[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"similar-janhq--jan":3,"tool-janhq--jan":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":124,"forks":125,"last_commit_at":126,"license":127,"difficulty_score":23,"env_os":128,"env_gpu":129,"env_ram":130,"env_deps":131,"category_tags":140,"github_topics":141,"view_count":150,"oss_zip_url":79,"oss_zip_packed_at":79,"status":16,"created_at":151,"updated_at":152,"faqs":153,"releases":183},631,"janhq\u002Fjan","jan","Jan is an open source alternative to ChatGPT that runs 100% offline on your computer.","Jan 是一款开源的本地 AI 聊天应用，作为 ChatGPT 的替代方案，它能在你的电脑上完全离线运行。这一设计核心解决了用户对数据隐私泄露的担忧，同时摆脱了对网络连接的依赖和云端服务的费用限制。\n\nJan 支持从 HuggingFace 下载并运行多种开源大模型，涵盖 Llama、Gemma、Qwen 等热门架构。除了本地部署，它也允许连接 OpenAI、Anthropic 等云端 API，实现混合使用。对于开发者而言，Jan 内置了 OpenAI 兼容的本地服务器接口，便于其他应用集成，同时还支持模型上下文协议（MCP）以增强智能体能力。\n\nJan 适合各类人群使用。注重隐私保护的普通用户可以享受安全的离线对话体验；开发者与研究人员则能利用其开源特性，自由定制助手或测试不同模型。跨平台的支持让它在 Windows、macOS 和 Linux 上都能流畅运行，是追求自主可控 AI 体验的理想选择。","# Jan - Open-source ChatGPT replacement\n\n\u003Cimg width=\"2048\" height=\"280\" alt=\"github jan banner\" src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fjanhq_jan_readme_81e27ec66522.png\" \u002F>\n\n\u003Cp align=\"center\">\n  \u003C!-- ALL-CONTRIBUTORS-BADGE:START - Do not remove or modify this section -->\n  \u003Cimg alt=\"GitHub commit activity\" src=\"https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fcommit-activity\u002Fm\u002Fjanhq\u002Fjan\"\u002F>\n  \u003Cimg alt=\"Github Last Commit\" src=\"https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002Fjanhq\u002Fjan\"\u002F>\n  \u003Cimg alt=\"Github Contributors\" src=\"https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fcontributors\u002Fjanhq\u002Fjan\"\u002F>\n  \u003Cimg alt=\"GitHub closed issues\" src=\"https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fissues-closed\u002Fjanhq\u002Fjan\"\u002F>\n  \u003Cimg alt=\"Discord\" src=\"https:\u002F\u002Fimg.shields.io\u002Fdiscord\u002F1107178041848909847?label=discord\"\u002F>\n\u003C\u002Fp>\n\n\u003Cp align=\"center\">\n  \u003Ca href=\"https:\u002F\u002Fjan.ai\u002Fdocs\u002Fdesktop\">Getting Started\u003C\u002Fa>\n  - \u003Ca href=\"https:\u002F\u002Fdiscord.gg\u002FExe46xPMbK\">Community\u003C\u002Fa>\n  - \u003Ca href=\"https:\u002F\u002Fjan.ai\u002Fchangelog\">Changelog\u003C\u002Fa>\n  - \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fissues\">Bug reports\u003C\u002Fa>\n\u003C\u002Fp>\n\nJan is bringing the best of open-source AI in an easy-to-use product. Download and run LLMs with **full control** and **privacy**.\n\n## Installation\n\n\u003Cp align=\"center\">\n  \u003Ctable>\n    \u003Ctr>\n      \u003C!-- Microsoft Store Badge -->\n      \u003Ctd align=\"center\" valign=\"middle\">\n        \u003Ca href=\"https:\u002F\u002Fapps.microsoft.com\u002Fdetail\u002Fxpdcnfn5cpzlqb\">\n          \u003Cimg height=\"60\"\n            width=\"200\"\n               alt=\"Get it from Microsoft Store\"\n               src=\"https:\u002F\u002Fget.microsoft.com\u002Fimages\u002Fen-us%20dark.svg\"\u002F>\n        \u003C\u002Fa>\n      \u003C\u002Ftd>\n      \u003C!-- Spacer -->\n      \u003Ctd width=\"20\">\u003C\u002Ftd>\n      \u003C!-- Flathub Official Badge -->\n      \u003Ctd align=\"center\" valign=\"middle\">\n        \u003Ca href=\"https:\u002F\u002Fflathub.org\u002Fapps\u002Fai.jan.Jan\">\n          \u003Cimg height=\"60\"\n            width=\"200\"\n               alt=\"Get it on Flathub\"\n               src=\"https:\u002F\u002Fflathub.org\u002Fassets\u002Fbadges\u002Fflathub-badge-en.svg\"\u002F>\n        \u003C\u002Fa>\n      \u003C\u002Ftd>\n    \u003C\u002Ftr>\n  \u003C\u002Ftable>\n\u003C\u002Fp>\n\nThe easiest way to get started is by downloading one of the following versions for your respective operating system:\n\n\u003Ctable>\n  \u003Ctr>\n    \u003Ctd>\u003Cb>Platform\u003C\u002Fb>\u003C\u002Ftd>\n    \u003Ctd>\u003Cb>Download\u003C\u002Fb>\u003C\u002Ftd>\n  \u003C\u002Ftr>\n  \u003Ctr>\n    \u003Ctd>\u003Cb>Windows\u003C\u002Fb>\u003C\u002Ftd>\n    \u003Ctd>\u003Ca href='https:\u002F\u002Fapp.jan.ai\u002Fdownload\u002Flatest\u002Fwin-x64'>jan.exe\u003C\u002Fa>\u003C\u002Ftd>\n  \u003C\u002Ftr>\n  \u003Ctr>\n    \u003Ctd>\u003Cb>macOS\u003C\u002Fb>\u003C\u002Ftd>\n    \u003Ctd>\u003Ca href='https:\u002F\u002Fapp.jan.ai\u002Fdownload\u002Flatest\u002Fmac-universal'>jan.dmg\u003C\u002Fa>\u003C\u002Ftd>\n  \u003C\u002Ftr>\n  \u003Ctr>\n    \u003Ctd>\u003Cb>Linux (deb)\u003C\u002Fb>\u003C\u002Ftd>\n    \u003Ctd>\u003Ca href='https:\u002F\u002Fapp.jan.ai\u002Fdownload\u002Flatest\u002Flinux-amd64-deb'>jan.deb\u003C\u002Fa>\u003C\u002Ftd>\n  \u003C\u002Ftr>\n  \u003Ctr>\n    \u003Ctd>\u003Cb>Linux (AppImage)\u003C\u002Fb>\u003C\u002Ftd>\n    \u003Ctd>\u003Ca href='https:\u002F\u002Fapp.jan.ai\u002Fdownload\u002Flatest\u002Flinux-amd64-appimage'>jan.AppImage\u003C\u002Fa>\u003C\u002Ftd>\n  \u003C\u002Ftr>\n  \u003Ctr>\n    \u003Ctd>\u003Cb>Linux (Arm64)\u003C\u002Fb>\u003C\u002Ftd>\n    \u003Ctd>\u003Ca href='https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fissues\u002F4543#issuecomment-3734911349'>How-to\u003C\u002Fa>\u003C\u002Ftd>\n  \u003C\u002Ftr>\n\u003C\u002Ftable>\n\n\nDownload from [jan.ai](https:\u002F\u002Fjan.ai\u002F) or [GitHub Releases](https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Freleases).\n\n## Features\n\n- **Local AI Models**: Download and run LLMs (Llama, Gemma, Qwen, GPT-oss etc.) from HuggingFace\n- **Cloud Integration**: Connect to GPT models via OpenAI, Claude models via Anthropic, Mistral, Groq, MiniMax, and others\n- **Custom Assistants**: Create specialized AI assistants for your tasks\n- **OpenAI-Compatible API**: Local server at `localhost:1337` for other applications\n- **Model Context Protocol**: MCP integration for agentic capabilities\n- **Privacy First**: Everything runs locally when you want it to\n\n## Build from Source\n\nFor those who enjoy the scenic route:\n\n### Prerequisites\n\n- Node.js ≥ 20.0.0\n- Yarn ≥ 4.5.3\n- Make ≥ 3.81\n- Rust (for Tauri)\n- (macOS Apple Silicon only) MetalToolchain `xcodebuild -downloadComponent MetalToolchain`\n\n### Run with Make\n\n```bash\ngit clone https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\ncd jan\nmake dev\n```\n\nThis handles everything: installs dependencies, builds core components, and launches the app.\n\n**Available make targets:**\n- `make dev` - Full development setup and launch\n- `make build` - Production build\n- `make test` - Run tests and linting\n- `make clean` - Delete everything and start fresh\n\n### Manual Commands\n\n```bash\nyarn install\nyarn build\nyarn dev\n```\n\n## System Requirements\n\n**Minimum specs for a decent experience:**\n\n- **macOS**: 13.6+ (8GB RAM for 3B models, 16GB for 7B, 32GB for 13B)\n- **Windows**: 10+ with GPU support for NVIDIA\u002FAMD\u002FIntel Arc\n- **Linux**: Most distributions work, GPU acceleration available\n\nFor detailed compatibility, check our [installation guides](https:\u002F\u002Fjan.ai\u002Fdocs\u002Fdesktop\u002Fmac).\n\n## Troubleshooting\n\nIf things go sideways:\n\n1. Check our [troubleshooting docs](https:\u002F\u002Fjan.ai\u002Fdocs\u002Fdesktop\u002Ftroubleshooting)\n2. Copy your error logs and system specs\n3. Ask for help in our [Discord](https:\u002F\u002Fdiscord.gg\u002FFTk2MvZwJH) `#🆘|jan-help` channel\n\n\n## Contributing\n\nContributions welcome. See [CONTRIBUTING.md](CONTRIBUTING.md) for the full spiel.\n\n## Links\n\n- [Documentation](https:\u002F\u002Fjan.ai\u002Fdocs) - The manual you should read\n- [API Reference](https:\u002F\u002Fjan.ai\u002Fapi-reference) - For the technically inclined\n- [Changelog](https:\u002F\u002Fjan.ai\u002Fchangelog) - What we broke and fixed\n- [Discord](https:\u002F\u002Fdiscord.gg\u002FFTk2MvZwJH) - Where the community lives\n\n## Contact\n\n- **Bugs**: [GitHub Issues](https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fissues)\n- **Business**: hello@jan.ai\n- **Jobs**: hr@jan.ai\n- **General Discussion**: [Discord](https:\u002F\u002Fdiscord.gg\u002FFTk2MvZwJH)\n\n## License\n\nApache 2.0 - Because sharing is caring.\n\n## Acknowledgements\n\nBuilt on the shoulders of giants:\n\n- [Llama.cpp](https:\u002F\u002Fgithub.com\u002Fggerganov\u002Fllama.cpp)\n- [Tauri](https:\u002F\u002Ftauri.app\u002F)\n- [Scalar](https:\u002F\u002Fgithub.com\u002Fscalar\u002Fscalar)\n","# Jan - 开源 ChatGPT 替代品\n\n\u003Cimg width=\"2048\" height=\"280\" alt=\"github jan banner\" src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fjanhq_jan_readme_81e27ec66522.png\" \u002F>\n\n\u003Cp align=\"center\">\n  \u003C!-- ALL-CONTRIBUTORS-BADGE:START - Do not remove or modify this section -->\n  \u003Cimg alt=\"GitHub commit activity\" src=\"https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fcommit-activity\u002Fm\u002Fjanhq\u002Fjan\"\u002F>\n  \u003Cimg alt=\"Github Last Commit\" src=\"https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002Fjanhq\u002Fjan\"\u002F>\n  \u003Cimg alt=\"Github Contributors\" src=\"https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fcontributors\u002Fjanhq\u002Fjan\"\u002F>\n  \u003Cimg alt=\"GitHub closed issues\" src=\"https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fissues-closed\u002Fjanhq\u002Fjan\"\u002F>\n  \u003Cimg alt=\"Discord\" src=\"https:\u002F\u002Fimg.shields.io\u002Fdiscord\u002F1107178041848909847?label=discord\"\u002F>\n\u003C\u002Fp>\n\n\u003Cp align=\"center\">\n  \u003Ca href=\"https:\u002F\u002Fjan.ai\u002Fdocs\u002Fdesktop\">入门指南\u003C\u002Fa>\n  - \u003Ca href=\"https:\u002F\u002Fdiscord.gg\u002FExe46xPMbK\">社区\u003C\u002Fa>\n  - \u003Ca href=\"https:\u002F\u002Fjan.ai\u002Fchangelog\">更新日志\u003C\u002Fa>\n  - \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fissues\">问题反馈\u003C\u002Fa>\n\u003C\u002Fp>\n\nJan 致力于将最优秀的开源 AI 整合进一款易于使用的产品中。下载并运行**大语言模型 (LLMs)**，实现**完全控制**与**隐私保护**。\n\n## 安装\n\n\u003Cp align=\"center\">\n  \u003Ctable>\n    \u003Ctr>\n      \u003C!-- Microsoft Store Badge -->\n      \u003Ctd align=\"center\" valign=\"middle\">\n        \u003Ca href=\"https:\u002F\u002Fapps.microsoft.com\u002Fdetail\u002Fxpdcnfn5cpzlqb\">\n          \u003Cimg height=\"60\"\n            width=\"200\"\n               alt=\"从 Microsoft Store 获取\"\n               src=\"https:\u002F\u002Fget.microsoft.com\u002Fimages\u002Fen-us%20dark.svg\"\u002F>\n        \u003C\u002Fa>\n      \u003C\u002Ftd>\n      \u003C!-- Spacer -->\n      \u003Ctd width=\"20\">\u003C\u002Ftd>\n      \u003C!-- Flathub Official Badge -->\n      \u003Ctd align=\"center\" valign=\"middle\">\n        \u003Ca href=\"https:\u002F\u002Fflathub.org\u002Fapps\u002Fai.jan.Jan\">\n          \u003Cimg height=\"60\"\n            width=\"200\"\n               alt=\"在 Flathub 上获取\"\n               src=\"https:\u002F\u002Fflathub.org\u002Fassets\u002Fbadges\u002Fflathub-badge-en.svg\"\u002F>\n        \u003C\u002Fa>\n      \u003C\u002Ftd>\n    \u003C\u002Ftr>\n  \u003C\u002Ftable>\n\u003C\u002Fp>\n\n开始使用最简单的方法是下载适用于您操作系统的以下版本之一：\n\n\u003Ctable>\n  \u003Ctr>\n    \u003Ctd>\u003Cb>平台\u003C\u002Fb>\u003C\u002Ftd>\n    \u003Ctd>\u003Cb>下载\u003C\u002Fb>\u003C\u002Ftd>\n  \u003C\u002Ftr>\n  \u003Ctr>\n    \u003Ctd>\u003Cb>Windows\u003C\u002Fb>\u003C\u002Ftd>\n    \u003Ctd>\u003Ca href='https:\u002F\u002Fapp.jan.ai\u002Fdownload\u002Flatest\u002Fwin-x64'>jan.exe\u003C\u002Fa>\u003C\u002Ftd>\n  \u003C\u002Ftr>\n  \u003Ctr>\n    \u003Ctd>\u003Cb>macOS\u003C\u002Fb>\u003C\u002Ftd>\n    \u003Ctd>\u003Ca href='https:\u002F\u002Fapp.jan.ai\u002Fdownload\u002Flatest\u002Fmac-universal'>jan.dmg\u003C\u002Fa>\u003C\u002Ftd>\n  \u003C\u002Ftr>\n  \u003Ctr>\n    \u003Ctd>\u003Cb>Linux (deb)\u003C\u002Fb>\u003C\u002Ftd>\n    \u003Ctd>\u003Ca href='https:\u002F\u002Fapp.jan.ai\u002Fdownload\u002Flatest\u002Flinux-amd64-deb'>jan.deb\u003C\u002Fa>\u003C\u002Ftd>\n  \u003C\u002Ftr>\n  \u003Ctr>\n    \u003Ctd>\u003Cb>Linux (AppImage)\u003C\u002Fb>\u003C\u002Ftd>\n    \u003Ctd>\u003Ca href='https:\u002F\u002Fapp.jan.ai\u002Fdownload\u002Flatest\u002Flinux-amd64-appimage'>jan.AppImage\u003C\u002Fa>\u003C\u002Ftd>\n  \u003C\u002Ftr>\n  \u003Ctr>\n    \u003Ctd>\u003Cb>Linux (Arm64)\u003C\u002Fb>\u003C\u002Ftd>\n    \u003Ctd>\u003Ca href='https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fissues\u002F4543#issuecomment-3734911349'>如何操作\u003C\u002Fa>\u003C\u002Ftd>\n  \u003C\u002Ftr>\n\u003C\u002Ftable>\n\n\n从 [jan.ai](https:\u002F\u002Fjan.ai\u002F) 或 [GitHub Releases](https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Freleases) 下载。\n\n## 功能特性\n\n- **本地 AI 模型**: 从 HuggingFace 下载并运行**大语言模型 (LLMs)**（如 Llama, Gemma, Qwen, GPT-oss 等）\n- **云集成**: 通过 OpenAI 连接 GPT 模型，通过 Anthropic 连接 Claude 模型，以及 Mistral, Groq, MiniMax 等其他服务\n- **自定义助手**: 为您的任务创建专门的 AI 助手\n- **兼容 OpenAI 的 API**: 在 `localhost:1337` 提供本地服务器供其他应用程序使用\n- **模型上下文协议 (MCP)**: MCP 集成以支持智能体能力\n- **隐私优先**: 当您需要时，所有内容均在本地运行\n\n## 从源码构建\n\n对于那些喜欢亲自动手（源码构建）的人：\n\n### 前置条件\n\n- Node.js ≥ 20.0.0\n- Yarn ≥ 4.5.3\n- Make ≥ 3.81\n- Rust (用于 Tauri)\n- (仅限 macOS Apple Silicon) MetalToolchain `xcodebuild -downloadComponent MetalToolchain`\n\n### 使用 Make 运行\n\n```bash\ngit clone https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\ncd jan\nmake dev\n```\n\n这将处理所有事情：安装依赖项、构建核心组件并启动应用。\n\n**可用的 make 目标：**\n- `make dev` - 完整的开发环境设置和启动\n- `make build` - 生产构建\n- `make test` - 运行测试和代码检查\n- `make clean` - 删除所有内容重新开始\n\n### 手动命令\n\n```bash\nyarn install\nyarn build\nyarn dev\n```\n\n## 系统要求\n\n**获得良好体验的最小配置要求：**\n\n- **macOS**: 13.6+ (3B 模型需 8GB RAM (内存)，7B 模型需 16GB，13B 模型需 32GB)\n- **Windows**: 10+，支持 NVIDIA\u002FAMD\u002FIntel Arc 的 GPU (图形处理器)\n- **Linux**: 大多数发行版可用，支持 GPU 加速\n\n有关详细的兼容性信息，请查看我们的 [安装指南](https:\u002F\u002Fjan.ai\u002Fdocs\u002Fdesktop\u002Fmac)。\n\n## 故障排除\n\n如果出现问题：\n\n1. 查看我们的 [故障排除文档](https:\u002F\u002Fjan.ai\u002Fdocs\u002Fdesktop\u002Ftroubleshooting)\n2. 复制您的错误日志和系统规格\n3. 在我们的 [Discord](https:\u002F\u002Fdiscord.gg\u002FFTk2MvZwJH) `#🆘|jan-help` 频道寻求帮助\n\n\n## 贡献\n\n欢迎贡献。查看 [CONTRIBUTING.md](CONTRIBUTING.md) 了解完整说明。\n\n## 链接\n\n- [文档](https:\u002F\u002Fjan.ai\u002Fdocs) - 你应该阅读的指南\n- [API 参考](https:\u002F\u002Fjan.ai\u002Fapi-reference) - 面向技术爱好者\n- [更新日志](https:\u002F\u002Fjan.ai\u002Fchangelog) - 我们修复了哪些问题\n- [Discord](https:\u002F\u002Fdiscord.gg\u002FFTk2MvZwJH) - 社区聚集地\n\n## 联系方式\n\n- **问题**: [GitHub Issues](https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fissues)\n- **商务**: hello@jan.ai\n- **招聘**: hr@jan.ai\n- **一般讨论**: [Discord](https:\u002F\u002Fdiscord.gg\u002FFTk2MvZwJH)\n\n## 许可证\n\nApache 2.0 - 因为分享即关爱。\n\n## 致谢\n\n站在巨人的肩膀上构建：\n\n- [Llama.cpp](https:\u002F\u002Fgithub.com\u002Fggerganov\u002Fllama.cpp)\n- [Tauri](https:\u002F\u002Ftauri.app\u002F)\n- [Scalar](https:\u002F\u002Fgithub.com\u002Fscalar\u002Fscalar)","# Jan 快速上手指南\n\nJan 是一款开源的本地 AI 聊天工具，旨在提供类似 ChatGPT 的体验，同时确保数据隐私与完全控制权。它支持在本地运行多种大语言模型（LLM），并兼容云端服务。\n\n## 1. 环境准备\n\n### 系统要求\n为了获得良好的运行体验，请确保您的设备满足以下最低配置：\n\n| 平台 | 版本要求 | 内存建议 (RAM) | 其他要求 |\n| :--- | :--- | :--- | :--- |\n| **macOS** | 13.6+ | 3B 模型需 8GB\u003Cbr>7B 模型需 16GB\u003Cbr>13B 模型需 32GB | Apple Silicon 需安装 MetalToolchain |\n| **Windows** | 10+ | 同上 | 推荐 NVIDIA\u002FAMD\u002FIntel Arc GPU 加速 |\n| **Linux** | 主流发行版 | 同上 | 支持 GPU 加速 |\n\n### 开发环境前置依赖\n如果您选择从源码构建，需要安装以下工具：\n- Node.js ≥ 20.0.0\n- Yarn ≥ 4.5.3\n- Make ≥ 3.81\n- Rust (用于 Tauri 构建)\n- (macOS Apple Silicon 仅) MetalToolchain (`xcodebuild -downloadComponent MetalToolchain`)\n\n## 2. 安装步骤\n\n### 方式一：下载预编译版本（推荐）\n直接访问 [jan.ai](https:\u002F\u002Fjan.ai\u002F) 或 [GitHub Releases](https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Freleases) 下载对应系统的安装包：\n\n- **Windows**: 下载 `jan.exe` ([链接](https:\u002F\u002Fapp.jan.ai\u002Fdownload\u002Flatest\u002Fwin-x64))\n- **macOS**: 下载 `jan.dmg` ([链接](https:\u002F\u002Fapp.jan.ai\u002Fdownload\u002Flatest\u002Fmac-universal))\n- **Linux (deb)**: 下载 `jan.deb` ([链接](https:\u002F\u002Fapp.jan.ai\u002Fdownload\u002Flatest\u002Flinux-amd64-deb))\n- **Linux (AppImage)**: 下载 `jan.AppImage` ([链接](https:\u002F\u002Fapp.jan.ai\u002Fdownload\u002Flatest\u002Flinux-amd64-appimage))\n- **Linux (Arm64)**: 参考 [Issue #4543](https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fissues\u002F4543#issuecomment-3734911349) 获取安装方法\n\n此外，Windows 用户也可通过 [Microsoft Store](https:\u002F\u002Fapps.microsoft.com\u002Fdetail\u002Fxpdcnfn5cpzlqb) 安装，Linux 用户可通过 [Flathub](https:\u002F\u002Fflathub.org\u002Fapps\u002Fai.jan.Jan) 安装。\n\n### 方式二：从源码构建\n适合希望自定义开发的开发者：\n\n```bash\ngit clone https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\ncd jan\nmake dev\n```\n\n该命令会自动处理依赖安装、核心组件构建及应用启动。若需手动操作，可执行以下命令：\n\n```bash\nyarn install\nyarn build\nyarn dev\n```\n\n## 3. 基本使用\n\n安装完成后，启动 Jan 应用程序即可开始使用。\n\n1. **运行本地模型**\n   - 在界面中连接 HuggingFace，下载并运行开源模型（如 Llama, Gemma, Qwen, GPT-oss 等）。\n   - 所有模型推理均在本地完成，保障隐私。\n\n2. **接入云端模型**\n   - 支持连接 OpenAI (GPT)、Anthropic (Claude)、Mistral、Groq 等云端服务。\n\n3. **API 集成**\n   - Jan 内置 OpenAI 兼容 API 服务器，默认监听地址为 `localhost:1337`。\n   - 其他应用程序可通过此接口调用 Jan 提供的本地模型能力。\n\n4. **高级功能**\n   - 创建自定义助手（Custom Assistants）以适配特定任务。\n   - 启用 MCP (Model Context Protocol) 集成以实现代理能力。","背景：某金融科技公司后端工程师小张，需要在严格保密的内网环境下分析包含敏感用户信息的系统日志，以快速定位生产环境的 Bug。\n\n### 没有 jan 时\n- 严禁将原始日志上传至公共云端大模型，导致无法利用强大的 AI 能力辅助排查复杂问题。\n- 手动逐行阅读海量日志效率极其低下，极易遗漏关键的错误堆栈信息和潜在关联线索。\n- 公司网络策略禁止访问外部 API，无法连接常规的在线 AI 服务，导致开发流程被迫中断。\n- 每次调试需反复向同事或外部人员复述上下文，沟通成本高且存在数据泄露风险。\n\n### 使用 jan 后\n- 安装 jan 后直接在本地部署开源模型，所有敏感数据完全不出内网，彻底消除隐私顾虑。\n- 通过 jan 提供的本地服务器接口快速调用模型，秒级解析日志结构并给出精准的修复建议。\n- 无需联网即可流畅运行，完美适配受限的内网开发环境，确保工作流连续不间断。\n- 创建专属代码审查助手，自动聚焦技术细节，大幅减少重复解释背景的时间，提升单兵作战效率。\n\nJan 实现了离线环境下的高效智能交互，让数据安全与开发生产力不再相互冲突。","https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fjanhq_jan_04a0b3d1.png","janhq","Jan","https:\u002F\u002Foss.gittoolsai.com\u002Favatars\u002Fjanhq_6e2c51f9.png","Jan is building Open Intelligence.",null,"hello@menlo.ai","jandotai","https:\u002F\u002Fjan.ai","https:\u002F\u002Fgithub.com\u002Fjanhq",[85,89,93,97,101,105,109,113,117,120],{"name":86,"color":87,"percentage":88},"TypeScript","#3178c6",71.6,{"name":90,"color":91,"percentage":92},"Rust","#dea584",21.8,{"name":94,"color":95,"percentage":96},"Swift","#F05138",2.3,{"name":98,"color":99,"percentage":100},"Python","#3572A5",1.8,{"name":102,"color":103,"percentage":104},"JavaScript","#f1e05a",1,{"name":106,"color":107,"percentage":108},"Shell","#89e051",0.5,{"name":110,"color":111,"percentage":112},"CSS","#663399",0.4,{"name":114,"color":115,"percentage":116},"Makefile","#427819",0.3,{"name":118,"color":119,"percentage":116},"PowerShell","#012456",{"name":121,"color":122,"percentage":123},"HTML","#e34c26",0,41565,2694,"2026-04-05T11:05:03","NOASSERTION","Windows, macOS, Linux","支持 NVIDIA\u002FAMD\u002FIntel Arc，非强制，显存需求随模型大小变化","8GB (3B 模型) \u002F 16GB (7B 模型) \u002F 32GB (13B 模型)",{"notes":132,"python":133,"dependencies":134},"基于 Tauri 构建的桌面应用，非纯 Python 项目；支持本地运行 HuggingFace 开源模型；提供 OpenAI 兼容 API 接口；隐私优先，数据本地处理。","未说明",[135,136,137,90,138,139],"Node.js >= 20.0.0","Yarn >= 4.5.3","Make >= 3.81","Llama.cpp","Tauri",[26,15,13],[142,143,144,145,146,147,148,149],"llamacpp","localai","self-hosted","gpt","tauri","chatgpt","llm","open-source",84,"2026-03-27T02:49:30.150509","2026-04-06T04:24:32.585358",[154,159,164,169,174,179],{"id":155,"question_zh":156,"answer_zh":157,"source_url":158},2588,"模型加载时一直显示 \"Message queued\" 且无任何活动怎么办？","此问题通常与 CUDA 驱动版本不匹配或系统资源有关。请尝试以下步骤：1. 将 CUDA 版本更新至与当前 GPU 驱动版本一致；2. 检查 CPU 核心数（Windows 用户可运行命令 `wmic cpu get numberOfCores` 确认输出）；3. 确保系统内存充足。该问题在部分新版本中已得到修复。","https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fissues\u002F1859",{"id":160,"question_zh":161,"answer_zh":162,"source_url":163},2589,"Linux AppImage 模式下模型下载总是失败提示 \"Download Failed\" 如何解决？","这通常是由于证书或权限问题导致的。根据官方反馈，相关修复（PR #5463）计划包含在 v0.6.5 版本中。建议暂时等待该版本发布，或检查系统网络环境是否允许访问模型源。","https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fissues\u002F4582",{"id":165,"question_zh":166,"answer_zh":167,"source_url":168},2590,"拒绝网络请求后 TensorRT-LLM 启动失败该如何处理？","如果在配置过程中拒绝了 Nitro 的网络请求，会导致 TensorRT-LLM 启动失败。建议接受网络请求以确保功能正常，或者暂时专注于使用 Cortex TensorRT-LLM 作为替代方案。","https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fissues\u002F3682",{"id":170,"question_zh":171,"answer_zh":172,"source_url":173},2591,"为什么会出现多个助手同时响应的情况？","这是特定测试版本（如 v0.5.12-rc2-beta）中的已知问题。在该版本下，系统可能错误地触发多个助手同时生成回复。建议升级到稳定版本以避免此类并发冲突。","https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fissues\u002F4291",{"id":175,"question_zh":176,"answer_zh":177,"source_url":178},2592,"Jan v0.5.15-rc17-beta 版本中所有链接都无法打开怎么办？","这是该测试版（RC）构建中的一个已知缺陷。由于是预发布版本，可能存在稳定性问题。建议回退到之前的稳定版本或等待官方修复后的正式版本发布。","https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fissues\u002F4456",{"id":180,"question_zh":181,"answer_zh":182,"source_url":178},2593,"聊天界面中的 STOP 按钮是否会停止模型生成？","是的，在 v0.5.15-rc16-beta 等测试版本中，点击 STOP 按钮会直接停止模型的生成过程。这是预期行为的一部分，但在某些情况下可能会意外中断对话，请注意操作时机。",[184,189,194,199,204,209,214,219,224,229,234,239,244,249,254,259,264,269,274,279],{"id":185,"version":186,"summary_zh":187,"released_at":188},102107,"v0.7.9","## What's Changed\r\n* fix: clean up ANTHROPIC_* env vars from shell config when server stops or app exits by @since-2017-hub in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7628\r\n* fix: add redirect from \u002Fguides to \u002Fdocs by @louis-jan in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7669\r\n* docs: update troubleshooting guides by @louis-jan in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7670\r\n* docs: restructure Reference by @louis-jan in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7674\r\n* docs: agents availability by @louis-jan in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7682\r\n* docs: add community cards to desktop overview by @louis-jan in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7687\r\n* chore: resolve release main conflict 0.7.8 by @Vanalite in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7713\r\n* Sync release\u002Fv0.7.8 to main branch by @louis-jan in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7711\r\n* doc: add changelog for v0.7.8 by @Vanalite in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7714\r\n* docs: update CLI and agents docs for v0.7.8 by @louis-jan in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7715\r\n* feat: update flatpak manifest v0.7.8 by @Minh141120 in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7717\r\n* fix: resolve Anthropic 400 error on serial tool calls by @atoz96 in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7696\r\n* Revert: clear ANTHROPIC_ env on app exit #7628 by @louis-jan in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7718\r\n* Merge pull request #7695 from oolokioo7\u002Ffix\u002Fedit-dialog-width by @louis-jan in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7719\r\n* Fix: gpu detection losing by @dataCenter430 in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7605\r\n* fix: system theme not updating when switching dark\u002Flight mode on KDE Linux by @since-2017-hub in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7629\r\n* docs: add Windows data folder relocation troubleshooting section by @louis-jan in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7724\r\n* docs: add troubleshooting for timeout port by @Vanalite in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7730\r\n* fix: fix error on openclaw doc by @Vanalite in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7731\r\n* fix: prevent duplicate backend downloads during llamacpp update by @atoz96 in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7721\r\n* fix: render code block without lang spec correcty by @cs-cat in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7741\r\n* refactor: fix `normalizeLatex` logic and improve performance by @cs-cat in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7743\r\n* docs: troubleshooting update for jan CLI on Windows by @louis-jan in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7736\r\n* docs: add instructions to uninstall openclaw by @Vanalite in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7754\r\n* docs: Add instruction to install HIP\u002FROCm llamacpp backend for AMD by @Vanalite in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7755\r\n* fix: update CLI help examples to use Jan model ID by @louis-jan in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7753\r\n* fix: kv-cache defaults and fit migration by @louis-jan in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7751\r\n* feat: default model for local api server by @urmauur in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7735\r\n* chore: remove the 32k ctx_len enforcement upon API server start by @Vanalite in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7756\r\n* feat: add default assistant setting by @urmauur in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7725\r\n* doc: update CONTRIBUTING.md by @Vanalite in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7764\r\n* fix: wrong display shortcut create project by @urmauur in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7757\r\n* feat: add foundation models plugin with server management capabilities by @dev-miro26 in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7744\r\n* feat: add Spanish (Español) locale by @dev-miro26 in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7765\r\n* fix: change data location that has accident symlink failed by @Vanalite in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7763\r\n* fix: resolve downloaded model toggle bug by handling developer prefix by @jamesdam in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7648\r\n* feat: safe define remove dir list during the factory reset by @Vanalite in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7766\r\n* chore: remove openclaw installation by @Vanalite in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7762\r\n* fix: cli install method on Window by @Vanalite in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7768\r\n* feat: add NVIDIA NIM as a predefined cloud provider by @MauroDruwel in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7740\r\n* fix: api server cors vulnerability by @Vanalite in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7769\r\n* refactor: replace toggle with chevron for show variants in Hub by @Lokimorty in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7059\r\n* feat: settings to auto increase ctx_len by @Vanalite in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7770\r\n* doc: temporary remove the MCP example section which was previously nuked by @Vanalite in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7776\r\n* feat: expand supported file types for document attachments by @dev-miro26 in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7772\r\n* fix: Hub behavior issues by @Vanalite in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7777\r\n* chore: disable foundation model for RC by @Vanalite in https:\u002F\u002Fgithub.com\u002Fj","2026-03-23T06:09:34",{"id":190,"version":191,"summary_zh":192,"released_at":193},102125,"v0.6.2","## Changes\r\n\r\n- 🔧config: remove MCP and tool use production gate @louis-menlo (#5531)\r\n- 🐛fix: default model settings @louis-menlo (#5528)\r\n- ✨enhancement: adjust placement exp toggle @urmauur (#5525)\r\n- ✨feat: improve local provider connectivity with CORS bypass @samhvw8 (#5458)\r\n- ✨enhancement: experimental feature toggle @urmauur (#5514)\r\n- 🐛fix: delete pre populate remote models @urmauur (#5516)\r\n- ♻️ sync: cherry pick v0.6.2 release @louis-menlo (#5515)\r\n\r\n## Contributor\r\n\r\n@louis-menlo, @samhvw8 and @urmauur\r\n","2025-06-26T07:28:39",{"id":195,"version":196,"summary_zh":197,"released_at":198},102126,"v0.6.1","## Changes\r\n\r\n- 🐛 fix: avoid rendering the HTML title of the thread @urmauur (#5375)\r\n\r\n## Contributor\r\n\r\n@urmauur\r\n","2025-06-19T16:44:03",{"id":200,"version":201,"summary_zh":202,"released_at":203},102108,"v0.7.8","## What's Changed\r\n* Sync Release\u002Fv0.7.7 to main by @louis-jan in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7504\r\n* docs: changelog for v0.7.7 by @Vanalite in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7507\r\n* chore: update flatpak manifest v0.7.7 by @Minh141120 in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7510\r\n* chore: update landing page app screenshots by @urmauur in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7511\r\n* fix: duplicate url manifest flatpak by @Minh141120 in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7519\r\n* Sync new change from Release\u002Fv0.7.7 to main by @louis-jan in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7518\r\n* ci: add condition for nightly external by @Minh141120 in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7523\r\n* fix: conditional show message toolbar by @urmauur in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7524\r\n* fix: adjustment dragable app window by @urmauur in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7521\r\n* fix: incorrect links in docs by @statxc in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7517\r\n* fix: thinking render with long content by @urmauur in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7527\r\n* fix: sorting provider name by @urmauur in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7526\r\n* fix: simplify mlx-server backend with new ChatSession update by @louis-jan in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7538\r\n* fix: gpt-oss disallows quantized cache types due to its use of attention sinks by @louis-jan in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7541\r\n* fix: MLX import dialog uses folder picker instead of file picker by @louis-jan in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7554\r\n* fix: long text error apikey by @urmauur in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7557\r\n* fix: replace AbortSignal.any with manual polyfill for WebKit compatibility by @since-2017-hub in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7552\r\n* fix: navigation back from detail hub page by @urmauur in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7569\r\n* fix: use libappindicator3-1 for deb package to fix Ubuntu 22.04 install conflict by @dev-miro26 in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7570\r\n* feat: add xAI provider by @louis-jan in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7551\r\n* fix: add dir=auto for bidirectional text support by @sesajad in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7542\r\n* fix: hide capability for mlx model by @urmauur in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7579\r\n* docs: add Jan-Code-4B, Jan-v3-4B, and Jan-v2-VL model pages by @louis-jan in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7598\r\n* fix: add back linux native top panel tauri by @urmauur in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7580\r\n* feat: openclaw integration by @Vanalite in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7583\r\n* fix: disconnect channel and add spinner by @Vanalite in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7599\r\n* feat: polish the initialize flow by @Vanalite in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7602\r\n* feat: Jan CLI support by @louis-jan in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7576\r\n* fix: update flash attention handling in ArgumentBuilder by @dev-miro26 in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7565\r\n* fix: overlap z-index model setting and dropdown model provider by @urmauur in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7600\r\n* enhancement: better setting organizations by @urmauur in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7601\r\n* feat: Jan manages Context Allocation dynamically by @louis-jan in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7609\r\n* fix: disable auto fit setting by default by @louis-jan in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7610\r\n* fix: scrollable dropdown assistant by @urmauur in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7607\r\n* enhancement: recommend small model  by @urmauur in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7606\r\n* fix: correct model eval chart by @louis-jan in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7614\r\n* fix(tauri): handle non-UTF-8 paths in default_data_folder_path by @eren-karakus0 in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7577\r\n* enhancement: add model provider options by @urmauur in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7611\r\n* fix: allow different images with same filename by deduplicating on co… by @mykh-hailo in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7563\r\n* fix: text color readme detail model screen by @urmauur in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7617\r\n* feat: agent mode toggle and sandbox config isolation for OpenClaw by @Vanalite in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7612\r\n* fix: add deeplink open in jan from models by @louis-jan in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7616\r\n* feat: starter screen and download management update UI by @urmauur in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7548\r\n* fix: mlx provider only show for MacOs by @urmauur in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7620\r\n* fix: setup failed ui openClaw, and run local api server when run agent by @urmauur in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7619\r\n* fix: missing command on window and linux by @Vanalite in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7621\r\n* fix: bundle jan-cli.exe in Windows NSIS installer by @louis-jan in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7618\r\n* chore: update left panel menu with agent chat by @urmauur in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7622\r\n* chore: update lo","2026-03-11T13:42:31",{"id":205,"version":206,"summary_zh":207,"released_at":208},102109,"v0.7.7","## What's Changed\r\n* fix: theme set loop on Windows by @louis-jan in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7407\r\n* fix: left panel full height by @urmauur in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7409\r\n* fix: throttle renderer to reduce pressure to the thread by @louis-jan in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7408\r\n* feat: prompt to download Jan VL model for vision capability by @Vanalite in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7410\r\n* docs: changelog for v0.7.6 by @Vanalite in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7418\r\n* chore: update manifest for flatpak jan 0.7.6 by @Minh141120 in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7419\r\n* chore: onboard new user with q4 k xl by @louis-jan in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7420\r\n* Fix: inconsistent code block formatting in Markdown rendering by @bytrangle in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7049\r\n* fix: accept x-api-key header in place of custom header by @louis-jan in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7421\r\n* fix: Display embedding models in settings with visual distinction by @bittoby in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7393\r\n* chore: sync release branch for merging by @Vanalite in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7425\r\n* chore: merge release branch by @Vanalite in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7424\r\n* fix: update api docs by @louis-jan in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7426\r\n* fix: default instruction update by @louis-jan in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7427\r\n* feat: streamable http exa default search mcp by @louis-jan in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7428\r\n* chore: disable auto updater for flatpak build by @hiento09 in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7432\r\n* ci: move config yarn makefile to ci by @Minh141120 in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7433\r\n* ui: revamp layout by @urmauur in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7431\r\n* fix: minor badge capabilities by @urmauur in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7435\r\n* fix: dynamically generate OpenAPI spec with actual server host and port by @Eruis2579 in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7434\r\n* fix: take back refresh and add model remote provider by @urmauur in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7436\r\n* fix: prefill value when rename thread by @urmauur in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7437\r\n* chore: delete all thread by @urmauur in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7447\r\n* fix: edit message with files attachment by @urmauur in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7446\r\n* chore: update font from local instead cdn by @urmauur in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7449\r\n* chore: avoid warning dialog components by @urmauur in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7450\r\n* chore: assistant assign into projects by @urmauur in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7441\r\n* feat: add delete all thread inside projects by @urmauur in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7453\r\n* fix: inline math latex by @urmauur in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7454\r\n* fix: hover menu dots for delete all chat by @urmauur in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7455\r\n* fix: notarize mlx bin by @Minh141120 in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7458\r\n* feat: add new backend - MLX by @louis-jan in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7459\r\n* chore: adjustment drag area by @urmauur in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7464\r\n* fix: chat performance rerender issue by @urmauur in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7465\r\n* fix: issue descendant element by @urmauur in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7466\r\n* fix: hub screen scroll and loader  by @urmauur in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7467\r\n* fix: prompt cache - cannot infer the shape of an empty array by @louis-jan in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7470\r\n* chore: refactor modelhub by @hiento09 in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7468\r\n* chore: base layout windows by @urmauur in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7471\r\n* feat: implement fit settings in llamacpp extension and overhaul argument builder tests by @qnixsynapse in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7442\r\n* chore: update copy for setup screen by @urmauur in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7472\r\n* feat: local api server improvement by @urmauur in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7460\r\n* chore: update copy web by @urmauur in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7474\r\n* refactor: remove model planner since now use auto fit setting by @louis-jan in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7473\r\n* fix: pass model parameters in fetch body for all providers by @louis-jan in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7475\r\n* fix: overflow scroll thinking by @urmauur in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7476\r\n* chore: update icon project by @urmauur in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7478\r\n* fix: stop MLX model inference when client aborts chat\u002Fcompletions by @louis-jan in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7477\r\n* fix: package mlx only for mac by @louis-jan in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7479\r\n* fix: disable custom parameters for remote providers by @louis-jan in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7481\r\n* fix: select none assistant remote provider by @urmauur in htt","2026-02-11T10:30:05",{"id":210,"version":211,"summary_zh":212,"released_at":213},102110,"v0.7.6","## What's Changed\r\n* docs: update homepage SEO meta title and description by @eckartal in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7024\r\n* chore: update flatpak manifest by @Minh141120 in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7025\r\n* blog: optimize \"run AI locally\" blog post for SEO by @eckartal in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7028\r\n* feat: combine attachments icon by @urmauur in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F6998\r\n* fix: cstdint patch flatpak by @Minh141120 in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7032\r\n* Fix\u002Fappstream caption by @Minh141120 in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7033\r\n* feat: Update Russian localization by @Kuzmich55 in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7039\r\n* SEO: Improve offline-chatgpt-alternative content by @eckartal in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7040\r\n* feat: flatpak disable auto updater by @Minh141120 in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7054\r\n* Update flatpak metainfo by @eckartal in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7064\r\n* fix: flatpak appstream metadata validation errors by @Minh141120 in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7067\r\n* docs: add Microsoft Store and Flathub badges by @qnixsynapse in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7068\r\n* feat: add Polish metainfo translation by @0rzech in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7050\r\n* fix: improve Hub download button UX for installed models by @Lokimorty in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7060\r\n* Resolve Clippy Warnings and Apply Consistent Code Formatting by @github-roushan in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7010\r\n* feat: Update Russian localization by @Kuzmich55 in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7082\r\n* feat: complete Czech translations by @MichalZem in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7081\r\n* Update metadata for ai.jan.Jan by @razzeee in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7045\r\n* chore: update flatpak release 0.7.4 by @Minh141120 in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7117\r\n* chore: add change log doc for v0.7.4 by @Vanalite in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7110\r\n* refactor: clean up JoyRide by @louis-jan in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7073\r\n* chore: update flatpak manifest for v0.7.5 by @Minh141120 in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7133\r\n* chore: add change log doc for v0.7.5 by @Vanalite in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7132\r\n* chore: resolve conflicts between dev and 0.7.5 release branch by @Vanalite in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7135\r\n* chore: merge release 0.7.5 into dev branch by @Vanalite in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7134\r\n* refactor: move llama.cpp config handling to Rust by @qnixsynapse in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7047\r\n* fix: publisher name on windows by @Minh141120 in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7144\r\n* feat: Update Russian localization by @Kuzmich55 in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7149\r\n* feat: Improve toast messages and errors by @github-roushan in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F6892\r\n* feat: improve sidebar UI with distinct sections and better empty states by @github-roushan in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F6745\r\n* fix: prevent CUDA backend install failure by removing invalid fs.mkdir args by @qnixsynapse in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7162\r\n* fix: responsive button action hero landing page by @urmauur in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7274\r\n* refactor: jan web ci to use main branch and deprecate old workflows by @Minh141120 in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7332\r\n* refactor: migrate llamacpp backend logic to rust plugin by @qnixsynapse in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7171\r\n* feat: add portable windows by @Minh141120 in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7350\r\n* feat: chat enhancement by @louis-jan in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7361\r\n* feat: persist token usage into message metadata by @louis-jan in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7366\r\n* ci: update matrix test on windows by @Minh141120 in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7367\r\n* fix: tools availability and model settings by @louis-jan in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7368\r\n* fix: file upload function and assistant migration by @louis-jan in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7369\r\n* fix: missing shiki lib and import css katex by @urmauur in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7372\r\n* fix: remove setting codeblock by @urmauur in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7371\r\n* fix: font setup by @urmauur in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7373\r\n* Make it easy to install on ARM by @SuperCowProducts in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7353\r\n* docs: fix dead links to \u002Fdocs\u002Fserver and \u002Fdocs\u002Fmodels by @chindris-mihai-alexandru in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7342\r\n* feat: search dialog by @urmauur in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7374\r\n* chore: refactor updater by @hiento09 in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7377\r\n* fix: update renderer using plugins by @louis-jan in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7376\r\n* chore: fix race condition in updater by @hiento09 in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7378\r\n* fix: mcp tool approval by @louis-jan in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7379\r","2026-01-27T03:40:11",{"id":215,"version":216,"summary_zh":217,"released_at":218},102111,"v0.7.5","## What's Changed\r\n* fix: model import issue on Windows by @louis-jan in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7124\r\n* fix: users couldn’t import the mmproj vision model if the base name didn’t match. by @louis-jan in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7127\r\n* fix: correct CUDA backend installation and migration issues by @qnixsynapse in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7130\r\n* fix: kill mcp server on app termination by @Vanalite in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7131\r\n\r\n\r\n**Full Changelog**: https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fcompare\u002Fv0.7.4...v0.7.5","2025-12-08T10:12:28",{"id":220,"version":221,"summary_zh":222,"released_at":223},102112,"v0.7.4","## What's Changed\r\n* feat: add backend migration mapping and update backend handling by @qnixsynapse in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F6917\r\n* ci: clean up deduplicate issue workflow by @Minh141120 in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F6923\r\n* Enhance localization by completing missing translations across all locales + czech support by @github-roushan in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F6758\r\n* feat: Add official jan browser mcp by @Vanalite in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F6929\r\n* docs: add changelog v0.7.3 by @Minh141120 in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F6951\r\n* Merge release 0.7.3 to dev by @Vanalite in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F6967\r\n* fix: csp restrictions from inline styles by @urmauur in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F6970\r\n* fix: glib issue on linux by @Minh141120 in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F6975\r\n* fix: app blocks image input by @louis-jan in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F6982\r\n* fix: disable autocorrect in model search input by @Lokimorty in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F6952\r\n* French translation menu item missing by @fredatgithub in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F6974\r\n* chore: separate the loader style by @urmauur in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F6984\r\n* fix: changing tools while conversing results in incorrect tool use by @louis-jan in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F6985\r\n* Enable desktop file attachments feature by @dinhlongviolin1 in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F6989\r\n* feat: migrate assistant screen into setting by @urmauur in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F6986\r\n* fix: trafficlight icon mac responsive by @urmauur in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F6994\r\n* fix: reenable zoom hotkey by @urmauur in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F6995\r\n* feat: add CUDA 13 support to backend by @qnixsynapse in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F6996\r\n* chore: add CUDA 13 backend as a priority backend by @qnixsynapse in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7005\r\n* chore: bump token.js by @Vanalite in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7006\r\n* Correct the \"Why Open-Source\" URL by @trunghaiy in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F6965\r\n* docs: update handbook by @mmngn in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7007\r\n* feat: move proactive mode to MCP settings by @Vanalite in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7008\r\n* feat: lockfile to kill conflict MCP's port by @Vanalite in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7012\r\n* fix: keep the untouched properties after modifying mcp settings by @Vanalite in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7014\r\n* fix: preserve dollar sign followed by numbers in markdown rendering by @qnixsynapse in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7027\r\n* fix: reattach the same file after deletion fix by @Vanalite in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7030\r\n* feat: add embedding flag to model metadata and automatic detection by @qnixsynapse in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7031\r\n* fix: Fix extension installation link by @Vanalite in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7042\r\n* fix: spawn new process with window close flag by @Vanalite in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7043\r\n* feat: update link to chrome store for Jan extension by @Vanalite in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7051\r\n* fix: disable context menu list projects by @urmauur in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7056\r\n* fix: ui check be version by @urmauur in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7057\r\n* feat: update flatpak build by @Minh141120 in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7061\r\n* fix: flatpak upload s3 by @Minh141120 in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7062\r\n* fix: Enable JIT compilation to fix MCP server memory allocation errors by @louis-jan in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7072\r\n* feat: quick start with Jan model by @Vanalite in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7052\r\n* fix: Toast and dismiss validating toast using model_id by @Vanalite in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7065\r\n* fix: cancel failed download task by @Vanalite in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7077\r\n* fix: fix linter with missing parameters by @Vanalite in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7078\r\n* feat: close app in background by @Vanalite in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7076\r\n* feat: jan browser mcp as chat input shortcut by @louis-jan in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7074\r\n* fix: skip model verification on quick start by @louis-jan in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7083\r\n* fix: killing process with name checking logic by @Vanalite in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7085\r\n* feat: Dialog to install Jan extension by @Vanalite in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7086\r\n* fix: model import name should be filename instead of GGUF baseName by @louis-jan in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7088\r\n* fix: could not save image edit by @louis-jan in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7089\r\n* feat: Cancellation mechanism during mcp connectivity check by @Vanalite in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7090\r\n* Feat\u002Fimprove file attachments by @dinhlongviolin1 in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F7080\r\n* fix: attachme","2025-12-05T10:10:36",{"id":225,"version":226,"summary_zh":227,"released_at":228},102113,"v0.7.3","## What's Changed\r\n* Feat: Mobile App Optimization and Backend Integration by @Vanalite in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F6512\r\n* feat: Configure iOS to use frontDist to independently build  by @Vanalite in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F6540\r\n* enhancement: base layout mobile by @urmauur in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F6549\r\n* Feat: Split different build configuration among different platforms by @Vanalite in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F6608\r\n* feat: Add make commands for ios and android development by @Vanalite in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F6610\r\n* Update handbook content with Nextra callout and content improvements by @eckartal in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F6562\r\n* Show supported files by @github-roushan in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F6618\r\n* docs: update missing redirect links by @Minh141120 in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F6634\r\n* enhancement: social media navbar and update menu footer by @urmauur in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F6640\r\n* fix: scroll issue chatgpt, padding not recalculated correctly by @dinhlongviolin1 in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F6639\r\n* feat: Disable text selection on Toaster by @Vanalite in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F6642\r\n* Emre to update & create content by @eckartal in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F6633\r\n* refactor: deprecate Vulkan external binaries by @louis-jan in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F6638\r\n* fix: Apply model name change correctly by @Vanalite in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F6643\r\n* Fix OG image paths and move images to general folder by @eckartal in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F6652\r\n* fix: remove Jan prefix from blog post titles for better SEO by @eckartal in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F6653\r\n* Feat: web temporary chat by @dinhlongviolin1 in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F6650\r\n* docs: update redirect links by @Minh141120 in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F6665\r\n* Emre to improve SEO by @eckartal in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F6654\r\n* Content\u002Femre by @eckartal in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F6666\r\n* feat: web add search button for extension by @dinhlongviolin1 in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F6671\r\n* fix: add missing eol newline by @dinhlongviolin1 in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F6673\r\n* fix: mcp bin path by @louis-jan in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F6667\r\n* sync release 0.7.0 to dev by @dinhlongviolin1 in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F6674\r\n* feat: disable all web mcp by default (new users) by @dinhlongviolin1 in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F6677\r\n* Feat: Jan has mobile MVP by @Vanalite in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F6657\r\n* fix: chat completion usage - token speed by @louis-jan in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F6675\r\n* resolve TypeScript and Rust warnings by @github-roushan in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F6612\r\n* fix: thread item overfetching by @dinhlongviolin1 in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F6699\r\n* feat: improve projects by @dinhlongviolin1 in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F6698\r\n* fix: web gg tag by @dinhlongviolin1 in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F6702\r\n* fix: Fix editing model without saving should restore original name by @Vanalite in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F6700\r\n* resolve rust analyzer warnings by @github-roushan in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F6696\r\n* docs: add Jan v0.7.0 changelog by @eckartal in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F6708\r\n* fix: Extract model capabilities correctly for various providers on various platforms by @Vanalite in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F6715\r\n* ci: remove upload msi by @Minh141120 in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F6723\r\n* fix: extensions missing on Unix dev by @dinhlongviolin1 in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F6724\r\n* fix: Local API Server - disable settings on run by @louis-jan in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F6707\r\n* changelog: release 0.7.1 by @urmauur in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F6730\r\n* chore: wrong version in detail changelog by @urmauur in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F6731\r\n* fix: update detail changelog 0.7.1 by @urmauur in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F6732\r\n* fix(ui): restore missing border on model selector (#6692) by @github-roushan in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F6736\r\n* Feat: Jan mobile has persistence store by @Vanalite in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F6714\r\n* UI enhancement for projects by @github-roushan in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F6726\r\n* fix: title recent when no result found by @urmauur in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F6744\r\n* fix: new chat with update last selected model dropdown by @urmauur in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F6742\r\n* fix: theme system cross platform by @urmauur in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F6713\r\n* Sync dev into release by @louis-jan in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F6747\r\n* Sync release v0.7.0 to dev  by @louis-jan in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F6720\r\n* feat: Hide projects for mobile version by @Vanalite in https:\u002F\u002Fgithub.com\u002Fjanhq\u002Fjan\u002Fpull\u002F6746\r\n* chore: ","2025-11-13T12:31:11",{"id":230,"version":231,"summary_zh":232,"released_at":233},102114,"v0.7.2","## What's Changed\r\n* chore: happy-dom update by @Minh141120 in https:\u002F\u002Fgithub.com\u002Fmenloresearch\u002Fjan\u002Fpull\u002F6790\r\n\r\n**Full Changelog**: https:\u002F\u002Fgithub.com\u002Fmenloresearch\u002Fjan\u002Fcompare\u002Fv0.7.1...v0.7.2","2025-10-16T05:27:29",{"id":235,"version":236,"summary_zh":237,"released_at":238},102115,"v0.7.1","## What's Changed\r\n* chore: use custom nsis template by @Minh141120 in https:\u002F\u002Fgithub.com\u002Fmenloresearch\u002Fjan\u002Fpull\u002F6721\r\n* ci: remove upload msi artifact by @Minh141120 in https:\u002F\u002Fgithub.com\u002Fmenloresearch\u002Fjan\u002Fpull\u002F6725\r\n* fix: prompt token by @urmauur in https:\u002F\u002Fgithub.com\u002Fmenloresearch\u002Fjan\u002Fpull\u002F6727\r\n* Fix: Anthropic request to add models by @Vanalite in https:\u002F\u002Fgithub.com\u002Fmenloresearch\u002Fjan\u002Fpull\u002F6728\r\n* fix: get model capabilities correctly by @Vanalite in https:\u002F\u002Fgithub.com\u002Fmenloresearch\u002Fjan\u002Fpull\u002F6715\r\n\r\n**Full Changelog**: https:\u002F\u002Fgithub.com\u002Fmenloresearch\u002Fjan\u002Fcompare\u002Fv0.7.0...v0.7.1","2025-10-03T16:18:05",{"id":240,"version":241,"summary_zh":242,"released_at":243},102116,"v0.7.0","## What's Changed\r\n* ci: separate jan web build and deploy by @Minh141120 in https:\u002F\u002Fgithub.com\u002Fmenloresearch\u002Fjan\u002Fpull\u002F6427\r\n* add mcp for web by @dinhlongviolin1 in https:\u002F\u002Fgithub.com\u002Fmenloresearch\u002Fjan\u002Fpull\u002F6411\r\n* fix: Polish translation by @0rzech in https:\u002F\u002Fgithub.com\u002Fmenloresearch\u002Fjan\u002Fpull\u002F6421\r\n* ci: remove paths triggered for jan server by @Minh141120 in https:\u002F\u002Fgithub.com\u002Fmenloresearch\u002Fjan\u002Fpull\u002F6430\r\n* ci: fix typo in branch name for jan web by @Minh141120 in https:\u002F\u002Fgithub.com\u002Fmenloresearch\u002Fjan\u002Fpull\u002F6433\r\n* Fix: Web Services Improvement by @dinhlongviolin1 in https:\u002F\u002Fgithub.com\u002Fmenloresearch\u002Fjan\u002Fpull\u002F6452\r\n* refactor: clean up empty folders by @louis-menlo in https:\u002F\u002Fgithub.com\u002Fmenloresearch\u002Fjan\u002Fpull\u002F6454\r\n* Update 4-goal.md by @LazyYuuki in https:\u002F\u002Fgithub.com\u002Fmenloresearch\u002Fjan\u002Fpull\u002F6451\r\n* chore: revert back old docs by @urmauur in https:\u002F\u002Fgithub.com\u002Fmenloresearch\u002Fjan\u002Fpull\u002F6460\r\n* fix: Markdown bullet list incorrectly converted in numbered list by @bytrangle in https:\u002F\u002Fgithub.com\u002Fmenloresearch\u002Fjan\u002Fpull\u002F6437\r\n* chore: missing local api server by @urmauur in https:\u002F\u002Fgithub.com\u002Fmenloresearch\u002Fjan\u002Fpull\u002F6461\r\n* Always allow MCP for web by @dinhlongviolin1 in https:\u002F\u002Fgithub.com\u002Fmenloresearch\u002Fjan\u002Fpull\u002F6462\r\n* feat: add model selector (fetch from v1\u002Fmodels) when user adds a provider model by @lugnicca in https:\u002F\u002Fgithub.com\u002Fmenloresearch\u002Fjan\u002Fpull\u002F6278\r\n* Add model response timeout for local api server as configurable value by @maxx-ukoo in https:\u002F\u002Fgithub.com\u002Fmenloresearch\u002Fjan\u002Fpull\u002F6384\r\n* remove assistant from web by @dinhlongviolin1 in https:\u002F\u002Fgithub.com\u002Fmenloresearch\u002Fjan\u002Fpull\u002F6468\r\n* Added Exa MCP by @theishangoswami in https:\u002F\u002Fgithub.com\u002Fmenloresearch\u002Fjan\u002Fpull\u002F6473\r\n* fix: remove website folder by @urmauur in https:\u002F\u002Fgithub.com\u002Fmenloresearch\u002Fjan\u002Fpull\u002F6496\r\n* chore: add redirect by @hiento09 in https:\u002F\u002Fgithub.com\u002Fmenloresearch\u002Fjan\u002Fpull\u002F6497\r\n* chore: fix redirect by @hiento09 in https:\u002F\u002Fgithub.com\u002Fmenloresearch\u002Fjan\u002Fpull\u002F6498\r\n* feat: system tray icon build flag by @louis-menlo in https:\u002F\u002Fgithub.com\u002Fmenloresearch\u002Fjan\u002Fpull\u002F6500\r\n* feat: add auth + google auth provider for web by @dinhlongviolin1 in https:\u002F\u002Fgithub.com\u002Fmenloresearch\u002Fjan\u002Fpull\u002F6505\r\n* fix: deeplink issue on Windows by @louis-menlo in https:\u002F\u002Fgithub.com\u002Fmenloresearch\u002Fjan\u002Fpull\u002F6469\r\n* Bring back 0.6.10 QA changes to dev by @dinhlongviolin1 in https:\u002F\u002Fgithub.com\u002Fmenloresearch\u002Fjan\u002Fpull\u002F6516\r\n* feat: Add GA Measurement and change keyboard bindings on web by @dinhlongviolin1 in https:\u002F\u002Fgithub.com\u002Fmenloresearch\u002Fjan\u002Fpull\u002F6514\r\n* feat: Add Jan API server Swagger UI by @qnixsynapse in https:\u002F\u002Fgithub.com\u002Fmenloresearch\u002Fjan\u002Fpull\u002F6502\r\n* fix: thread rerender issue by @louis-menlo in https:\u002F\u002Fgithub.com\u002Fmenloresearch\u002Fjan\u002Fpull\u002F6515\r\n* docs: update url for gifs and videos by @Minh141120 in https:\u002F\u002Fgithub.com\u002Fmenloresearch\u002Fjan\u002Fpull\u002F6527\r\n* fix: Typo in openapi JSON by @qnixsynapse in https:\u002F\u002Fgithub.com\u002Fmenloresearch\u002Fjan\u002Fpull\u002F6528\r\n* fix(number-input): preserve '0.0x' format when typing (#6520) by @github-roushan in https:\u002F\u002Fgithub.com\u002Fmenloresearch\u002Fjan\u002Fpull\u002F6526\r\n* docs: update changelog for v0.6.10 by @Minh141120 in https:\u002F\u002Fgithub.com\u002Fmenloresearch\u002Fjan\u002Fpull\u002F6524\r\n* chore: update build tauri commands by @Minh141120 in https:\u002F\u002Fgithub.com\u002Fmenloresearch\u002Fjan\u002Fpull\u002F6518\r\n* feat: fix remote provider vision capability by @louis-menlo in https:\u002F\u002Fgithub.com\u002Fmenloresearch\u002Fjan\u002Fpull\u002F6475\r\n* fix: prevent consecutive messages with same role by @louis-menlo in https:\u002F\u002Fgithub.com\u002Fmenloresearch\u002Fjan\u002Fpull\u002F6544\r\n* enhancement: toaster delete mcp server by @urmauur in https:\u002F\u002Fgithub.com\u002Fmenloresearch\u002Fjan\u002Fpull\u002F6529\r\n* feat: Prompt progress when streaming by @qnixsynapse in https:\u002F\u002Fgithub.com\u002Fmenloresearch\u002Fjan\u002Fpull\u002F6503\r\n* chore: add ci for web stag by @hiento09 in https:\u002F\u002Fgithub.com\u002Fmenloresearch\u002Fjan\u002Fpull\u002F6550\r\n* feat: add getTokensCount method to compute token usage by @qnixsynapse in https:\u002F\u002Fgithub.com\u002Fmenloresearch\u002Fjan\u002Fpull\u002F6467\r\n* fix: custom fetch for all providers by @louis-menlo in https:\u002F\u002Fgithub.com\u002Fmenloresearch\u002Fjan\u002Fpull\u002F6538\r\n* Fix: add full-width model names by @gdmka in https:\u002F\u002Fgithub.com\u002Fmenloresearch\u002Fjan\u002Fpull\u002F6350\r\n* fix: prevent relocation to root directories by @louis-menlo in https:\u002F\u002Fgithub.com\u002Fmenloresearch\u002Fjan\u002Fpull\u002F6547\r\n* feat: web remote conversation by @dinhlongviolin1 in https:\u002F\u002Fgithub.com\u002Fmenloresearch\u002Fjan\u002Fpull\u002F6554\r\n* feat: add azure as first class provider by @louis-menlo in https:\u002F\u002Fgithub.com\u002Fmenloresearch\u002Fjan\u002Fpull\u002F6555\r\n* fix: layout ability model by @urmauur in https:\u002F\u002Fgithub.com\u002Fmenloresearch\u002Fjan\u002Fpull\u002F6559\r\n* enhancement: migrate handbook and janv2 by @urmauur in https:\u002F\u002Fgithub.com\u002Fmenloresearch\u002Fjan\u002Fpull\u002F6552\r\n* ✨ feat: Re-arrange docs as needed by @LazyYuuki in https:\u002F\u002Fgithub.com\u002Fmenloresearch\u002Fjan\u002Fpull\u002F6535\r\n* fix: Catch local API server various errors by @Vanalite in https:\u002F\u002Fgithub.com\u002Fmenloresearch\u002Fjan\u002Fpull\u002F6548\r\n* fix: LocalAPI server trusted host should accept asterisk by @louis-menlo in https:\u002F\u002Fgithub.com\u002Fmenloresearch\u002Fjan\u002Fpull\u002F6551\r\n* feat(llamacpp):","2025-10-02T09:30:34",{"id":245,"version":246,"summary_zh":247,"released_at":248},102117,"v0.6.10","## What's Changed\r\n* Bring back QA changes 0.6.9 by @dinhlongviolin1 in https:\u002F\u002Fgithub.com\u002Fmenloresearch\u002Fjan\u002Fpull\u002F6320\r\n* docs: Major restructure and consolidation by @ramonpzg in https:\u002F\u002Fgithub.com\u002Fmenloresearch\u002Fjan\u002Fpull\u002F6323\r\n* hotfix: fixed home page hyperlink and extension gif by @ramonpzg in https:\u002F\u002Fgithub.com\u002Fmenloresearch\u002Fjan\u002Fpull\u002F6324\r\n* fix: Use 80% total memory for compatibility check (#6321) by @dinhlongviolin1 in https:\u002F\u002Fgithub.com\u002Fmenloresearch\u002Fjan\u002Fpull\u002F6333\r\n* hotfix: changed website theme by @ramonpzg in https:\u002F\u002Fgithub.com\u002Fmenloresearch\u002Fjan\u002Fpull\u002F6335\r\n* fix: mise build failing by @theproductiveprogrammer in https:\u002F\u002Fgithub.com\u002Fmenloresearch\u002Fjan\u002Fpull\u002F6344\r\n* chore: fix id code-block for avoid duplicate same state by @urmauur in https:\u002F\u002Fgithub.com\u002Fmenloresearch\u002Fjan\u002Fpull\u002F6346\r\n* chore: update docs font by @urmauur in https:\u002F\u002Fgithub.com\u002Fmenloresearch\u002Fjan\u002Fpull\u002F6359\r\n* fix: remove timezone specific from utils by @urmauur in https:\u002F\u002Fgithub.com\u002Fmenloresearch\u002Fjan\u002Fpull\u002F6363\r\n* fix: search hgf repo and downloaded filter by @urmauur in https:\u002F\u002Fgithub.com\u002Fmenloresearch\u002Fjan\u002Fpull\u002F6366\r\n* feat: allow see Apikey when server local status running by @urmauur in https:\u002F\u002Fgithub.com\u002Fmenloresearch\u002Fjan\u002Fpull\u002F6364\r\n* feat: download llamacpp backend fail back to cdn by @hiento09 in https:\u002F\u002Fgithub.com\u002Fmenloresearch\u002Fjan\u002Fpull\u002F6361\r\n* feat: Jan Web (reusing Jan Desktop UI) by @dinhlongviolin1 in https:\u002F\u002Fgithub.com\u002Fmenloresearch\u002Fjan\u002Fpull\u002F6298\r\n* feat: Web use jan model by @dinhlongviolin1 in https:\u002F\u002Fgithub.com\u002Fmenloresearch\u002Fjan\u002Fpull\u002F6374\r\n* ci: add paths for jan server web by @Minh141120 in https:\u002F\u002Fgithub.com\u002Fmenloresearch\u002Fjan\u002Fpull\u002F6377\r\n* chore: update Dockerfile to use custom nginx.conf by @Minh141120 in https:\u002F\u002Fgithub.com\u002Fmenloresearch\u002Fjan\u002Fpull\u002F6378\r\n* docs: add first‑class API Reference to Jan docs (Local + Server) by @ramonpzg in https:\u002F\u002Fgithub.com\u002Fmenloresearch\u002Fjan\u002Fpull\u002F6372\r\n* ci: remove unnecessary folder paths and on Dockerfile by @Minh141120 in https:\u002F\u002Fgithub.com\u002Fmenloresearch\u002Fjan\u002Fpull\u002F6392\r\n* enhancement: responsive dialog modals by @urmauur in https:\u002F\u002Fgithub.com\u002Fmenloresearch\u002Fjan\u002Fpull\u002F6381\r\n* feat: allow user import model include mmproj file by @urmauur in https:\u002F\u002Fgithub.com\u002Fmenloresearch\u002Fjan\u002Fpull\u002F6388\r\n* chore: add cicd for jan web prod by @hiento09 in https:\u002F\u002Fgithub.com\u002Fmenloresearch\u002Fjan\u002Fpull\u002F6396\r\n* feat: improve testing by @dinhlongviolin1 in https:\u002F\u002Fgithub.com\u002Fmenloresearch\u002Fjan\u002Fpull\u002F6395\r\n* fix: jan server api base url for prod by @hiento09 in https:\u002F\u002Fgithub.com\u002Fmenloresearch\u002Fjan\u002Fpull\u002F6403\r\n* removed cloud api spec update by @ramonpzg in https:\u002F\u002Fgithub.com\u002Fmenloresearch\u002Fjan\u002Fpull\u002F6406\r\n* ci: add claude issue dedup by @Minh141120 in https:\u002F\u002Fgithub.com\u002Fmenloresearch\u002Fjan\u002Fpull\u002F6408\r\n* enhancement: rollback edit capabilities for local model by @urmauur in https:\u002F\u002Fgithub.com\u002Fmenloresearch\u002Fjan\u002Fpull\u002F6409\r\n* feat: Smart model management by @qnixsynapse in https:\u002F\u002Fgithub.com\u002Fmenloresearch\u002Fjan\u002Fpull\u002F6390\r\n* feat: enhance llamacpp backend management and installation by @qnixsynapse in https:\u002F\u002Fgithub.com\u002Fmenloresearch\u002Fjan\u002Fpull\u002F6360\r\n* ci: add nightly build for external contributors by @Minh141120 in https:\u002F\u002Fgithub.com\u002Fmenloresearch\u002Fjan\u002Fpull\u002F6413\r\n* fix: include lm_head and embedding layers in totalLayers count by @qnixsynapse in https:\u002F\u002Fgithub.com\u002Fmenloresearch\u002Fjan\u002Fpull\u002F6415\r\n* fix: clean up unused packages by @louis-menlo in https:\u002F\u002Fgithub.com\u002Fmenloresearch\u002Fjan\u002Fpull\u002F6414\r\n* fix: render new line for user message by @urmauur in https:\u002F\u002Fgithub.com\u002Fmenloresearch\u002Fjan\u002Fpull\u002F6412\r\n* bug: Deleted model file from imported models blocking model loading (#6317) by @dinhlongviolin1 in https:\u002F\u002Fgithub.com\u002Fmenloresearch\u002Fjan\u002Fpull\u002F6417\r\n* enhancement: add label experimental for optimize setting by @urmauur in https:\u002F\u002Fgithub.com\u002Fmenloresearch\u002Fjan\u002Fpull\u002F6416\r\n* fix: error connecting to ollama (#6349) by @dinhlongviolin1 in https:\u002F\u002Fgithub.com\u002Fmenloresearch\u002Fjan\u002Fpull\u002F6418\r\n* exclude jan extension web from desktop build by @dinhlongviolin1 in https:\u002F\u002Fgithub.com\u002Fmenloresearch\u002Fjan\u002Fpull\u002F6419\r\n* fix: avoid error validate nested DOM by @urmauur in https:\u002F\u002Fgithub.com\u002Fmenloresearch\u002Fjan\u002Fpull\u002F6426\r\n* fix: correct context shift flag handling in LlamaCPP extension (#6404) by @qnixsynapse in https:\u002F\u002Fgithub.com\u002Fmenloresearch\u002Fjan\u002Fpull\u002F6431\r\n* enhancement: copy MCP permission by @urmauur in https:\u002F\u002Fgithub.com\u002Fmenloresearch\u002Fjan\u002Fpull\u002F6456\r\n* fix: KVCache size calculation and refactor by @qnixsynapse in https:\u002F\u002Fgithub.com\u002Fmenloresearch\u002Fjan\u002Fpull\u002F6438\r\n* chore: makefile rust targets macos by @Minh141120 in https:\u002F\u002Fgithub.com\u002Fmenloresearch\u002Fjan\u002Fpull\u002F6457\r\n* fix: detect allocation failures as out-of-memory errors by @qnixsynapse in https:\u002F\u002Fgithub.com\u002Fmenloresearch\u002Fjan\u002Fpull\u002F6459\r\n* fix: set default memory mode and clean up unused import by @qnixsynapse in https:\u002F\u002Fgithub.com\u002Fmenloresearch\u002Fjan\u002Fpull\u002F6463\r\n* fix: pathname file install BE by @urmauur in https:\u002F\u002Fgithub.com\u002Fmenloresearch\u002Fjan\u002Fpull\u002F6464\r\n* fix: attachment edit message by @urmauur in https:\u002F\u002Fgithub.com\u002Fmenloresea","2025-09-18T08:06:32",{"id":250,"version":251,"summary_zh":252,"released_at":253},102118,"v0.6.9","## What's Changed\r\n* ci: add disable auto update flag by @Minh141120 in https:\u002F\u002Fgithub.com\u002Fmenloresearch\u002Fjan\u002Fpull\u002F6143\r\n* add disable auto updater input for nightly build by @Minh141120 in https:\u002F\u002Fgithub.com\u002Fmenloresearch\u002Fjan\u002Fpull\u002F6159\r\n* enhancement: Add support for mmproj models by @urmauur in https:\u002F\u002Fgithub.com\u002Fmenloresearch\u002Fjan\u002Fpull\u002F6150\r\n* ci: fix tauri build nightly for linux by @Minh141120 in https:\u002F\u002Fgithub.com\u002Fmenloresearch\u002Fjan\u002Fpull\u002F6161\r\n* feat: Add GGUF metadata reading functionality by @qnixsynapse in https:\u002F\u002Fgithub.com\u002Fmenloresearch\u002Fjan\u002Fpull\u002F6120\r\n* fix: handle modelId special char by @urmauur in https:\u002F\u002Fgithub.com\u002Fmenloresearch\u002Fjan\u002Fpull\u002F6172\r\n* fix: feature toggle auto updater by @Minh141120 in https:\u002F\u002Fgithub.com\u002Fmenloresearch\u002Fjan\u002Fpull\u002F6175\r\n* feat: add flatpak ci by @Minh141120 in https:\u002F\u002Fgithub.com\u002Fmenloresearch\u002Fjan\u002Fpull\u002F6177\r\n* Feat: Add flatpak manifest by @qnixsynapse in https:\u002F\u002Fgithub.com\u002Fmenloresearch\u002Fjan\u002Fpull\u002F4732\r\n* refactor: flathub submission by @Minh141120 in https:\u002F\u002Fgithub.com\u002Fmenloresearch\u002Fjan\u002Fpull\u002F6182\r\n* Backend Architecture Refactoring (#6094) by @dinhlongviolin1 in https:\u002F\u002Fgithub.com\u002Fmenloresearch\u002Fjan\u002Fpull\u002F6162\r\n* chore: replace md5 with sha256 for CUDA by @Minh141120 in https:\u002F\u002Fgithub.com\u002Fmenloresearch\u002Fjan\u002Fpull\u002F6193\r\n* New tutoriasl for v0.6.8 docs by @ramonpzg in https:\u002F\u002Fgithub.com\u002Fmenloresearch\u002Fjan\u002Fpull\u002F6196\r\n* Fix Issue #6199 by @Jasper-256 in https:\u002F\u002Fgithub.com\u002Fmenloresearch\u002Fjan\u002Fpull\u002F6200\r\n* fix: default color not selected in appearance color palette by @cmppoon in https:\u002F\u002Fgithub.com\u002Fmenloresearch\u002Fjan\u002Fpull\u002F6092\r\n* blog: Add Deep Research Piece by @danielcwq in https:\u002F\u002Fgithub.com\u002Fmenloresearch\u002Fjan\u002Fpull\u002F6039\r\n* 🚀feat: allow user mark model as favorite by @urmauur in https:\u002F\u002Fgithub.com\u002Fmenloresearch\u002Fjan\u002Fpull\u002F6006\r\n* feat: mcp enhancement by @louis-menlo in https:\u002F\u002Fgithub.com\u002Fmenloresearch\u002Fjan\u002Fpull\u002F6188\r\n* enhancement: mcp disable save button when server name still empty by @urmauur in https:\u002F\u002Fgithub.com\u002Fmenloresearch\u002Fjan\u002Fpull\u002F6214\r\n* fix: re-enable Vulkan backend in integrated GPUs with enough memory by @qnixsynapse in https:\u002F\u002Fgithub.com\u002Fmenloresearch\u002Fjan\u002Fpull\u002F6215\r\n* feat: add support for reasoning fields (OpenRouter) by @dinhlongviolin1 in https:\u002F\u002Fgithub.com\u002Fmenloresearch\u002Fjan\u002Fpull\u002F6206\r\n* fix: update token.js to remove retired models by @louis-menlo in https:\u002F\u002Fgithub.com\u002Fmenloresearch\u002Fjan\u002Fpull\u002F6219\r\n* feat: #5917 - model tool use capability should be auto detected by @louis-menlo in https:\u002F\u002Fgithub.com\u002Fmenloresearch\u002Fjan\u002Fpull\u002F6222\r\n* fix: cancel stream mid run (#6221) by @dinhlongviolin1 in https:\u002F\u002Fgithub.com\u002Fmenloresearch\u002Fjan\u002Fpull\u002F6227\r\n* fix: should use custom fetch provided by app by @louis-menlo in https:\u002F\u002Fgithub.com\u002Fmenloresearch\u002Fjan\u002Fpull\u002F6224\r\n* fix: Auto select model only for active provider by @urmauur in https:\u002F\u002Fgithub.com\u002Fmenloresearch\u002Fjan\u002Fpull\u002F6229\r\n* enhancement: offload model when provider not active by @urmauur in https:\u002F\u002Fgithub.com\u002Fmenloresearch\u002Fjan\u002Fpull\u002F6226\r\n* feat: Pass API key via environment variable instead of command line arg by @qnixsynapse in https:\u002F\u002Fgithub.com\u002Fmenloresearch\u002Fjan\u002Fpull\u002F6225\r\n* fix: downloaded model should from variant level instead of the model level by @urmauur in https:\u002F\u002Fgithub.com\u002Fmenloresearch\u002Fjan\u002Fpull\u002F6234\r\n* fix: improve ux import model by @urmauur in https:\u002F\u002Fgithub.com\u002Fmenloresearch\u002Fjan\u002Fpull\u002F6233\r\n* feat: add tool call cancellation by @louis-menlo in https:\u002F\u002Fgithub.com\u002Fmenloresearch\u002Fjan\u002Fpull\u002F6236\r\n* feat: attachment UI by @urmauur in https:\u002F\u002Fgithub.com\u002Fmenloresearch\u002Fjan\u002Fpull\u002F6134\r\n* fix: resolve issue #6025 - default color selection in appearance page by @Louis454545 in https:\u002F\u002Fgithub.com\u002Fmenloresearch\u002Fjan\u002Fpull\u002F6198\r\n* Add contributing section for jan (#6231) by @dinhlongviolin1 in https:\u002F\u002Fgithub.com\u002Fmenloresearch\u002Fjan\u002Fpull\u002F6232\r\n* Fix: Validate GGUF files before loading by @qnixsynapse in https:\u002F\u002Fgithub.com\u002Fmenloresearch\u002Fjan\u002Fpull\u002F6238\r\n* fix: prevent scroll position jump when AI completes response while user reading by @Louis454545 in https:\u002F\u002Fgithub.com\u002Fmenloresearch\u002Fjan\u002Fpull\u002F6203\r\n* enhancement: remove validate file extension from select file when import gguf by @urmauur in https:\u002F\u002Fgithub.com\u002Fmenloresearch\u002Fjan\u002Fpull\u002F6242\r\n* chore: update new domain for jan docs by @Minh141120 in https:\u002F\u002Fgithub.com\u002Fmenloresearch\u002Fjan\u002Fpull\u002F6245\r\n* fix: local api server log (#6240) by @dinhlongviolin1 in https:\u002F\u002Fgithub.com\u002Fmenloresearch\u002Fjan\u002Fpull\u002F6244\r\n* fix: hidden sort filter when searching model by @urmauur in https:\u002F\u002Fgithub.com\u002Fmenloresearch\u002Fjan\u002Fpull\u002F6246\r\n* chore: re enable reasoning_content in backend by @qnixsynapse in https:\u002F\u002Fgithub.com\u002Fmenloresearch\u002Fjan\u002Fpull\u002F6228\r\n* feat: allow user to set max_attempt for MCP to avoid looping by @louis-menlo in https:\u002F\u002Fgithub.com\u002Fmenloresearch\u002Fjan\u002Fpull\u002F6241\r\n* ci: add autoqa reliability workflow for windows by @Minh141120 in https:\u002F\u002Fgithub.com\u002Fmenloresearch\u002Fjan\u002Fpull\u002F6248\r\n* enhancement: vision icon hub model list by @urmauur in https:\u002F\u002Fgithub.com\u002Fmenloresearch\u002Fjan\u002Fpull\u002F6251\r\n* feat: MCP server error handling ","2025-08-28T10:22:10",{"id":255,"version":256,"summary_zh":257,"released_at":258},102119,"v0.6.8","## What's Changed\r\n* Sync Release\u002Fv0.6.6 into dev by @louis-menlo in https:\u002F\u002Fgithub.com\u002Fmenloresearch\u002Fjan\u002Fpull\u002F5973\r\n* fix: thread sorting issue by @cmppoon in https:\u002F\u002Fgithub.com\u002Fmenloresearch\u002Fjan\u002Fpull\u002F5976\r\n* ✨enhancement: blurry logo model provider by @urmauur in https:\u002F\u002Fgithub.com\u002Fmenloresearch\u002Fjan\u002Fpull\u002F5986\r\n* fix: missing text color responsive left panel by @urmauur in https:\u002F\u002Fgithub.com\u002Fmenloresearch\u002Fjan\u002Fpull\u002F5989\r\n* fix assistant dropdown onClick not triggered consistently by @cmppoon in https:\u002F\u002Fgithub.com\u002Fmenloresearch\u002Fjan\u002Fpull\u002F5991\r\n* Sync Release\u002Fv0.6.6 into dev by @louis-menlo in https:\u002F\u002Fgithub.com\u002Fmenloresearch\u002Fjan\u002Fpull\u002F5997\r\n* Add comprehensive Products section and reorganize documentation structure by @ramonpzg in https:\u002F\u002Fgithub.com\u002Fmenloresearch\u002Fjan\u002Fpull\u002F5958\r\n* Sync release\u002Fv0.6.6 into dev by @louis-menlo in https:\u002F\u002Fgithub.com\u002Fmenloresearch\u002Fjan\u002Fpull\u002F6004\r\n* refactor: clean up cortex by @louis-menlo in https:\u002F\u002Fgithub.com\u002Fmenloresearch\u002Fjan\u002Fpull\u002F6003\r\n* ci: enable PR trigger for dev branch in tauri nightly workflow by @Minh141120 in https:\u002F\u002Fgithub.com\u002Fmenloresearch\u002Fjan\u002Fpull\u002F6014\r\n* fix: react state loop from hooks useMediaQuery by @urmauur in https:\u002F\u002Fgithub.com\u002Fmenloresearch\u002Fjan\u002Fpull\u002F6031\r\n* fix: wrong desc setting cont_batching by @urmauur in https:\u002F\u002Fgithub.com\u002Fmenloresearch\u002Fjan\u002Fpull\u002F6034\r\n* Fix: Llama.cpp server hangs on model load by @qnixsynapse in https:\u002F\u002Fgithub.com\u002Fmenloresearch\u002Fjan\u002Fpull\u002F6030\r\n* feat(docs): Docs v2 Astro migration by @ramonpzg in https:\u002F\u002Fgithub.com\u002Fmenloresearch\u002Fjan\u002Fpull\u002F5950\r\n* feat: Improve llama.cpp argument handling and add device parsing tests by @qnixsynapse in https:\u002F\u002Fgithub.com\u002Fmenloresearch\u002Fjan\u002Fpull\u002F6041\r\n* fix: show error toast message on download error by @cmppoon in https:\u002F\u002Fgithub.com\u002Fmenloresearch\u002Fjan\u002Fpull\u002F6044\r\n* fix: Generate A Response button does not show context size error dialog by @urmauur in https:\u002F\u002Fgithub.com\u002Fmenloresearch\u002Fjan\u002Fpull\u002F6029\r\n* fix connected servers status not in sync when edit mcp json by @cmppoon in https:\u002F\u002Fgithub.com\u002Fmenloresearch\u002Fjan\u002Fpull\u002F6020\r\n* feat: Add check for AVX2 instruction support for MCP on MacOS with Intel CPUs by @shmutalov in https:\u002F\u002Fgithub.com\u002Fmenloresearch\u002Fjan\u002Fpull\u002F5530\r\n* chore: skip nightly build workflow for external contributor by @Minh141120 in https:\u002F\u002Fgithub.com\u002Fmenloresearch\u002Fjan\u002Fpull\u002F6050\r\n* fix: support missing llamacpp cuda backends by @louis-menlo in https:\u002F\u002Fgithub.com\u002Fmenloresearch\u002Fjan\u002Fpull\u002F6046\r\n* ci: disable autoqa on nightly build by @Minh141120 in https:\u002F\u002Fgithub.com\u002Fmenloresearch\u002Fjan\u002Fpull\u002F6051\r\n* ✨feat: recommended label llamacpp setting by @urmauur in https:\u002F\u002Fgithub.com\u002Fmenloresearch\u002Fjan\u002Fpull\u002F6052\r\n* Fix: Improve Llama.cpp model path handling and error handling by @qnixsynapse in https:\u002F\u002Fgithub.com\u002Fmenloresearch\u002Fjan\u002Fpull\u002F6045\r\n* ✨feat: jinja template customize per model instead provider level by @urmauur in https:\u002F\u002Fgithub.com\u002Fmenloresearch\u002Fjan\u002Fpull\u002F6053\r\n* fix: Jan hub model detail and deep link by @louis-menlo in https:\u002F\u002Fgithub.com\u002Fmenloresearch\u002Fjan\u002Fpull\u002F6024\r\n* fix: Add conditional Vulkan support check for better GPU compatibility by @qnixsynapse in https:\u002F\u002Fgithub.com\u002Fmenloresearch\u002Fjan\u002Fpull\u002F6066\r\n* Readme Update and Additional Model Providers by @ramonpzg in https:\u002F\u002Fgithub.com\u002Fmenloresearch\u002Fjan\u002Fpull\u002F6064\r\n* fix: gpt-oss thinking block by @urmauur in https:\u002F\u002Fgithub.com\u002Fmenloresearch\u002Fjan\u002Fpull\u002F6071\r\n* fix: should not include reasoning text in the chat completion request by @louis-menlo in https:\u002F\u002Fgithub.com\u002Fmenloresearch\u002Fjan\u002Fpull\u002F6072\r\n* chore: update workflow name by @Minh141120 in https:\u002F\u002Fgithub.com\u002Fmenloresearch\u002Fjan\u002Fpull\u002F6073\r\n* ci: deprecate jan docs new release workflow in favor of jan-docs by @Minh141120 in https:\u002F\u002Fgithub.com\u002Fmenloresearch\u002Fjan\u002Fpull\u002F6078\r\n* Add gpt-oss local installation blog post by @eckartal in https:\u002F\u002Fgithub.com\u002Fmenloresearch\u002Fjan\u002Fpull\u002F6075\r\n* feat: Add support for overriding tensor buffer type by @qnixsynapse in https:\u002F\u002Fgithub.com\u002Fmenloresearch\u002Fjan\u002Fpull\u002F6062\r\n* refactor: move session management & port allocation to backend by @qnixsynapse in https:\u002F\u002Fgithub.com\u002Fmenloresearch\u002Fjan\u002Fpull\u002F6083\r\n* 🐛fix: onboarding loop by @urmauur in https:\u002F\u002Fgithub.com\u002Fmenloresearch\u002Fjan\u002Fpull\u002F6054\r\n* refactor: Use more precise terminology in API server logs by @qnixsynapse in https:\u002F\u002Fgithub.com\u002Fmenloresearch\u002Fjan\u002Fpull\u002F6085\r\n* fix: update ux recemmend backend label into desc setting by @urmauur in https:\u002F\u002Fgithub.com\u002Fmenloresearch\u002Fjan\u002Fpull\u002F6088\r\n* feat: Introduce structured error handling for llamacpp extension by @qnixsynapse in https:\u002F\u002Fgithub.com\u002Fmenloresearch\u002Fjan\u002Fpull\u002F6087\r\n* refactor: clean up unused hardware apis by @louis-menlo in https:\u002F\u002Fgithub.com\u002Fmenloresearch\u002Fjan\u002Fpull\u002F6089\r\n* added v0.6.7 changelog and jupyter mcp tutorial by @ramonpzg in https:\u002F\u002Fgithub.com\u002Fmenloresearch\u002Fjan\u002Fpull\u002F6116\r\n* fix: Prevent accidental message submitting on ChatInput for IME users by @B0sh in https:\u002F\u002Fgithub.com\u002Fmenloresearch\u002Fjan\u002Fpull\u002F6109\r\n* adding handbook, blog, and changelog to jan docs v2 by @ramonpzg in https:\u002F\u002Fgithu","2025-08-14T09:29:09",{"id":260,"version":261,"summary_zh":262,"released_at":263},102120,"v0.6.7","## Changes\r\n- fix: should not include reasoning text in the chat completion request @louis-menlo (#6072)\r\n- fix: gpt-oss thinking block @urmamur (#6071)\r\n- fix: react state loop from hooks useMediaQuery @urmamur (#6031)\r\n\r\n## Contributor\r\n\r\n@louis-menlo and @urmauur\r\n","2025-08-06T11:04:11",{"id":265,"version":266,"summary_zh":267,"released_at":268},102121,"v0.6.6","## Changes\r\n\r\n- hotfix: regression issue with colon in model name @louis-menlo (#6008)\r\n- Add RunEvent::Exit event to tauri to handle macos context menu exit @qnixsynapse (#6005)\r\n- fix: remove auto refresh model custom provider @urmauur (#6002)\r\n- fix: generate response button disappear on tool call @louis-menlo (#5988)\r\n- fix: title tooltip MCP edit json @urmauur (#5987)\r\n- fix: download progress missing when left panel scrollable @urmauur (#5984)\r\n- fix: failed provider models list due to broken cortex import @louis-menlo (#5983)\r\n- Sync Release\u002Fv0.6.6 into dev @louis-menlo (#5973)\r\n- fix: use direct process termination instead of console events on Windows @qnixsynapse (#5972)\r\n- fix: rename thread dialog shows previous thread @urmauur (#5963)\r\n- chore: allow all HTTPS image sources in img-src directive @Minh141120 (#5970)\r\n- feat: Enhance port selection with availability check @qnixsynapse (#5966)\r\n- fix: csp including img.shields.io and cdn-uploads.huggingface.co in img-src directive @Minh141120 (#5967)\r\n- ci: tolerate artifact upload @Minh141120 (#5969)\r\n- fix: assistant with last used and fix metadata @urmauur (#5955)\r\n- fix: search models result in hub should be sorted by weight @louis-menlo (#5954)\r\n- fix: factory reset fail with access denied error @louis-menlo (#5952)\r\n- fix: set autoUnload in onLoad() @qnixsynapse (#5956)\r\n- fix: update edge case experimental feature MCP @urmauur (#5951)\r\n- fix: correctly apply `auto_unload` setting from config @qnixsynapse (#5953)\r\n- fix: Prevent race condition with auto-unload during rapid model loading @qnixsynapse (#5947)\r\n- chore: uninstall when upgrading windows installer @Minh141120 (#5945)\r\n- fix: openrouter unselect itself @louis-menlo (#5943)\r\n- fix: tool approval params scrollable @urmauur (#5941)\r\n- fix: migrate app settings to the new version @louis-menlo (#5936)\r\n- fix: Remove sInfo from activeSessions before unloading @qnixsynapse (#5938)\r\n- fix: update default GPU toggle, and simplify state @urmauur (#5937)\r\n- chore: revert back to passive mode on windows installer @Minh141120 (#5934)\r\n- fix: update ui version\\_backend, mem usage hardware @urmauur (#5932)\r\n- fix: Frontend updates when llama.cpp backend auto-downloads @qnixsynapse (#5926)\r\n- fix: calculation memory on hardware and system monitor @urmauur (#5922)\r\n- fix: persist model capabilities refresh app @urmauur (#5918)\r\n- fix: validate name assistant and improve area clickable @urmauur (#5920)\r\n- fix: Allow N-GPU Layers (NGL) to be set to 0 in llama.cpp @qnixsynapse (#5907)\r\n- fix: models hub should show latest data only @louis-menlo (#5925)\r\n- fix: Persist 'Auto-Unload Old Models' setting in llama.cpp @qnixsynapse (#5906)\r\n- feat: Enhance Llama.cpp backend management with persistence @qnixsynapse (#5886)\r\n- Chore cua mac runner @hiento09 (#5888)\r\n- fix: provider settings should be refreshed on page load @louis-menlo (#5887)\r\n- 🐛fix: get system info and system usage @urmauur (#5884)\r\n- fix: gpu detected from backend version @urmauur (#5882)\r\n- fix: bring back HF repo ID search in Hub @louis-menlo (#5880)\r\n- chore: revert app artifact name for macos linux and windows builds @Minh141120 (#5878)\r\n- feat: add support for querying available backend devices @qnixsynapse (#5877)\r\n- fix: llama.cpp backend shows blank list sometime @louis-menlo (#5876)\r\n- ci: rename app github artifact on windows and linux build @Minh141120 (#5875)\r\n- ci: autoqa github artifact @Minh141120 (#5873)\r\n- fix: jan should have a general assistant instruction @louis-menlo (#5872)\r\n- fix: tmp download file should be removed on cancel @louis-menlo (#5849)\r\n- 🐛fix: remove sampling parameters from llamacpp extension @urmauur (#5871)\r\n- 🐛fix: update vulkan active syntax @urmauur (#5869)\r\n- fix: app should not show manually deleted models @louis-menlo (#5868)\r\n- feat: migrate cortex models to llamacpp extension @louis-menlo (#5838)\r\n- fix: charmap encoding @Minh141120 (#5865)\r\n- fix: HuggingFace provider should be non-deletable @louis-menlo (#5856)\r\n- fix: gemini tool call support - version bump @louis-menlo (#5848)\r\n- Fix: engine unable to find dlls on when running on Windows @qnixsynapse (#5863)\r\n- chore: update build appimage script @Minh141120 (#5866)\r\n- ✨enhancement: dialog model error trigger from provider screen @urmauur (#5858)\r\n- fix: support load model configurations @urmauur (#5843)\r\n- fix: delete all thread should not include fav @urmauur (#5864)\r\n- Chore: enrich autoqa log @hiento09 (#5862)\r\n- refactor: Improve Llama.cpp backend management and auto-update @qnixsynapse (#5845)\r\n- fix: autoqa prompt template @Minh141120 (#5854)\r\n- feat: add vcruntime for windows installer @Minh141120 (#5852)\r\n- ✨enhancement: auto focus always allow action from tool approval dialog and add req parameters @urmauur (#5836)\r\n- enhancement: better error page component @urmauur (#5834)\r\n- chore: sync make build with dev @Minh141120 (#5847)\r\n- refactor: standardize build process and remove build-tauri target @Minh141120 (#5846)\r\n- fix: custom","2025-07-31T11:17:35",{"id":270,"version":271,"summary_zh":272,"released_at":273},102122,"v0.6.5","## Changes\r\n\r\n- ✨enhancement: support base layout responsive Ul @urmauur (#5472)\r\n- ✨enhancement: setting responsive @urmauur (#5615)\r\n- ✨feat: bump version of llama.cpp - b5857 @louis-menlo (#5742)\r\n- 🐛fix: revert back stat hover for three dots @urmauur (#5777)\r\n- 🐛fix: download icon when left panel close @urmauur (#5776)\r\n- 🐛fix: revert installationmode in nsis template @Minh141120 (#5778)\r\n- 🐛fix: make three dots default show 3 dots and can trigger with right click  @urmauur (#5712)\r\n- 🐛fix: custom based url and header by upgrade token.js version @samhvw8 (#5596)\r\n- 🐛fix: update base URL for Anthropic provider @samhvw8 (#5600)\r\n- 🐛fix: Tauri Applmage failing to render on wayland + mesa @DistractionRectangle (#5463)\r\n- 🐛fix: fetch models from custom provider causes app to crash @louis-menlo (#5791)\r\n- 🔧 config: all yml to md for issue template @LazyYuuki (#5661)\r\n- 🔧 config: fix bug template @LazyYuuki (#5658)\r\n- 🔧 config: from yml to md for template @LazyYuuki (#5657)\r\n\r\n## Contributors\r\n\r\n@LazyYuuki, @Minh141120, @louis-menlo, @samhvw8, @DistractionRectangle and @urmauur","2025-07-17T09:02:43",{"id":275,"version":276,"summary_zh":277,"released_at":278},102123,"v0.6.4","## Changes\r\n\r\n- fix: top_k validation @louis-menlo (#5650)\r\n- fix: some of the model settings are not applied @louis-menlo (#5644)\r\n- fix: min_p validation on model load @louis-menlo (#5568)\r\n## Contributor\r\n\r\n@louis-menlo\r\n","2025-07-01T12:27:04",{"id":280,"version":281,"summary_zh":282,"released_at":283},102124,"v0.6.3","## Changes\r\n\r\n- fix: handle context shift setting from old app versions @louis-menlo (#5547)\r\n- 🐛fix: modal action light mode @urmauur (#5545)\r\n- hotfix: increase context size window does not popup first time @louis-menlo (#5542)\r\n\r\n## Contributor\r\n\r\n@louis-menlo and @urmauur\r\n","2025-06-26T13:53:51"]