Verified project record

janhq/jan

Jan is a desktop application that lets users download and run large language models locally or connect to cloud providers, maintaining data control without mandatory cloud dependence. It supports text prompts and provides an OpenAI-compatible local API for integration with other applications.

Project overview

Project type: MCP · Model Runtime
Use cases: Chat Assistants
Deployment: Refer to project documentation
License: License pending

Best for

General users who prefer a desktop GUI for running local models without coding requirements.
Developers needing an OpenAI-compatible local API at localhost:1337 for connecting other applications.

Key capabilities

Download and run LLMs (Llama, Gemma, Qwen, GPT-oss) locally from HuggingFace.
Connect to GPT models via OpenAI, Claude models via Anthropic, Mistral, Groq, MiniMax, and others.
Create specialized AI assistants for your tasks.
Local server at localhost:1337 for other applications.
MCP integration for agentic capabilities.

Limitations and risks

Specific RAM requirements scale with model size. macOS 13.6+ requires 8GB RAM for 3B models, 16GB for 7B, and 32GB for 13B. Windows 10+ requires GPU support for NVIDIA, AMD, or Intel Arc.

Getting started

Desktop installers are provided for all major platforms via direct download and app stores. The first success path is to download the installer for your OS, install the application, and open Jan.

Evidence and sources

GitHub project description: Jan is an open source alternative to ChatGPT that runs 100% offline on your computer.
README: Jan is bringing the best of open-source AI in an easy-to-use product. Download and run LLMs with full control and privacy.
README: The easiest way to get started is by downloading one of the following versions for your respective operating system:
README: Local AI Models: Download and run LLMs (Llama, Gemma, Qwen, GPT-oss etc.) from HuggingFace
README: Cloud Integration: Connect to GPT models via OpenAI, Claude models via Anthropic, Mistral, Groq, MiniMax, and others

Reviewed at: 2026-07-17T07:29:56Z