Jan

A desktop app that runs open language models offline on your computer, as a private ChatGPT replacement, with an optional local OpenAI-compatible server.

45.2k stars, 3.1k forks Rust On GitHub since August 2023

What is Jan?

Jan downloads models such as Llama, Gemma and Qwen from Hugging Face and runs them on your machine, with installers for Windows, macOS and Linux. You can also connect it to OpenAI, Anthropic, Mistral, Groq and other providers when you want a hosted model. Custom assistants handle repeated tasks, MCP support connects tools, and a local API server on port 1337 lets other applications use your models. Its interface comes in 13 languages.

Good fit if

  • You want private, offline chat on a laptop with a simple installer.
  • You want one app for both local and hosted models.

Look elsewhere if

Before you adopt it

Jan moved from AGPL-3.0 to the more permissive Apache-2.0 in May 2025, and nothing in it is paid. One developer writes most of the recent code.

Drafted with AI from the project's README and repository data, then checked against that data on 30 October 2026. Report a correction

Jan health: is it still maintained?

73 of 100, actively developed

  • Activity
    1,164 commits in the last 90 days, the latest on 30 October 2026.
    30 / 30
  • Contributors
    4 people wrote the latest 100 commits; the most active wrote 74% of them.
    9 / 20
  • Releases
    15 releases in the last 12 months; the latest, v0.8.8, on 28 October 2026.
    19 / 20
  • Replies to issues
    Too few recent issues from outside the team to measure, so this part gets a neutral score.
    10 / 20
  • Security practices
    No OpenSSF Scorecard for this repository yet, so this part gets a neutral score.
    5 / 10

Read from GitHub on 1 November 2026. How the score works

Jan license: is it open source?

Jan uses Apache-2.0, an open-source license approved by the OSI.

  1. August 2023First published on GitHub under AGPL-3.0.
  2. 20 May 2025Changed to Apache-2.0. Commit: chore: Jan's code is now under the Apache license (#5042)
  3. TodayApache-2.0.

How to run Jan yourself

Docker
No Docker files in the repository
Compose file
None in the repository
Setup effort
Not rated: no compose file to judge from
Kubernetes
No Helm chart in the repository
Desktop and mobile
Builds for macOS, Windows, Linux, including ARM in GitHub releases
Interface languages
13 languages

Install instructions: jan.ai or the README on GitHub.

Alternatives to Jan

  • OnyxOpen Source AI Platform - AI Chat with advanced features that works with every LLM 77 health · MIT · 33.1k stars
  • AnythingLLMStop renting your intelligence. Own it with AnythingLLM. Everything you need for a powerful local-first… 94 health · MIT · 67.8k stars
  • KoboldCppKoboldCpp - Run GGUF AI models locally with a KoboldAI UI. One File. Zero Install. 93 health · AGPL-3.0 · 12.1k stars
  • vLLMA high-throughput and memory-efficient inference and serving engine for LLMs 84 health · Apache-2.0 · 96k stars
  • DocsGPTPrivate AI platform for agents, assistants and enterprise search. Built-in Agent Builder, Deep research,… 84 health · MIT · 18.4k stars

All 36 projects in AI chat & local LLMs

Questions about Jan

Is Jan open source?

Yes. Jan is published under Apache-2.0, an OSI-approved open-source license.

Is Jan still maintained?

Its health score is 73 of 100 (actively developed). It had 1,164 commits in the last 90 days, the latest on 30 October 2026, and its latest release came out on 28 October 2026.

Did Jan change its license?

Yes. It moved from AGPL-3.0 to Apache-2.0 on 20 May 2025.

How do I run Jan?

You can run it as an app for macOS, Windows, Linux, including ARM. The README on GitHub has the exact steps.

What are the alternatives to Jan?

Close alternatives in the AI chat & local LLMs category include Onyx, AnythingLLM, KoboldCpp.