Overview
Jan is an open-source desktop app for running AI models with full control and privacy. You download open models such as Llama, Gemma, Qwen and GPT-oss from Hugging Face and run them locally, or connect to cloud models from OpenAI, Anthropic, Mistral, Groq and others. It runs on macOS, Windows and Linux.
What it does well
Jan lets you create custom assistants for specific tasks, supports MCP for agent tools, and runs a local OpenAI-compatible API server so other apps can use your local models. Everything stays on your machine when you use local models.
Why it’s in the collection
Jan is one of the easiest ways to run AI models on your own computer, with a clean chat app and the option to mix in cloud models. It is Apache-licensed.
On GitHub
- Stars
- 0
- Forks
- 0
- Commits
- 0
- Repository
- janhq/jan
Languages
- Rust 55.9%
- TypeScript 39.5%
- Python 1.6%
- JavaScript 1.3%
- Other 1.7%
Compared with
ChatGPTOpenAI's AI chat assistant.
LM StudioDesktop app for running local language models.
OllamaNo. 079Open-source tool for running models locally.
See every open-source alternative to ChatGPT and LM Studio in the collection.
