janhq /jan
Jan is an open source alternative to ChatGPT that runs 100% offline on your computer.
★ 45,731⑂ 3,175👁 227⑃ 4,957● 4,139▤ 108
+5
Daily
+110
Weekly
45,731
stars
3,175
forks
227
watchers
4,957
prs
4,139
issues
108
releases
README
Jan - Open-source ChatGPT replacement
English ·
中文 ·
日本語
Getting Started
- Community
- Changelog
- Bug reports
Jan is bringing the best of open-source AI in an easy-to-use product. Download and run LLMs with full control and privacy.
Installation
The easiest way to get started is by downloading one of the following versions for your respective operating system:
Platform
Download
Windows
jan.exe
macOS
jan.dmg
Linux (deb)
jan.deb
Linux (AppImage)
jan.AppImage
Linux (Arm64)
How-to
Download from jan.ai or GitHub Releases.
Features
- Local AI Models: Download and run LLMs (Llama, Gemma, Qwen, GPT-oss etc.) from HuggingFace
- Cloud Integration: Connect to GPT models via OpenAI, Claude models via Anthropic, Mistral, Groq, MiniMax, and others
- 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
Build from Source
For those who enjoy the scenic route:
Prerequisites
- Node.js ≥ 20.0.0
- Yarn ≥ 4.5.3
- Make ≥ 3.81
- Rust (for Tauri)
- (macOS Apple Silicon only) MetalToolchain xcodebuild -downloadComponent MetalToolchain
Run with Make
bash
git clone https://github.com/janhq/jan
cd jan
make dev
This handles everything: installs dependencies, builds core components, and launches the app.
Available make targets:
- make dev - Full development setup and launch
- make build - Production build
- make test - Run tests and linting
- make clean - Delete everything and start fresh
Manual Commands
bash
yarn install
yarn build
yarn dev
Building on Windows
Run make dev from Git Bash (installed with Git for Windows) — make dispatches its recipes through sh, so a plain cmd.exe won't work.
You do not need a "Native Tools Command Prompt for VS 2022". The bundled llama.cpp engine builds with Ninja + clang-cl, and clang-cl locates the MSVC toolchain and Windows SDK on its own. What has to be installed (and on PATH for ninja/clang-cl/cmake):
- Visual Studio 2022 Build Tools (MSVC x64 workload + Windows SDK)
- LLVM (provides clang-cl)
- Ninja
- CMake
- CUDA Toolkit — only for JAN_ENGINE_VARIANT=cuda12/cuda13 builds
Engine variants are picked with JAN_ENGINE_VARIANT (tokens: cpu, vulkan, metal, cuda12, cuda13, hip/rocm, joined by -), e.g.:
bash
make dev JAN_ENGINE_VARIANT=cuda13
"nvcc fatal : Could not open output file ...fattn-...cu.obj.d" during tauri-plugin-llamacpp(build) means the build path crossed Windows' 260-character MAX_PATH limit — nvcc does not honor the long-path opt-in. The build script now detects this and automatically relocates the llama.cpp build tree tTop issues
#7728bug: Jan does not download models in version v0.7.832 comments · 2026-03-12#8373Build error: App built from tarball has GUI broken18 comments · 2026-07-01#6017discussion: No default backend included16 comments · 2025-07-31#6166idea: Voice input using local / remote whisper14 comments · 2025-08-13#8266bug: AMD ROCm GPU not recognized in flatpak linux12 comments · 2026-06-02#7561bug: A thinking model completely freezes the app12 comments · 2026-02-26#7461bug: Unable to start default Jan model in macOS 15.7.312 comments · 2026-02-04#8530Bug: Thinking mode intermittent — reasoning block appears inconsistently even with mode set to ON or AUTO, regenerating fixes it11 comments · 2026-07-25
Discussions
#9686mcp-slim: Zero-dependency MCP stdio proxy for Jan Desktop (-50% to -98% schema tokens & local GGUF tool-call fixes)0 comments · 2026-11-12#9620How do I install REA or Universal modders?0 comments · 2026-11-07#9528Multimodal RAG0 comments · 2026-11-02#9512Podcast research in Jan: choose the file scope before adding your notes0 comments · 2026-10-30#9433Manually unload a model2 comments · 2026-10-24#9417It would be great if Jan.ai didn't require an internet connection to use local tools/MCP1 comments · 2026-10-21#9370Is there a way to disable JAN's ability to run terminal commands?1 comments · 2026-10-20#9309Concise user guide in French0 comments · 2026-10-17
Latest release
0.8.8 v0.8.8 2026-10-28Jan v0.8.8: security fixes, llama.cpp 0.7.0, and Trusted Hosts for the local API A security update to v0.8.7. We recommend updating. Your data and settings carry over; a few behaviours change, listed under What you might notice. Security - Links in chat open in your browser. Links in model replies, tool results, model cards and release notes now always open in your system browser, never inside Jan's window. Links that aren't web or email links are shown as plain text. - The local API server checks where browser requests come from. A web page can only call it if its origin is trusted: the s