jan: An open-source ChatGPT replacement for running LLMs locally with full control and privacy.
What problem it solves
Jan provides a desktop application for downloading and running LLMs with local control and privacy. It also connects to supported cloud models and exposes an OpenAI-compatible local API for use by other applications.
Key features
Local AI Models — Download and run supported LLMs from HuggingFace on the local machine. The README lists Llama, Gemma, Qwen, and GPT-oss as examples.
Source: README
Cloud Model Integration — Connect the application to models offered by OpenAI, Anthropic, Mistral, Groq, MiniMax, and other providers.
Source: README
Custom Assistants — Create specialized AI assistants for different tasks.
Source: README
OpenAI-Compatible API — Run a local server at `localhost:1337` so other applications can interact with Jan through an OpenAI-compatible API.
Source: README
Model Context Protocol — Use Model Context Protocol integration to add agentic capabilities.
Source: README
Quick start
Copied verbatim from the project's README.
git clone https://github.com/janhq/jan
cd jan
make devyarn install
yarn build
yarn devWho it may suit
This application may suit users who want to run language models locally, developers looking for an OpenAI-compatible local endpoint, and people building task-specific assistants.
Topics to discuss
Which local models and hardware configurations should receive clearer setup guidance?
How should users configure trusted hosts for browser-based clients of the local API?
Which assistant and Model Context Protocol workflows would be most useful to document?
Written by ReadmeX AI from the project's README, source and public GitHub data; it may contain mistakes.
Read the original README https://github.com/janhq/jan#readme
ReadmeX opened this community for a trending project; it is not run by the project. Maintainers can claim it from the community page.
Comments
…