Jan
App : A product you use directly
Open-source alternative to LM Studio, with zero telemetry.
The most privacy-respecting option for one-click local chat.
Security reflects where data goes, requested permissions and incidents on record at the verification date. It is not a guarantee of zero risk: check the deployment mode and the connections you enable.
What it does, concretely
Most AI chat tools send your conversations to remote servers, raising legitimate privacy concerns. Jan lets you run language models directly on your computer, with no data leaving your machine.
In practice, you download the app, choose a model from those available (Llama, Gemma, Qwen, DeepSeek and others), and start chatting. Jan can also connect to online services such as OpenAI, Anthropic or Mistral if you prefer. It also runs a local server compatible with the OpenAI API on port 1337, allowing other applications to connect to it.
Jan is aimed at anyone who wants to use a conversational AI without entrusting their data to a third party: professionals handling sensitive information, developers looking to integrate a local model into their projects, or privacy-conscious users.
That said, Jan requires significant hardware resources: at least 8 GB of RAM for a 3-billion-parameter model, 16 GB for a 7-billion model, and 32 GB for a 13-billion model. Users with less powerful machines or those looking for a setup-free experience may find it harder to get the most out of it.
What it offers
- ·Download and run open-source models (Llama, Gemma, Qwen, DeepSeek, etc.) directly from HuggingFace, with no internet connection required during use.
- ·Optional connection to cloud services such as OpenAI, Anthropic, Mistral or Groq to use online models from the same interface.
- ·Local server compatible with the OpenAI API on port 1337, allowing other applications to connect to Jan as they would to any OpenAI service.
- ·Creation of custom assistants tailored to specific tasks.
- ·Model Context Protocol (MCP) integration for agentic capabilities.
- ·No telemetry: no data is collected or sent to external servers.
- ·Available on Windows (including the Microsoft Store), macOS and Linux (.deb packages, AppImage and Flathub).
In practice
- Price
- Free
- Commercial use
- Commercial use: yes
- Available on
- macos, windows, linux
- Licence
- Apache-2.0
Security and data
- Rating
- Security: nothing to flag
- Your data
- Data stays local
- Maintenance
- Active
- Last release
- 20 October 2026
Links and repository checked on 25 October 2026 · added on 1 September 2023