Jan

Offline desktop ChatGPT alternative that runs models on each employee's computer.

Active Private ChatGPT-style chat Apache-2.0

Quick answer

Jan is an offline desktop ChatGPT alternative that runs models on each employee's computer, listed under Private ChatGPT-style chat. A typical small-business use: staff who handle confidential files and need AI without any upload. It runs on each user's own computer (official minimum 8 GB RAM · 10 GB disk (recommended 16 GB RAM)), so there is no server to rent. License: Apache-2.0, which allows internal business use.

Last updated · facts verified against official docs on · sources

GitHub stars45.0k
Forks3.1k
Latest releasev0.8.7Oct 20, 2026
Last commitOct 21, 2026
Est. server costNone (desktop)

Activity data comes from GitHub and was last refreshed Oct 22, 2026.

What is Jan?

Jan is a desktop app for Windows, macOS and Linux that downloads and runs open models locally and keeps all chats on the machine. It can also connect to cloud APIs. There is no server to host; each person installs it on their own computer.

Where it fits in a 10–200 person business

  • Staff who handle confidential files and need AI without any upload
  • Offline AI on laptops for travel or field work
  • Trying local models before investing in a GPU server

These use cases are our editorial suggestions, not claims made by the project.

Can a business use Jan? (license)

LicenseApache-2.0
TypePermissive: MIT / Apache-2.0: use, modify and sell with few obligations.
Internal business useAllowed under the license text
What to watchPermissive. Internal and commercial use allowed; keep license and notices.

This is a plain-English summary of the license text, not legal advice. Third-party models you run with it have their own licenses.

What hardware does Jan need?

Minimum8 GB RAM · 10 GB disk
Recommended16 GB RAM
GPU6 GB VRAM minimum for GPU acceleration

Per-computer requirements (Linux page). The CPU must support AVX2 (Intel Haswell 2013+, AMD Excavator 2015+).

Source: docs.jan.ai/desktop/install/linux

How much does it cost to host Jan per month?

Runs on each user's own computer, so there is no server to rent.

How to deploy Jan

Method: Desktop installer

# Download the installer for your OS from https://www.jan.ai
# Debian/Ubuntu example:
sudo apt-get install ./Jan_{version}_amd64.deb

From the official instructions: docs.jan.ai/desktop/install/linux. Always check the source for the current version before you run it.

Known gotchas when self-hosting Jan

  • The .deb package is not updated by the in-app updater; only the AppImage auto-updates. source
  • CPUs without AVX2 are not supported. source

Alternatives in Private ChatGPT-style chat

Jan FAQ

How much RAM does Jan need?

The official minimum is 8 GB RAM · 10 GB disk. The recommended spec is 16 GB RAM. Per-computer requirements (Linux page). The CPU must support AVX2 (Intel Haswell 2013+, AMD Excavator 2015+).

Does Jan need a GPU?

6 GB VRAM minimum for GPU acceleration

How much does it cost to self-host Jan?

The software is free to download. It runs on each user's own computer, so there is no server to rent.

Is Jan free for commercial use?

Jan is licensed under Apache-2.0 (Permissive). Internal business use is allowed under the license text. Permissive. Internal and commercial use allowed; keep license and notices. This is a summary, not legal advice.

What are common problems when self-hosting Jan?

The .deb package is not updated by the in-app updater; only the AppImage auto-updates. CPUs without AVX2 are not supported.

Is Jan still maintained?

Yes, it is actively developed. Last commit: Oct 21, 2026. Latest release: v0.8.7 (Oct 20, 2026). Checked Oct 22, 2026.

How do I install Jan?

The official method is Desktop installer. The exact commands are in the "How to deploy" section above and in the official instructions: https://docs.jan.ai/desktop/install/linux

What are self-hosted alternatives to Jan?

Other apps in Private ChatGPT-style chat: Open WebUI, LobeHub (LobeChat), LibreChat.

Sources

Facts on this page were checked against the project's own repository and docs on 2026-10-22. Spotted something out of date? Tell us.