Jan

An open-source desktop assistant that runs models locally by default and can be pointed at a hosted one when you choose.

Hybrid
Active
Allowed adult content
Open source

Website Source

At a glance

Where it runs: HybridBoth: run it yourself, or use the hosted version.
Adult content: AllowedAdult content is permitted within the published rules.
Trains on your content: NoYour content is not used to train models.
Status: ActiveMaintained and working today.
Account needed: No
Licence: Apache-2.0
Cost: Free and open source.
What it keeps: Conversations are stored in a local folder you can read and delete.

What it takes to run

Graphics memory: No GPU needed
System memory: 8 GB, 16 GB recommended
Disk: about 20 GB
Runs on: Linux, macOS, Windows

Find what fits your machine on the tools page — pick your hardware from the first menu.

The pitch is a ChatGPT-shaped application that happens to be open source and offline by default. Download a model in the app, talk to it, and nothing leaves the machine unless you deliberately configure a remote provider.

Being open source is the practical difference from LM Studio: the privacy claim is checkable.

Worth knowing before you start

Younger than the alternatives Fewer years of bug reports behind it than llama.cpp-based tools.

What it does

Offline by default
Local API server
Can connect to remote providers
Conversations stored as readable files

Models it runs

How it relates to other tools

an alternative to LM Studio

Signs of life

Checked automatically. These are the only figures on this page a machine wrote, and they say when they were taken.

Last answered: Yes, 3 hours ago Its website responded when we asked.
Stars on GitHub: 44,488 3,028 forks.
Last commit: 4 hours ago2026-09-16 02:04 UTC
Latest release: v0.8.4
Archived copy: Wayback Machine A snapshot, in case this one stops answering.