NxJan

Local AI chat — run LLMs on your machine with full control and privacy.

Bug reports · Releases

NxJan brings open-source AI models into a desktop app you can run locally. Download models from HuggingFace, chat offline, and connect cloud providers when you need them.

• Local AI Models: Download and run LLMs (Llama, Gemma, Qwen, GPT-oss, etc.)
• Cloud Integration: OpenAI, Anthropic, Mistral, Groq, MiniMax, and more
• Custom Assistants: Create specialized AI assistants for your tasks
• OpenAI-Compatible API: Local server at localhost:1337
• Model Context Protocol: MCP integration for agentic workflows
• Privacy First: Run everything locally when you want to

• Node.js ≥ 20.0.0
• Yarn ≥ 4.5.3
• Make ≥ 3.81
• Rust (for Tauri)
• (macOS Apple Silicon only) MetalToolchain xcodebuild -downloadComponent MetalToolchain

git clone https://github.com/Nxkoo/NxJan
cd NxJan
make dev

Make targets:

• make dev — development setup and launch
• make build — production build
• make test — tests and linting
• make clean — clean build artifacts

yarn install
yarn build
yarn dev

• macOS: 13.6+ (8GB RAM for 3B models, 16GB for 7B, 32GB for 13B)
• Windows: 10+ with GPU support for NVIDIA/AMD/Intel Arc
• Linux: Most distributions; GPU acceleration available

Contributions welcome. Open an issue or PR on GitHub.

Apache 2.0

NxJan © 2026 Nxkoo.

Includes software from Jan (Menlo Research), licensed under Apache 2.0.

Built with:

• Llama.cpp
• Tauri
• Scalar