explaingit

janhq/jan

📈 Trending★ 42,585TypeScriptAudience · developerComplexity · 3/5ActiveLicenseSetup · moderate

TLDR

Desktop app to download and run AI models locally on your computer with no internet needed, keeping your conversations private.

Mindmap

mindmap
  root((repo))
    What it does
      Run AI models locally
      Chat interface
      OpenAI-compatible API
      Tool use and actions
    How to use
      Download models
      Chat with models
      Connect to cloud APIs
      Build AI apps
    Tech stack
      TypeScript
      Tauri
      llama.cpp
    Use cases
      Private AI assistant
      Test AI apps locally
      Cut development costs
      Experiment offline
    Audience
      Developers
      Privacy-conscious users
      AI experimenters

Things people build with this

USE CASE 1

Run a private AI assistant on your computer that never sends data to external servers.

USE CASE 2

Test and develop AI-powered applications locally before deploying to paid cloud APIs.

USE CASE 3

Download open-source models from HuggingFace and experiment with different AI models without subscriptions.

USE CASE 4

Build applications that call a local OpenAI-compatible API running on your machine.

Tech stack

TypeScriptTaurillama.cppHuggingFaceRust

Getting it running

Difficulty · moderate Time to first run · 30min

Requires downloading large model files from HuggingFace (gigabytes) and building Tauri desktop app.

Open-source software allowing free use, modification, and distribution for any purpose including commercial use.

In plain English

Jan is an open-source desktop application that lets you download and run large language models, the kind of AI that powers ChatGPT, entirely on your own computer, with no internet connection required once the models are downloaded. The problem it solves is privacy and control: services like ChatGPT send your conversations to external servers, whereas Jan keeps everything local so your data never leaves your machine. With Jan, you browse and download models from HuggingFace, a platform that hosts open-source AI models. Once downloaded, models run locally using your computer's CPU or GPU. You can then chat with them through a user-friendly interface similar to ChatGPT. Jan also supports connecting to cloud AI providers like OpenAI, Anthropic Claude, Mistral, and Groq if you prefer to use remote models for tasks requiring more power than your local hardware can provide. Beyond basic chat, Jan runs a local OpenAI-compatible API server on your machine at localhost:1337, which means other applications can send requests to it as if it were the real OpenAI API. This enables developers to build or test AI-powered apps against locally running models before using the paid cloud API. Jan also supports the Model Context Protocol (MCP), which allows the AI to take actions, browsing the web, reading files, or calling tools, rather than only generating text. Someone would use Jan when they want a private, offline AI assistant, when they are developing AI applications and want to cut costs during testing, or when they simply want to experiment with open-source models without a subscription. It runs on Windows, macOS, and Linux. The tech stack is TypeScript for the application frontend, Tauri (a Rust-based framework) for the native desktop shell, and llama.cpp under the hood for running the actual AI models.

Copy-paste prompts

Prompt 1
How do I set up Jan to run open-source language models locally on my computer?
Prompt 2
Show me how to use Jan's OpenAI-compatible API at localhost:1337 to test my AI application before using the real OpenAI API.
Prompt 3
What models can I download from HuggingFace through Jan, and how do I choose between running them on CPU vs GPU?
Prompt 4
How do I enable the Model Context Protocol in Jan so my AI can browse the web and call tools?
Prompt 5
Can I use Jan to connect to cloud providers like OpenAI or Claude while also running local models?
Open on GitHub → Explain another repo

Generated 2026-05-18 · Model: sonnet-4-6 · Verify against the repo before relying on details.