33rd of 4 in Desktop AI apps
jan
Desktop app that runs local models or cloud APIs, with a local server
Documentation ↗
(opens in a new tab)Website ↗
(opens in a new tab)Repository on GitHub ↗
(opens in a new tab)
- Stars
- 44.9k
- License
- custom license
- Last commit
- Oct 2026
- Last release
- Oct 2026
- Language
- Rust
40,537 on 24 Mar 202644,941 on 13 Oct 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
Jan is a Tauri desktop app for Windows, macOS and Linux that downloads LLMs from Hugging Face and runs them through a bundled llama.cpp engine. It can also connect to cloud providers such as OpenAI, Anthropic, Mistral and Groq. It exposes an OpenAI-compatible API at localhost:1337 and supports MCP for agent tools.
Who it is for: Users who want a local ChatGPT-style desktop app with a local API
Strengths
- Runs local models and cloud providers from one app
- OpenAI-compatible local server at localhost:1337 for other applications
- MCP integration for agentic tool use
- Engine variants for CPU, Vulkan, Metal, CUDA and ROCm builds
Weaknesses
- Desktop only; no Docker image or multi-user web deployment
- README says Apache 2.0, but license detection reports NOASSERTION
- Source build needs Node, Yarn, Rust; Windows also needs LLVM, Ninja, CMake
- Linux Arm64 is a linked how-to, not a packaged download
What it needs
- RAM ≥ 8 GB
- GPU optional
- Models: GGUF via llama.cpp, Hugging Face models, OpenAI, Anthropic, Mistral
- port 1337
Head to head
Also in Desktop AI apps
See all 4| Rank | Project | Score |
|---|---|---|
| 1 | deep-live-camReal-time webcam face swap from a single source image | 75 out of 100 |
| 2 | cherry-studioCross-platform desktop chat client for many cloud and local LLM providers | 75 out of 100 |
| #4 | chatboxDesktop and mobile chat client for OpenAI, Claude, Gemini and Ollama models | 59 out of 100 |