本地大模型运行AGPL-3.0TypeScript

Jan

Open-source ChatGPT-style desktop app that runs 100% offline.

Star 数
45K
Fork 数
3.1K
未关闭 Issue
579
最近提交
2026-10-15

数据来自 GitHub API · 更新于 2026-10-15

Jan 是什么?

Jan is a desktop app for chatting with local models (powered by llama.cpp) or remote APIs. It includes a model hub, a local OpenAI-compatible API server and extensions — an open-source alternative to LM Studio.

主要功能

  • Offline chat with local models
  • Model hub with one-click downloads
  • Local OpenAI-compatible API server
  • Optional remote providers

系统要求

平台
Windows · macOS · Linux
内存
8 GB minimum, 16 GB+ recommended

如何安装 Jan

根据项目 README 整理。开源项目更新很快,请以 GitHub 页面上的最新说明为准。

Desktop app

  1. 1
    Download Jan for your OS from jan.ai or GitHub Releases and install it.
  2. 2
    Open the Hub, download a model and start chatting.

优势

  • Polished, fully open-source UI
  • Private by default

不足

  • Fewer advanced settings than LM Studio

Jan 替代品对比

软件Star 数许可证平台显存
Jan

Open-source ChatGPT-style desktop app that runs 100% offline.

45KAGPL-3.0—
GPT4All

Private, on-device chat with local document Q&A.

77.4KMIT—
Ollama

Get up and running with large language models locally.

183.2KMIT—
AnythingLLM

All-in-one desktop and Docker app for private document chat and agents.

67.1KMIT—
Open WebUI

Self-hosted ChatGPT-style interface for Ollama and OpenAI-compatible APIs.

155.7KOpen WebUI License (BSD-3-Clause based)—
llama.cpp

LLM inference in C/C++ — the engine behind most local AI apps.

131.2KMIT—

常见问题

Jan 免费吗?

是的——Jan 是开源软件,采用 AGPL-3.0 许可证。商用前请确认软件及模型权重的许可条款。

Jan 支持 Windows、Mac 和 Linux 吗?

Jan 支持:Windows, macOS, Linux。

运行 Jan 需要什么配置?

RAM: 8 GB minimum, 16 GB+ recommended

如何安装 Jan?

1. Download Jan for your OS from jan.ai or GitHub Releases and install it. 2. Open the Hub, download a model and start chatting.

Jan 有哪些好的替代品?

常见替代品包括 GPT4All, Ollama, AnythingLLM, Open WebUI,详见本页对比表。