Jan
Jan’s Goal
Section titled “Jan’s Goal”Jan’s goal is to build superintelligence that you can self-host and use locally.
What is Jan?
Section titled “What is Jan?”Jan is an open-source AI ecosystem that runs on your hardware.
- Available Today: Jan Desktop - run AI models on your computer with zero setup
- Coming Soon: Complete ecosystem with specialized models, tools, and cross-device sync
The Stack
Section titled “The Stack”Models: Specialized AI models trained for real tasks (search, analysis, writing) Tools: Browser automation, web search, memory systems via MCP Applications: Desktop (now), Web/Mobile/Server (coming 2025)
Everything works together. Everything runs where you want it.
Core Features
Section titled “Core Features”Run Models Locally
Section titled “Run Models Locally”- Download any GGUF model from Hugging Face
- Use our Jan models optimized for specific tasks
- Automatic GPU acceleration (NVIDIA/AMD/Intel)
- OpenAI-compatible API at
localhost:1337
Connect to Cloud (Optional)
Section titled “Connect to Cloud (Optional)”- Your API keys for OpenAI, Anthropic, etc.
- Jan.ai cloud models (coming soon)
- Self-hosted Jan Server
Extend with Tools
Section titled “Extend with Tools”- Web search via MCP
- Browser automation
- File parsing and analysis
- Custom tool development
Architecture
Section titled “Architecture”Jan is built on:
- Llama.cpp for inference
- Model Context Protocol for tools
- Local-first data storage in
~/jan
Why Jan?
Section titled “Why Jan?”| Feature | Other AI Platforms | Jan |
|---|---|---|
| Deployment | Their servers only | Your device, your servers, or our cloud |
| Models | One-size-fits-all | Specialized models for specific tasks |
| Data | Stored on their servers | Stays on your hardware |
| Cost | Monthly subscription | Free locally, pay for cloud |
| Extensibility | Limited APIs | Full ecosystem with MCP tools |
Development Philosophy
Section titled “Development Philosophy”- Local First: Everything works offline. Cloud is optional.
- User Owned: Your data, your models, your compute.
- Built in Public: Watch our models train. See our code. Track our progress.
System Requirements
Section titled “System Requirements”Minimum: 8GB RAM, 10GB storage Recommended: 16GB RAM, NVIDIA GPU, 50GB storage Supported: Windows 10+, macOS 12+, Linux (Ubuntu 20.04+)
What’s Next?
Section titled “What’s Next?”When will mobile/web versions launch?
- Jan Web: Beta Q1 2025
- Jan Mobile: Q4 2025
- Jan Server: Q3 2025
All versions will sync seamlessly with your desktop.
What models are available?
Now:
- Any GGUF model from Hugging Face
- Cloud models via API keys (OpenAI, Anthropic, etc.)
Coming Q1 2025:
- Jan-Search: Optimized for web search and synthesis
- Jan-Write: Creative and technical writing
- Jan-Analyze: Data analysis and reasoning
How does Jan make money?
- Local use: Always free
- Cloud features: Optional paid services (coming 2025)
- Enterprise: Self-hosted deployment and support
We don’t sell your data. We sell software and services.
Can I contribute?
Yes. Everything is open:
- GitHub - Code contributions
- Model Training - See how we train
- Discord - Join discussions
- Model Testing - Help evaluate models
Is this just another ChatGPT wrapper?
No. We’re building:
- Our own models trained for specific tasks
- Complete local AI infrastructure
- Tools that extend model capabilities
- An ecosystem that works offline
ChatGPT is one model behind an API. Jan is a complete AI platform you own.
What about privacy?
Local mode: Your data never leaves your device. Period. Cloud mode: You choose when to use cloud features. Clear separation.
See our Privacy Policy.
Get Started
Section titled “Get Started”- Install Jan Desktop - Your AI workstation
- Explore Models - Download and configure
- Learn the API - Build with Jan
Questions? Join our Discord or check GitHub roadmap.