2...0.35.3) (2025-10-10)\r\n\r\n> [!IMPORTANT]  \r\n> **This is a Docker-only release**.\r\n> The most current version of Hollama for macOS, Linux or Windows is [`0.35.1`](https:\u002F\u002Fgithub.com\u002Ffmaclen\u002Fhollama\u002Freleases\u002Ftag\u002F0.35.1)\r\n\r\n### Bug Fixes\r\n\r\n* port mapping for VITE after container update ([#335](https:\u002F\u002Fgithub.com\u002Ffmaclen\u002Fhollama\u002Fissues\u002F335)) ([2077286](https:\u002F\u002Fgithub.com\u002Ffmaclen\u002Fhollama\u002Fcommit\u002F2077286a5d8d5d74b419c097a64bf3064595070a))\r\n\r\n\r\n\r\n","2025-10-10T19:13:10",{"id":167,"version":168,"summary_zh":169,"released_at":170},116179,"0.35.2","> [!IMPORTANT]  \r\n> **This is a Docker-only release**.\r\n> The most current version of Hollama for macOS, Linux or Windows is [`0.35.1`](https:\u002F\u002Fgithub.com\u002Ffmaclen\u002Fhollama\u002Freleases\u002Ftag\u002F0.35.1)\r\n\r\n## [0.35.2](https:\u002F\u002Fgithub.com\u002Ffmaclen\u002Fhollama\u002Fcompare\u002F0.35.1...0.35.2) (2025-10-09)\r\n\r\n\r\n### Bug Fixes\r\n\r\n* optimize docker image builds ([#334](https:\u002F\u002Fgithub.com\u002Ffmaclen\u002Fhollama\u002Fissues\u002F334)) ([26f4b64](https:\u002F\u002Fgithub.com\u002Ffmaclen\u002Fhollama\u002Fcommit\u002F26f4b643cee3bfa3d3fad420d7b4fecfd714f73d)), closes [#333](https:\u002F\u002Fgithub.com\u002Ffmaclen\u002Fhollama\u002Fissues\u002F333)\r\n\r\n\r\n\r\n","2025-10-09T15:42:37",{"id":172,"version":173,"summary_zh":174,"released_at":175},116180,"0.35.1","## [0.35.1](https:\u002F\u002Fgithub.com\u002Ffmaclen\u002Fhollama\u002Fcompare\u002F0.35.0...0.35.1) (2025-07-20)\n\n\n### Bug Fixes\n\n* trigger warning toast when localstorage is full ([#329](https:\u002F\u002Fgithub.com\u002Ffmaclen\u002Fhollama\u002Fissues\u002F329)) ([15cc272](https:\u002F\u002Fgithub.com\u002Ffmaclen\u002Fhollama\u002Fcommit\u002F15cc272e9971a171f73b30d58f1ac9313857e0e4)), closes [#318](https:\u002F\u002Fgithub.com\u002Ffmaclen\u002Fhollama\u002Fissues\u002F318)\n\n\n\n","2025-07-20T20:30:03",{"id":177,"version":178,"summary_zh":179,"released_at":180},116181,"0.35.0","# [0.35.0](https:\u002F\u002Fgithub.com\u002Ffmaclen\u002Fhollama\u002Fcompare\u002F0.34.0...0.35.0) (2025-07-02)\r\n\r\n\r\n### Features\r\n\r\n* add ability to submit images without prompts ([#326](https:\u002F\u002Fgithub.com\u002Ffmaclen\u002Fhollama\u002Fissues\u002F326)) ([b91c606](https:\u002F\u002Fgithub.com\u002Ffmaclen\u002Fhollama\u002Fcommit\u002Fb91c606d5ecd20f038db73568d2cab4fd9e7cc42)), closes [#325](https:\u002F\u002Fgithub.com\u002Ffmaclen\u002Fhollama\u002Fissues\u002F325)\r\n\r\n\r\n\r\n","2025-07-04T14:27:33",{"id":182,"version":183,"summary_zh":184,"released_at":185},116182,"0.34.0","# [0.34.0](https:\u002F\u002Fgithub.com\u002Ffmaclen\u002Fhollama\u002Fcompare\u002F0.33.0...0.34.0) (2025-06-09)\n\n\n### Features\n\n* copy and paste images ([#316](https:\u002F\u002Fgithub.com\u002Ffmaclen\u002Fhollama\u002Fissues\u002F316)) ([848155d](https:\u002F\u002Fgithub.com\u002Ffmaclen\u002Fhollama\u002Fcommit\u002F848155d2fc7c1ca8dc19d2769066ebf15b9683e9)), closes [#314](https:\u002F\u002Fgithub.com\u002Ffmaclen\u002Fhollama\u002Fissues\u002F314)\n* new collapsible sidebar ([#315](https:\u002F\u002Fgithub.com\u002Ffmaclen\u002Fhollama\u002Fissues\u002F315)) ([c6a4924](https:\u002F\u002Fgithub.com\u002Ffmaclen\u002Fhollama\u002Fcommit\u002Fc6a4924f61453c2732def73fe628907412bea457)), closes [#310](https:\u002F\u002Fgithub.com\u002Ffmaclen\u002Fhollama\u002Fissues\u002F310)\n* preserve partial responses when stopping completion ([#317](https:\u002F\u002Fgithub.com\u002Ffmaclen\u002Fhollama\u002Fissues\u002F317)) ([c59a136](https:\u002F\u002Fgithub.com\u002Ffmaclen\u002Fhollama\u002Fcommit\u002Fc59a1361a104e092a0f3f740bb58b57b95f3cc27)), closes [#297](https:\u002F\u002Fgithub.com\u002Ffmaclen\u002Fhollama\u002Fissues\u002F297)\n\n\n\n","2025-06-09T02:31:05",{"id":187,"version":188,"summary_zh":189,"released_at":190},116183,"0.33.0","# [0.33.0](https:\u002F\u002Fgithub.com\u002Ffmaclen\u002Fhollama\u002Fcompare\u002F0.32.2...0.33.0) (2025-05-14)\n\n\n### Features\n\n* it exports, imports and settings, sessions, knowledge ([#305](https:\u002F\u002Fgithub.com\u002Ffmaclen\u002Fhollama\u002Fissues\u002F305)) ([a5ed17a](https:\u002F\u002Fgithub.com\u002Ffmaclen\u002Fhollama\u002Fcommit\u002Fa5ed17a25775f67bc9f2882bce9502c2b7d65421)), closes [#162](https:\u002F\u002Fgithub.com\u002Ffmaclen\u002Fhollama\u002Fissues\u002F162)\n\n\n\n","2025-05-14T14:02:47",{"id":192,"version":193,"summary_zh":194,"released_at":195},116184,"0.32.2","## [0.32.2](https:\u002F\u002Fgithub.com\u002Ffmaclen\u002Fhollama\u002Fcompare\u002F0.32.1...0.32.2) (2025-05-09)\n\n\n### Bug Fixes\n\n* bump dependencies, improve the versioning and release workflows ([#301](https:\u002F\u002Fgithub.com\u002Ffmaclen\u002Fhollama\u002Fissues\u002F301)) ([47c1154](https:\u002F\u002Fgithub.com\u002Ffmaclen\u002Fhollama\u002Fcommit\u002F47c115447df5b4df1dfd51624be85012fa731437))\n* Reasoning is visible by default, auto-closes once the LLM completes the reasoning ([#293](https:\u002F\u002Fgithub.com\u002Ffmaclen\u002Fhollama\u002Fissues\u002F293)) ([1c7a664](https:\u002F\u002Fgithub.com\u002Ffmaclen\u002Fhollama\u002Fcommit\u002F1c7a664aa731e3389bd794ea1444f15e00624b18)), closes [#292](https:\u002F\u002Fgithub.com\u002Ffmaclen\u002Fhollama\u002Fissues\u002F292)\n* run the full versioning workflow ([87b7860](https:\u002F\u002Fgithub.com\u002Ffmaclen\u002Fhollama\u002Fcommit\u002F87b786016a71953be83f171f8a3378dfee17a093))\n\n\n\n","2025-05-09T20:39:31",{"id":197,"version":198,"summary_zh":199,"released_at":200},116185,"0.32.1","## [0.32.1](https:\u002F\u002Fgithub.com\u002Ffmaclen\u002Fhollama\u002Fcompare\u002F0.32.0...0.32.1) (2025-05-07)\n\n\n### Bug Fixes\n\n* ownership bug preventing docker container from running ([2396215](https:\u002F\u002Fgithub.com\u002Ffmaclen\u002Fhollama\u002Fcommit\u002F23962152a24e601df28390e3d4942298f30bff2e))\n\n\n\n","2025-05-07T01:53:08",{"id":202,"version":203,"summary_zh":204,"released_at":205},116186,"0.32.0","# [0.32.0](https:\u002F\u002Fgithub.com\u002Ffmaclen\u002Fhollama\u002Fcompare\u002F0.31.0...0.32.0) (2025-05-04)\n\n\n### Features\n\n* support for vision models (Ollama + OpenAI) ([#296](https:\u002F\u002Fgithub.com\u002Ffmaclen\u002Fhollama\u002Fissues\u002F296)) ([b2415f2](https:\u002F\u002Fgithub.com\u002Ffmaclen\u002Fhollama\u002Fcommit\u002Fb2415f24c890b09d7c545f806ebeff0df180f745)), closes [#230](https:\u002F\u002Fgithub.com\u002Ffmaclen\u002Fhollama\u002Fissues\u002F230) [#128](https:\u002F\u002Fgithub.com\u002Ffmaclen\u002Fhollama\u002Fissues\u002F128)\n\n\n\n","2025-05-04T20:46:47",{"id":207,"version":208,"summary_zh":209,"released_at":210},116187,"0.31.0","# [0.31.0](https:\u002F\u002Fgithub.com\u002Ffmaclen\u002Fhollama\u002Fcompare\u002F0.30.0...0.31.0) (2025-03-30)\n\n\n### Features\n\n* add support for `\u003Cthought>` reasoning tags ([#288](https:\u002F\u002Fgithub.com\u002Ffmaclen\u002Fhollama\u002Fissues\u002F288)) ([6c3f431](https:\u002F\u002Fgithub.com\u002Ffmaclen\u002Fhollama\u002Fcommit\u002F6c3f431732c2536591362b61ff83b33588bccfce))\n\n\n\n","2025-03-30T19:17:43",{"id":212,"version":213,"summary_zh":214,"released_at":215},116188,"0.30.0","# [0.30.0](https:\u002F\u002Fgithub.com\u002Ffmaclen\u002Fhollama\u002Fcompare\u002F0.29.0...0.30.0) (2025-03-24)\n\n\n### Features\n\n* edit session titles manually ([#284](https:\u002F\u002Fgithub.com\u002Ffmaclen\u002Fhollama\u002Fissues\u002F284)) ([0a1f8ce](https:\u002F\u002Fgithub.com\u002Ffmaclen\u002Fhollama\u002Fcommit\u002F0a1f8cefcafe352d9138b493915b60fcb738bf7f)), closes [#275](https:\u002F\u002Fgithub.com\u002Ffmaclen\u002Fhollama\u002Fissues\u002F275)\n\n\n\n","2025-03-24T17:37:36",{"id":217,"version":218,"summary_zh":219,"released_at":220},116189,"0.29.0","# [0.29.0](https:\u002F\u002Fgithub.com\u002Ffmaclen\u002Fhollama\u002Fcompare\u002F0.28.0...0.29.0) (2025-03-24)\n\n\n### Features\n\n* warn user before leaving behind an unsaved prompt ([#281](https:\u002F\u002Fgithub.com\u002Ffmaclen\u002Fhollama\u002Fissues\u002F281)) ([9c50137](https:\u002F\u002Fgithub.com\u002Ffmaclen\u002Fhollama\u002Fcommit\u002F9c50137e3e47b50c5ef4f5eff96c7759e24f21f5)), closes [#274](https:\u002F\u002Fgithub.com\u002Ffmaclen\u002Fhollama\u002Fissues\u002F274)\n\n\n\n","2025-03-24T14:54:52",{"id":222,"version":223,"summary_zh":224,"released_at":225},116190,"0.28.0","# [0.28.0](https:\u002F\u002Fgithub.com\u002Ffmaclen\u002Fhollama\u002Fcompare\u002F0.27.0...0.28.0) (2025-03-24)\n\n\n### Features\n\n* add support for math notation using katex ([#280](https:\u002F\u002Fgithub.com\u002Ffmaclen\u002Fhollama\u002Fissues\u002F280)) ([a38265b](https:\u002F\u002Fgithub.com\u002Ffmaclen\u002Fhollama\u002Fcommit\u002Fa38265bfcae277774f8a0b5fc310a6c107b6faea)), closes [#263](https:\u002F\u002Fgithub.com\u002Ffmaclen\u002Fhollama\u002Fissues\u002F263)\n\n\n\n","2025-03-24T14:10:12",{"id":227,"version":228,"summary_zh":229,"released_at":230},116191,"0.27.0","# [0.27.0](https:\u002F\u002Fgithub.com\u002Ffmaclen\u002Fhollama\u002Fcompare\u002F0.26.1...0.27.0) (2025-02-22)\n\n\n### Features\n\n* allow requests from specified hosts ([#271](https:\u002F\u002Fgithub.com\u002Ffmaclen\u002Fhollama\u002Fissues\u002F271)) ([84d365b](https:\u002F\u002Fgithub.com\u002Ffmaclen\u002Fhollama\u002Fcommit\u002F84d365b8d109269cb64127d3306900664652e5c7)), closes [#266](https:\u002F\u002Fgithub.com\u002Ffmaclen\u002Fhollama\u002Fissues\u002F266)\n\n\n\n","2025-02-22T18:49:03",{"id":232,"version":233,"summary_zh":234,"released_at":235},116192,"0.26.1","## [0.26.1](https:\u002F\u002Fgithub.com\u002Ffmaclen\u002Fhollama\u002Fcompare\u002F0.26.0...0.26.1) (2025-02-22)\n\n\n### Bug Fixes\n\n* Add .nvmrc to allow users to deploy on cloudflare pages ([#269](https:\u002F\u002Fgithub.com\u002Ffmaclen\u002Fhollama\u002Fissues\u002F269)) ([e18b6f3](https:\u002F\u002Fgithub.com\u002Ffmaclen\u002Fhollama\u002Fcommit\u002Fe18b6f3ef78bf22c0de5a111feb17734b103cd28))\n\n\n\n","2025-02-22T16:48:07",{"id":237,"version":238,"summary_zh":239,"released_at":240},116193,"0.26.0","# [0.26.0](https:\u002F\u002Fgithub.com\u002Ffmaclen\u002Fhollama\u002Fcompare\u002F0.25.1...0.26.0) (2025-02-12)\n\n\n### Features\n\n* add French language support ([#267](https:\u002F\u002Fgithub.com\u002Ffmaclen\u002Fhollama\u002Fissues\u002F267)) ([c9ef7b3](https:\u002F\u002Fgithub.com\u002Ffmaclen\u002Fhollama\u002Fcommit\u002Fc9ef7b31b3ab576818ec29620627dedaf6fcb163))\n\n\n\n","2025-02-12T14:08:52",{"id":242,"version":243,"summary_zh":244,"released_at":245},116194,"0.25.1","## [0.25.1](https:\u002F\u002Fgithub.com\u002Ffmaclen\u002Fhollama\u002Fcompare\u002F0.25.0...0.25.1) (2025-01-26)\n\n\n### Bug Fixes\n\n* update dependencies and Docker configuration ([#262](https:\u002F\u002Fgithub.com\u002Ffmaclen\u002Fhollama\u002Fissues\u002F262)) ([4b59bb8](https:\u002F\u002Fgithub.com\u002Ffmaclen\u002Fhollama\u002Fcommit\u002F4b59bb8dda9addeb95358a5c9b5ffacbe95b39a5)), closes [#259](https:\u002F\u002Fgithub.com\u002Ffmaclen\u002Fhollama\u002Fissues\u002F259)\n\n\n\n","2025-01-26T20:37:59",{"id":247,"version":248,"summary_zh":249,"released_at":250},116195,"0.25.0","# [0.25.0](https:\u002F\u002Fgithub.com\u002Ffmaclen\u002Fhollama\u002Fcompare\u002F0.24.0...0.25.0) (2025-01-26)\n\n\n### Features\n\n* add dedicated UI for reasoning model responses ([#261](https:\u002F\u002Fgithub.com\u002Ffmaclen\u002Fhollama\u002Fissues\u002F261)) ([bc50b03](https:\u002F\u002Fgithub.com\u002Ffmaclen\u002Fhollama\u002Fcommit\u002Fbc50b030ffac06a879c22b73be34b98929173b94))\n\n\n\n","2025-01-26T20:00:02",{"id":252,"version":253,"summary_zh":254,"released_at":255},116196,"0.24.0","# [0.24.0](https:\u002F\u002Fgithub.com\u002Ffmaclen\u002Fhollama\u002Fcompare\u002F0.23.2...0.24.0) (2024-12-19)\n\n\n### Features\n\n* copy content on insecure connections (HTTP) ([#251](https:\u002F\u002Fgithub.com\u002Ffmaclen\u002Fhollama\u002Fissues\u002F251)) ([a710a53](https:\u002F\u002Fgithub.com\u002Ffmaclen\u002Fhollama\u002Fcommit\u002Fa710a532efe4e0b15236c54ff3d0a1216b0425cc)), closes [#250](https:\u002F\u002Fgithub.com\u002Ffmaclen\u002Fhollama\u002Fissues\u002F250)\n\n\n\n","2024-12-19T20:56:52"]