Local runtime
Runs and manages models on private infrastructure.
Ollama
Local models with Ollama.
Ollama runs and manages AI models on infrastructure we control. Its API supports local workflows without making every task depend on a hosted model provider.
What it handles
Useful APIs
Supports native and OpenAI-compatible integrations.
Modern models
Supports chat, embeddings, vision, and tool use.
How we use it
We run Ollama on our AI server behind Open WebUI. It supports private experiments and workloads where local control matters.
AI applications