OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
Local & Self-hosted AI

Jan

Jan is an open-source desktop application for downloading and running large language models locally, with an offline chat interface, custom assistants, cloud-provider connections and a local OpenAI-compatible server.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Jan — OpenViST project profile in Local & Self-hosted AI.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use Jan when you want a desktop workflow for local model downloads and chat, or need a local model server for another application. Choose its documented cloud-provider connections when you want to use hosted models instead.

Who it is for

  • People who want to chat with language models running on their own computer.
  • Users who want a desktop interface to download and experiment with open models.
  • Developers connecting other applications to a local model server.

Documented uses

  • Download and run models such as Llama, Gemma, Qwen and GPT-oss from Hugging Face.
  • Use a local chat assistant offline.
  • Create specialized assistants for particular tasks.
  • Connect supported cloud model providers when using hosted models.
  • Serve a local model to other applications through an OpenAI-compatible endpoint at localhost:1337.
Before you choose

Requirements & limits

Desktop downloads are listed for Windows, macOS and Linux. The README identifies Apache 2.0 as the license.

  • Local models run on the computer; cloud integrations connect to external providers, so the two workflows have different data paths.
  • Model size affects the stated memory guidance: Jan lists 8 GB RAM for 3B models, 16 GB for 7B and 32 GB for 13B on macOS.
  • The project lists macOS 13.6 or later and Windows 10 or later; GPU acceleration details vary by platform.
  • Building from source requires Node.js 20 or later, Yarn 4.5.3 or later, Make 3.81 or later and Rust.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Build and launch Jan from source with Make

Set up the Jan development project and launch the app using its Make target.

Before you start

  • Node.js 20.0.0 or later.
  • Yarn 4.5.3 or later.
  • Make 3.81 or later.
  • Rust for Tauri.
  • On macOS Apple Silicon, MetalToolchain, installed with xcodebuild -downloadComponent MetalToolchain.

Steps

  1. Clone the repository with the command below.

    Documented command
    git clone https://github.com/janhq/jan

  2. Change into the repository directory with cd jan.

  3. Run the command below to install dependencies, build core components, and launch the app.

    Documented command
    make dev

Expected outcome

The Make target handles dependency installation and core builds, then launches the app.

Guide limitations

  • The README does not detail model download or chat steps.
  • Windows builds require additional tooling; CUDA Toolkit is required only for cuda12 or cuda13 engine builds.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
14 October 2026
Original website title
janhq/jan · Official homepage title · retained in its source language
How we review sourcesSuggest a correction