Connect to locally hosted Large Language Models for offline AI processing.
Overview
The Local Model integration on StackAI lets you point any OpenAI-compatible endpoint — vLLM, Ollama, LM Studio, Text Generation Inference, llama.cpp servers, or a private GPU cluster — at the platform and use it as a first-class LLM node. It is essential for teams that cannot send data to public model APIs for regulatory or compliance reasons.
Top Use Cases
On-prem and air-gapped deployments
Use Local Model on StackAI to run AI workflows inside customer VPCs or air-gapped environments where data must never leave the network, while keeping the same drag-and-drop builder experience.
