Jan AI开源桌面应用程序，用于在本地全私有化与脱机访问中运行 LLM。

4.2 (5)

审阅者 Daniel Nikulshyn·更新 2026年7月

Open Source Local LLM Desktop App Privacy Offline Cross-Platform Developer Tools

概览

Jan 是一个开源的桌面应用程序，可以在全私有化与脱机访问的情况下运行本地大型语言模型 (LLM)。它旨在提供一个只有针对用户个人智能系统。该应用程序提供了各种功能，包括选择开源模型或将喜欢的在线模型插入，如 ChatGPT, claude, Gemini, Llama 和更多。还具有memory功能，记住用户的内容和偏好，使其更具个人化体验。该应用程序已获得了显著影响，下载超过 4,000万次，是免费的 macOS 下载。它是在公众的基础上构建的，反映了开发者的信念，即 AI 应该是公开的，并通过社区参与而增长。

主要功能

本地 LLM 推理
内置模型库和下载器
聊天界面
可选的远程 AI 服务连接
扩展和 API 支持
脱机模式
基于个人设备的执行

价格

模型: Free
分类: 緶制器
评分: 4.2 / 5 (5)

使用场景

私有的脱机 AI 交流

与大的语言模型聊天，全部在自己机器上，避免 telemetry 但不提供云

尝试开源模型

通过内置的模型库浏览、下载和切换开源 LLM 以比较输出和找到适合工作的最佳模型

混合性本地和云工作流

在本地进行私人工作，并可选连接远程供应商如 OpenAI，以找到更强大的模型

开发人员的定制 AI 工具

利用扩展和 API 支持来创建定制的集成、自动化工作流或将 Jan 本地 LLM 能力嵌入开发人员的流线

优点 & 缺点

优点

本地执行确保了数据的私有性
开源和自主
支持 Windows, macOS 和 Linux 多个平台
兼容多个开源模型
兼容多个 cloud API

缺点

执行性能取决于本地硬件
较大的模型可能需要大量内存和磁盘空间
设置可能是技术的

评测

4.2

5 个评分的平均值。

登录以留下评测。

Grace Okafor

Jan 13, 2026

Years in this space

I've evaluated a lot of these over the years. What stands out here is extension and API support for customization — handled better than most — and works with many open models and optional cloud APIs. Larger models require significant RAM and disk space is my one real gripe. Worth the time if this is your use case.

Naomi Suzuki

Nov 2, 2025

Years in this space

I've evaluated a lot of these over the years. What stands out here is offline mode with no telemetry by default — handled better than most — and fully local execution keeps data private. Setup can be technical for non-developers is my one real gripe. Worth the time if this is your use case.

Jamal Carter

Oct 23, 2025

Compared a few options

Evaluated this against two competitors. Where it wins: extension and API support for customization and open-source and self-hostable. On balance the feature set — especially local LLM inference on personal devices — justifies the 5 stars for our use case.

Hannah Goldberg

Sep 7, 2025

Solid for our team

We rolled this out across the team last quarter and open-source and self-hostable. Optional connections to remote AI providers fits neatly into how we already work, and chat interface with conversation history removed a step we used to do by hand. Performance depends on local hardware, which is the main caveat, but it has held up under daily use.

Gunnar Eriksson

Sep 1, 2025

Compared a few options

Evaluated this against two competitors. Where it wins: local LLM inference on personal devices and cross-platform support for Windows, macOS, and Linux. Where it lags: setup can be technical for non-developers. On balance the feature set — especially built-in model hub and downloader — justifies the 4 stars for our use case.

问答

Are there any system requirements for running Jan AI?

The performance of Jan AI depends on local hardware, and larger models require significant RAM and disk space.

Asked by Lena Fischer · Nov 8, 2025

What models are compatible with Jan AI?

Jan AI is compatible with many open models, including ChatGPT, Claude, Gemini, Llama, and more, and also allows you to plug in your favorite online models.

Asked by Ivo Novotný · Nov 5, 2025

Can I use Jan AI offline?

Yes, Jan AI has an offline mode with no telemetry by default, allowing for full privacy and offline access.

Asked by Noor Siddiqui · Sep 4, 2025

Is Jan AI free?

Yes, Jan AI is available for free as a Mac download and is open-source.

Asked by Thandiwe Dlamini · Aug 24, 2025