Jan is an open-source ChatGPT alternative that runs 100% offline on your computer. Built with TypeScript and Rust, it supports both local LLMs (Llama, Gemma, Qwen, Mistral) and cloud models (OpenAI, Anthropic, Mistral, Groq). Jan provides an OpenAI-compatible API server at localhost:1337 for integration with other applications.
License: Apache-2.0 (since May 2025)
Latest Version: 0.7.9 (March 23, 2026)
Website: jan.ai
GitHub: janhq/jan (41.2k ⭐)
- 🧠 Local AI Models - Download and run LLMs from HuggingFace (Llama, Gemma, Qwen, Mistral, DeepSeek)
- ☁️ Cloud Integration - Connect to OpenAI, Anthropic, Mistral, Groq, Google Gemini
- 🤖 Custom Assistants - Create specialized AI assistants for your tasks
- 🔌 OpenAI-Compatible API - Local server at
localhost:1337 for other applications
- 🔗 Model Context Protocol - MCP integration for agentic capabilities
- 🔒 Privacy First - Everything runs locally when you want it to
- 🖥️ Desktop Apps - Windows, macOS, Linux support
- 🎨 Modern UI - Clean, intuitive interface
- 📦 Model Hub - Built-in model discovery and download
- 🚀 MLX Backend - Apple Silicon acceleration (v0.7.7+)
- 👁️ Vision Support - Image recognition with Jan VL models
- 🛠️ Tool Calling - Function calling for agentic workflows
- Private AI Chat - 100% offline ChatGPT alternative
- Local LLM Development - Test and experiment with open-source models
- Self-hosted AI - Full control over AI infrastructure
- API Backend - Use OpenAI-compatible local server for applications
- Custom AI Assistants - Build task-specific assistants
- Enterprise AI - Apache-2.0 license for commercial use
| Component |
Technology |
| Backend |
Rust, TypeScript |
| Frontend |
TypeScript |
| Inference Engine |
llama.cpp, MLX (Apple Silicon) |
| Framework |
Tauri |
| API |
OpenAI-compatible REST API |
Language Breakdown:
- TypeScript: 72.4%
- Rust: 21.1%
- Swift: 2.0%
- Python: 1.9%
- JavaScript: 1.1%
| Requirement |
Details |
| OS |
macOS 13.6 or higher |
| RAM |
8GB (3B models), 16GB (7B), 32GB (13B) |
| Storage |
10GB+ free space |
| GPU |
Metal acceleration (Apple Silicon M1/M2/M3) |
| Requirement |
Details |
| OS |
Windows 10 or higher |
| CPU |
Intel Haswell+ or AMD equivalent (AVX2 support required) |
| RAM |
8GB (3B), 16GB (7B), 32GB (13B) |
| GPU |
6GB+ VRAM recommended (NVIDIA/AMD/Intel Arc) |
| Storage |
10GB+ free space |
| Requirement |
Details |
| OS |
Debian, Ubuntu, RHEL, Fedora, Arch, openSUSE |
| CPU |
x86_64 (amd64) |
| GPU |
Optional (NVIDIA CUDA, AMD ROCm) |
| Formats |
.deb, .rpm, AppImage, Flatpak |
- ✅ Apache-2.0 License (since May 2025) - Free for commercial use
- ✅ Open-source and self-hosted
- ✅ Active development (v0.7.9 - March 23, 2026)
- ✅ 41.2k+ GitHub stars, 2.6k forks, 7,736 commits
- ✅ 99 releases
- ✅ Desktop apps for Windows, macOS, Linux
- ✅ MLX backend for Apple Silicon (v0.7.7+)
- ✅ Vision support with Jan VL models
- ✅ MCP integration for agentic capabilities
¶ History and References
Any questions?
Feel free to contact us. Find all contact information on our contact page.
🆘 Stuck? Our team provides paid consulting for Jan setup, configuration, and troubleshooting. Get in touch.