TuxNest · local-first AI engineering
Models
Choose the model runtime that fits the task instead of locking your workflow to one provider.
Built around control.
Minimal interface, explicit model choice, reviewable changes and evidence you can inspect.
01Local Ollama
Discover and use models running on localhost.
02Remote Ollama
Reach your own remote runtime through SSH tunneling.
03OpenAI-compatible
Point TuxNest at an explicit compatible endpoint when you choose.
04Model control
Selection stays visible and user-directed.
Local AI should feel local.
Your editor, your model runtime, your hardware and your approval remain first-class parts of the workflow.