A desktop client that runs open-source LLMs like Llama and Mistral directly on consumer hardware. It provides an offline-capable chat interface compatible with OpenAI APIs for local execution.
Tech Stack
TypeScriptAI, ML & Data
Why jan?
• Runs offline on consumer GPU/CPU
• OpenAI API compatible server
• Cross-platform support
Limitations
• Requires high RAM/VRAM
• Slower than cloud inference
• Model management is manual
3/5/2026
Last Update
2,546
Forks
255
Issues
Other
License
Financial Leak Detected
Stop the "SaaS Tax"
Your team could be burning cash. Switching to jan instantly boosts your runway.
