Applied AI·Local and self-hosted inference
you pull a model with one command and get a local HTTP API shaped like the hosted one, which is right for your scripts and not for a fleet.
Ollama
Draft summary, pending review
The developer-friendly local runner: pulls models from a registry, manages them, and exposes a local HTTP API mirroring the hosted-API shape. Built on llama.cpp. The right tool for your scripts and experiments; capable single-machine serving, not a fleet-scale server.